| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_DCACHE_H #define __LINUX_DCACHE_H #include <linux/atomic.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/rculist_bl.h> #include <linux/spinlock.h> #include <linux/seqlock.h> #include <linux/cache.h> #include <linux/rcupdate.h> #include <linux/lockref.h> #include <linux/stringhash.h> #include <linux/wait.h> struct path; struct vfsmount; /* * linux/include/linux/dcache.h * * Dirent cache data structures * * (C) Copyright 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ #define IS_ROOT(x) ((x) == (x)->d_parent) /* The hash is always the low bits of hash_len */ #ifdef __LITTLE_ENDIAN #define HASH_LEN_DECLARE u32 hash; u32 len #define bytemask_from_count(cnt) (~(~0ul << (cnt)*8)) #else #define HASH_LEN_DECLARE u32 len; u32 hash #define bytemask_from_count(cnt) (~(~0ul >> (cnt)*8)) #endif /* * "quick string" -- eases parameter passing, but more importantly * saves "metadata" about the string (ie length and the hash). * * hash comes first so it snuggles against d_parent in the * dentry. */ struct qstr { union { struct { HASH_LEN_DECLARE; }; u64 hash_len; }; const unsigned char *name; }; #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } extern const struct qstr empty_name; extern const struct qstr slash_name; struct dentry_stat_t { long nr_dentry; long nr_unused; long age_limit; /* age in seconds */ long want_pages; /* pages requested by system */ long nr_negative; /* # of unused negative dentries */ long dummy; /* Reserved for future use */ }; extern struct dentry_stat_t dentry_stat; /* * Try to keep struct dentry aligned on 64 byte cachelines (this will * give reasonable cacheline footprint with larger lines without the * large memory footprint increase). */ #ifdef CONFIG_64BIT # define DNAME_INLINE_LEN 32 /* 192 bytes */ #else # ifdef CONFIG_SMP # define DNAME_INLINE_LEN 36 /* 128 bytes */ # else # define DNAME_INLINE_LEN 40 /* 128 bytes */ # endif #endif #define d_lock d_lockref.lock struct dentry { /* RCU lookup touched fields */ unsigned int d_flags; /* protected by d_lock */ seqcount_spinlock_t d_seq; /* per dentry seqlock */ struct hlist_bl_node d_hash; /* lookup hash list */ struct dentry *d_parent; /* parent directory */ struct qstr d_name; struct inode *d_inode; /* Where the name belongs to - NULL is * negative */ unsigned char d_iname[DNAME_INLINE_LEN]; /* small names */ /* Ref lookup also touches following */ struct lockref d_lockref; /* per-dentry lock and refcount */ const struct dentry_operations *d_op; struct super_block *d_sb; /* The root of the dentry tree */ unsigned long d_time; /* used by d_revalidate */ void *d_fsdata; /* fs-specific data */ union { struct list_head d_lru; /* LRU list */ wait_queue_head_t *d_wait; /* in-lookup ones only */ }; struct list_head d_child; /* child of parent list */ struct list_head d_subdirs; /* our children */ /* * d_alias and d_rcu can share memory */ union { struct hlist_node d_alias; /* inode alias list */ struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; } __randomize_layout; /* * dentry->d_lock spinlock nesting subclasses: * * 0: normal * 1: nested */ enum dentry_d_lock_class { DENTRY_D_LOCK_NORMAL, /* implicitly used by plain spin_lock() APIs. */ DENTRY_D_LOCK_NESTED }; struct dentry_operations { int (*d_revalidate)(struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); int (*d_compare)(const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(const struct dentry *); int (*d_init)(struct dentry *); void (*d_release)(struct dentry *); void (*d_prune)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, const struct inode *); } ____cacheline_aligned; /* * Locking rules for dentry_operations callbacks are to be found in * Documentation/filesystems/locking.rst. Keep it updated! * * FUrther descriptions are found in Documentation/filesystems/vfs.rst. * Keep it updated too! */ /* d_flags entries */ #define DCACHE_OP_HASH 0x00000001 #define DCACHE_OP_COMPARE 0x00000002 #define DCACHE_OP_REVALIDATE 0x00000004 #define DCACHE_OP_DELETE 0x00000008 #define DCACHE_OP_PRUNE 0x00000010 #define DCACHE_DISCONNECTED 0x00000020 /* This dentry is possibly not currently connected to the dcache tree, in * which case its parent will either be itself, or will have this flag as * well. nfsd will not use a dentry with this bit set, but will first * endeavour to clear the bit either by discovering that it is connected, * or by performing lookup operations. Any filesystem which supports * nfsd_operations MUST have a lookup function which, if it finds a * directory inode with a DCACHE_DISCONNECTED dentry, will d_move that * dentry into place and return that dentry rather than the passed one, * typically using d_splice_alias. */ #define DCACHE_REFERENCED 0x00000040 /* Recently used, don't discard. */ #define DCACHE_DONTCACHE 0x00000080 /* Purge from memory on final dput() */ #define DCACHE_CANT_MOUNT 0x00000100 #define DCACHE_GENOCIDE 0x00000200 #define DCACHE_SHRINK_LIST 0x00000400 #define DCACHE_OP_WEAK_REVALIDATE 0x00000800 #define DCACHE_NFSFS_RENAMED 0x00001000 /* this dentry has been "silly renamed" and has to be deleted on the last * dput() */ #define DCACHE_COOKIE 0x00002000 /* For use by dcookie subsystem */ #define DCACHE_FSNOTIFY_PARENT_WATCHED 0x00004000 /* Parent inode is watched by some fsnotify listener */ #define DCACHE_DENTRY_KILLED 0x00008000 #define DCACHE_MOUNTED 0x00010000 /* is a mountpoint */ #define DCACHE_NEED_AUTOMOUNT 0x00020000 /* handle automount on this dir */ #define DCACHE_MANAGE_TRANSIT 0x00040000 /* manage transit from this dirent */ #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) #define DCACHE_LRU_LIST 0x00080000 #define DCACHE_ENTRY_TYPE 0x00700000 #define DCACHE_MISS_TYPE 0x00000000 /* Negative dentry (maybe fallthru to nowhere) */ #define DCACHE_WHITEOUT_TYPE 0x00100000 /* Whiteout dentry (stop pathwalk) */ #define DCACHE_DIRECTORY_TYPE 0x00200000 /* Normal directory */ #define DCACHE_AUTODIR_TYPE 0x00300000 /* Lookupless directory (presumed automount) */ #define DCACHE_REGULAR_TYPE 0x00400000 /* Regular file type (or fallthru to such) */ #define DCACHE_SPECIAL_TYPE 0x00500000 /* Other file type (or fallthru to such) */ #define DCACHE_SYMLINK_TYPE 0x00600000 /* Symlink (or fallthru to such) */ #define DCACHE_MAY_FREE 0x00800000 #define DCACHE_FALLTHRU 0x01000000 /* Fall through to lower layer */ #define DCACHE_NOKEY_NAME 0x02000000 /* Encrypted name encoded without key */ #define DCACHE_OP_REAL 0x04000000 #define DCACHE_PAR_LOOKUP 0x10000000 /* being looked up (with parent locked shared) */ #define DCACHE_DENTRY_CURSOR 0x20000000 #define DCACHE_NORCU 0x40000000 /* No RCU delay for freeing */ extern seqlock_t rename_lock; /* * These are the low-level FS interfaces to the dcache.. */ extern void d_instantiate(struct dentry *, struct inode *); extern void d_instantiate_new(struct dentry *, struct inode *); extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *); extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op); /* allocate/de-allocate */ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); extern struct dentry * d_alloc_anon(struct super_block *); extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *, wait_queue_head_t *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); extern struct dentry * d_exact_alias(struct dentry *, struct inode *); extern struct dentry *d_find_any_alias(struct inode *inode); extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); extern void shrink_dcache_sb(struct super_block *); extern void shrink_dcache_parent(struct dentry *); extern void shrink_dcache_for_umount(struct super_block *); extern void d_invalidate(struct dentry *); /* only used at mount-time */ extern struct dentry * d_make_root(struct inode *); /* <clickety>-<click> the ramfs-type tree */ extern void d_genocide(struct dentry *); extern void d_tmpfile(struct dentry *, struct inode *); extern struct dentry *d_find_alias(struct inode *); extern void d_prune_aliases(struct inode *); /* test whether we have any submounts in a subdir tree */ extern int path_has_submounts(const struct path *); /* * This adds the entry to the hash queues. */ extern void d_rehash(struct dentry *); extern void d_add(struct dentry *, struct inode *); /* used for rename() and baskets */ extern void d_move(struct dentry *, struct dentry *); extern void d_exchange(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); /* appendix may either be NULL or be used for transname suffixes */ extern struct dentry *d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seq); static inline unsigned d_count(const struct dentry *dentry) { return dentry->d_lockref.count; } /* * helper function for dentry_operations.d_dname() members */ extern __printf(4, 5) char *dynamic_dname(struct dentry *, char *, int, const char *, ...); extern char *__d_path(const struct path *, const struct path *, char *, int); extern char *d_absolute_path(const struct path *, char *, int); extern char *d_path(const struct path *, char *, int); extern char *dentry_path_raw(struct dentry *, char *, int); extern char *dentry_path(struct dentry *, char *, int); /* Allocation counts.. */ /** * dget, dget_dlock - get a reference to a dentry * @dentry: dentry to get a reference to * * Given a dentry or %NULL pointer increment the reference count * if appropriate and return the dentry. A dentry will not be * destroyed when it has references. */ static inline struct dentry *dget_dlock(struct dentry *dentry) { if (dentry) dentry->d_lockref.count++; return dentry; } static inline struct dentry *dget(struct dentry *dentry) { if (dentry) lockref_get(&dentry->d_lockref); return dentry; } extern struct dentry *dget_parent(struct dentry *dentry); /** * d_unhashed - is dentry hashed * @dentry: entry to check * * Returns true if the dentry passed is not currently hashed. */ static inline int d_unhashed(const struct dentry *dentry) { return hlist_bl_unhashed(&dentry->d_hash); } static inline int d_unlinked(const struct dentry *dentry) { return d_unhashed(dentry) && !IS_ROOT(dentry); } static inline int cant_mount(const struct dentry *dentry) { return (dentry->d_flags & DCACHE_CANT_MOUNT); } static inline void dont_mount(struct dentry *dentry) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_CANT_MOUNT; spin_unlock(&dentry->d_lock); } extern void __d_lookup_done(struct dentry *); static inline int d_in_lookup(const struct dentry *dentry) { return dentry->d_flags & DCACHE_PAR_LOOKUP; } static inline void d_lookup_done(struct dentry *dentry) { if (unlikely(d_in_lookup(dentry))) { spin_lock(&dentry->d_lock); __d_lookup_done(dentry); spin_unlock(&dentry->d_lock); } } extern void dput(struct dentry *); static inline bool d_managed(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MANAGED_DENTRY; } static inline bool d_mountpoint(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MOUNTED; } /* * Directory cache entry type accessor functions. */ static inline unsigned __d_entry_type(const struct dentry *dentry) { return dentry->d_flags & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_MISS_TYPE; } static inline bool d_is_whiteout(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_WHITEOUT_TYPE; } static inline bool d_can_lookup(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE; } static inline bool d_is_autodir(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE; } static inline bool d_is_dir(const struct dentry *dentry) { return d_can_lookup(dentry) || d_is_autodir(dentry); } static inline bool d_is_symlink(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE; } static inline bool d_is_reg(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_REGULAR_TYPE; } static inline bool d_is_special(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SPECIAL_TYPE; } static inline bool d_is_file(const struct dentry *dentry) { return d_is_reg(dentry) || d_is_special(dentry); } static inline bool d_is_negative(const struct dentry *dentry) { // TODO: check d_is_whiteout(dentry) also. return d_is_miss(dentry); } static inline bool d_flags_negative(unsigned flags) { return (flags & DCACHE_ENTRY_TYPE) == DCACHE_MISS_TYPE; } static inline bool d_is_positive(const struct dentry *dentry) { return !d_is_negative(dentry); } /** * d_really_is_negative - Determine if a dentry is really negative (ignoring fallthroughs) * @dentry: The dentry in question * * Returns true if the dentry represents either an absent name or a name that * doesn't map to an inode (ie. ->d_inode is NULL). The dentry could represent * a true miss, a whiteout that isn't represented by a 0,0 chardev or a * fallthrough marker in an opaque directory. * * Note! (1) This should be used *only* by a filesystem to examine its own * dentries. It should not be used to look at some other filesystem's * dentries. (2) It should also be used in combination with d_inode() to get * the inode. (3) The dentry may have something attached to ->d_lower and the * type field of the flags may be set to something other than miss or whiteout. */ static inline bool d_really_is_negative(const struct dentry *dentry) { return dentry->d_inode == NULL; } /** * d_really_is_positive - Determine if a dentry is really positive (ignoring fallthroughs) * @dentry: The dentry in question * * Returns true if the dentry represents a name that maps to an inode * (ie. ->d_inode is not NULL). The dentry might still represent a whiteout if * that is represented on medium as a 0,0 chardev. * * Note! (1) This should be used *only* by a filesystem to examine its own * dentries. It should not be used to look at some other filesystem's * dentries. (2) It should also be used in combination with d_inode() to get * the inode. */ static inline bool d_really_is_positive(const struct dentry *dentry) { return dentry->d_inode != NULL; } static inline int simple_positive(const struct dentry *dentry) { return d_really_is_positive(dentry) && !d_unhashed(dentry); } extern void d_set_fallthru(struct dentry *dentry); static inline bool d_is_fallthru(const struct dentry *dentry) { return dentry->d_flags & DCACHE_FALLTHRU; } extern int sysctl_vfs_cache_pressure; static inline unsigned long vfs_pressure_ratio(unsigned long val) { return mult_frac(val, sysctl_vfs_cache_pressure, 100); } /** * d_inode - Get the actual inode of this dentry * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes * in their own dentries and ignore the layering superimposed upon them. */ static inline struct inode *d_inode(const struct dentry *dentry) { return dentry->d_inode; } /** * d_inode_rcu - Get the actual inode of this dentry with READ_ONCE() * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes * in their own dentries and ignore the layering superimposed upon them. */ static inline struct inode *d_inode_rcu(const struct dentry *dentry) { return READ_ONCE(dentry->d_inode); } /** * d_backing_inode - Get upper or lower inode we should be using * @upper: The upper layer * * This is the helper that should be used to get at the inode that will be used * if this dentry were to be opened as a file. The inode may be on the upper * dentry or it may be on a lower dentry pinned by the upper. * * Normal filesystems should not use this to access their own inodes. */ static inline struct inode *d_backing_inode(const struct dentry *upper) { struct inode *inode = upper->d_inode; return inode; } /** * d_backing_dentry - Get upper or lower dentry we should be using * @upper: The upper layer * * This is the helper that should be used to get the dentry of the inode that * will be used if this dentry were opened as a file. It may be the upper * dentry or it may be a lower dentry pinned by the upper. * * Normal filesystems should not use this to access their own dentries. */ static inline struct dentry *d_backing_dentry(struct dentry *upper) { return upper; } /** * d_real - Return the real dentry * @dentry: the dentry to query * @inode: inode to select the dentry from multiple layers (can be NULL) * * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. * * See also: Documentation/filesystems/vfs.rst */ static inline struct dentry *d_real(struct dentry *dentry, const struct inode *inode) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) return dentry->d_op->d_real(dentry, inode); else return dentry; } /** * d_real_inode - Return the real inode * @dentry: The dentry to query * * If dentry is on a union/overlay, then return the underlying, real inode. * Otherwise return d_inode(). */ static inline struct inode *d_real_inode(const struct dentry *dentry) { /* This usage of d_real() results in const dentry */ return d_backing_inode(d_real((struct dentry *) dentry, NULL)); } struct name_snapshot { struct qstr name; unsigned char inline_name[DNAME_INLINE_LEN]; }; void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); #endif /* __LINUX_DCACHE_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/attr.c * * Copyright (C) 1991, 1992 Linus Torvalds * changes by Thomas Schoebel-Theuer */ #include <linux/export.h> #include <linux/time.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/sched/signal.h> #include <linux/capability.h> #include <linux/fsnotify.h> #include <linux/fcntl.h> #include <linux/security.h> #include <linux/evm.h> #include <linux/ima.h> #include "internal.h" /** * setattr_should_drop_sgid - determine whether the setgid bit needs to be * removed * @inode: inode to check * * This function determines whether the setgid bit needs to be removed. * We retain backwards compatibility and require setgid bit to be removed * unconditionally if S_IXGRP is set. Otherwise we have the exact same * requirements as setattr_prepare() and setattr_copy(). * * Return: ATTR_KILL_SGID if setgid bit needs to be removed, 0 otherwise. */ int setattr_should_drop_sgid(const struct inode *inode) { umode_t mode = inode->i_mode; if (!(mode & S_ISGID)) return 0; if (mode & S_IXGRP) return ATTR_KILL_SGID; if (!in_group_or_capable(inode, inode->i_gid)) return ATTR_KILL_SGID; return 0; } /** * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to * be dropped * @inode: inode to check * * This function determines whether the set{g,u}id bits need to be removed. * If the setuid bit needs to be removed ATTR_KILL_SUID is returned. If the * setgid bit needs to be removed ATTR_KILL_SGID is returned. If both * set{g,u}id bits need to be removed the corresponding mask of both flags is * returned. * * Return: A mask of ATTR_KILL_S{G,U}ID indicating which - if any - setid bits * to remove, 0 otherwise. */ int setattr_should_drop_suidgid(struct inode *inode) { umode_t mode = inode->i_mode; int kill = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; kill |= setattr_should_drop_sgid(inode); if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) return kill; return 0; } EXPORT_SYMBOL(setattr_should_drop_suidgid); static bool chown_ok(const struct inode *inode, kuid_t uid) { if (uid_eq(current_fsuid(), inode->i_uid) && uid_eq(uid, inode->i_uid)) return true; if (capable_wrt_inode_uidgid(inode, CAP_CHOWN)) return true; if (uid_eq(inode->i_uid, INVALID_UID) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } static bool chgrp_ok(const struct inode *inode, kgid_t gid) { if (uid_eq(current_fsuid(), inode->i_uid) && (in_group_p(gid) || gid_eq(gid, inode->i_gid))) return true; if (capable_wrt_inode_uidgid(inode, CAP_CHOWN)) return true; if (gid_eq(inode->i_gid, INVALID_GID) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } /** * setattr_prepare - check if attribute changes to a dentry are allowed * @dentry: dentry to check * @attr: attributes to change * * Check if we are allowed to change the attributes contained in @attr * in the given dentry. This includes the normal unix access permission * checks, as well as checks for rlimits and others. The function also clears * SGID bit from mode if user is not allowed to set it. Also file capabilities * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set. * * Should be called as the first thing in ->setattr implementations, * possibly after taking additional locks. */ int setattr_prepare(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); unsigned int ia_valid = attr->ia_valid; /* * First check size constraints. These can't be overriden using * ATTR_FORCE. */ if (ia_valid & ATTR_SIZE) { int error = inode_newsize_ok(inode, attr->ia_size); if (error) return error; } /* If force is set do it anyway. */ if (ia_valid & ATTR_FORCE) goto kill_priv; /* Make sure a caller can chown. */ if ((ia_valid & ATTR_UID) && !chown_ok(inode, attr->ia_uid)) return -EPERM; /* Make sure caller can chgrp. */ if ((ia_valid & ATTR_GID) && !chgrp_ok(inode, attr->ia_gid)) return -EPERM; /* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { if (!inode_owner_or_capable(inode)) return -EPERM; /* Also check the setgid bit! */ if (!in_group_or_capable(inode, (ia_valid & ATTR_GID) ? attr->ia_gid : inode->i_gid)) attr->ia_mode &= ~S_ISGID; } /* Check for setting the inode time. */ if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) { if (!inode_owner_or_capable(inode)) return -EPERM; } kill_priv: /* User has permission for the change */ if (ia_valid & ATTR_KILL_PRIV) { int error; error = security_inode_killpriv(dentry); if (error) return error; } return 0; } EXPORT_SYMBOL(setattr_prepare); /** * inode_newsize_ok - may this inode be truncated to a given size * @inode: the inode to be truncated * @offset: the new size to assign to the inode * * inode_newsize_ok must be called with i_mutex held. * * inode_newsize_ok will check filesystem limits and ulimits to check that the * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ * when necessary. Caller must not proceed with inode size change if failure is * returned. @inode must be a file (not directory), with appropriate * permissions to allow truncate (inode_newsize_ok does NOT check these * conditions). * * Return: 0 on success, -ve errno on failure */ int inode_newsize_ok(const struct inode *inode, loff_t offset) { if (offset < 0) return -EINVAL; if (inode->i_size < offset) { unsigned long limit; limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY && offset > limit) goto out_sig; if (offset > inode->i_sb->s_maxbytes) goto out_big; } else { /* * truncation of in-use swapfiles is disallowed - it would * cause subsequent swapout to scribble on the now-freed * blocks. */ if (IS_SWAPFILE(inode)) return -ETXTBSY; } return 0; out_sig: send_sig(SIGXFSZ, current, 0); out_big: return -EFBIG; } EXPORT_SYMBOL(inode_newsize_ok); /** * setattr_copy - copy simple metadata updates into the generic inode * @inode: the inode to be updated * @attr: the new attributes * * setattr_copy must be called with i_mutex held. * * setattr_copy updates the inode's metadata with that specified * in attr. Noticeably missing is inode size update, which is more complex * as it requires pagecache updates. * * The inode is not marked as dirty after this operation. The rationale is * that for "simple" filesystems, the struct inode is the inode storage. * The caller is free to mark the inode dirty afterwards if needed. */ void setattr_copy(struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; if (ia_valid & ATTR_UID) inode->i_uid = attr->ia_uid; if (ia_valid & ATTR_GID) inode->i_gid = attr->ia_gid; if (ia_valid & ATTR_ATIME) inode->i_atime = attr->ia_atime; if (ia_valid & ATTR_MTIME) inode->i_mtime = attr->ia_mtime; if (ia_valid & ATTR_CTIME) inode->i_ctime = attr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; if (!in_group_or_capable(inode, inode->i_gid)) mode &= ~S_ISGID; inode->i_mode = mode; } } EXPORT_SYMBOL(setattr_copy); /** * notify_change - modify attributes of a filesytem object * @dentry: object affected * @attr: new attributes * @delegated_inode: returns inode, if the inode is delegated * * The caller must hold the i_mutex on the affected object. * * If notify_change discovers a delegation in need of breaking, * it will return -EWOULDBLOCK and return a reference to the inode in * delegated_inode. The caller should then break the delegation and * retry. Because breaking a delegation may take a long time, the * caller should drop the i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. Also, passing NULL is fine for callers holding * the file open for write, as there can be no conflicting delegation in * that case. */ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; umode_t mode = inode->i_mode; int error; struct timespec64 now; unsigned int ia_valid = attr->ia_valid; WARN_ON_ONCE(!inode_is_locked(inode)); if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) { if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; } /* * If utimes(2) and friends are called with times == NULL (or both * times are UTIME_NOW), then we need to check for write permission */ if (ia_valid & ATTR_TOUCH) { if (IS_IMMUTABLE(inode)) return -EPERM; if (!inode_owner_or_capable(inode)) { error = inode_permission(inode, MAY_WRITE); if (error) return error; } } if ((ia_valid & ATTR_MODE)) { /* * Don't allow changing the mode of symlinks: * * (1) The vfs doesn't take the mode of symlinks into account * during permission checking. * (2) This has never worked correctly. Most major filesystems * did return EOPNOTSUPP due to interactions with POSIX ACLs * but did still updated the mode of the symlink. * This inconsistency led system call wrapper providers such * as libc to block changing the mode of symlinks with * EOPNOTSUPP already. * (3) To even do this in the first place one would have to use * specific file descriptors and quite some effort. */ if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; /* Flag setting protected by i_mutex */ if (is_sxid(attr->ia_mode)) inode->i_flags &= ~S_NOSEC; } now = current_time(inode); attr->ia_ctime = now; if (!(ia_valid & ATTR_ATIME_SET)) attr->ia_atime = now; else attr->ia_atime = timestamp_truncate(attr->ia_atime, inode); if (!(ia_valid & ATTR_MTIME_SET)) attr->ia_mtime = now; else attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode); if (ia_valid & ATTR_KILL_PRIV) { error = security_inode_need_killpriv(dentry); if (error < 0) return error; if (error == 0) ia_valid = attr->ia_valid &= ~ATTR_KILL_PRIV; } /* * We now pass ATTR_KILL_S*ID to the lower level setattr function so * that the function has the ability to reinterpret a mode change * that's due to these bits. This adds an implicit restriction that * no function will ever call notify_change with both ATTR_MODE and * ATTR_KILL_S*ID set. */ if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) && (ia_valid & ATTR_MODE)) BUG(); if (ia_valid & ATTR_KILL_SUID) { if (mode & S_ISUID) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = (inode->i_mode & ~S_ISUID); } } if (ia_valid & ATTR_KILL_SGID) { if (mode & S_ISGID) { if (!(ia_valid & ATTR_MODE)) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = inode->i_mode; } attr->ia_mode &= ~S_ISGID; } } if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID))) return 0; /* * Verify that uid/gid changes are valid in the target * namespace of the superblock. */ if (ia_valid & ATTR_UID && !kuid_has_mapping(inode->i_sb->s_user_ns, attr->ia_uid)) return -EOVERFLOW; if (ia_valid & ATTR_GID && !kgid_has_mapping(inode->i_sb->s_user_ns, attr->ia_gid)) return -EOVERFLOW; /* Don't allow modifications of files with invalid uids or * gids unless those uids & gids are being made valid. */ if (!(ia_valid & ATTR_UID) && !uid_valid(inode->i_uid)) return -EOVERFLOW; if (!(ia_valid & ATTR_GID) && !gid_valid(inode->i_gid)) return -EOVERFLOW; error = security_inode_setattr(dentry, attr); if (error) return error; error = try_break_deleg(inode, delegated_inode); if (error) return error; if (inode->i_op->setattr) error = inode->i_op->setattr(dentry, attr); else error = simple_setattr(dentry, attr); if (!error) { fsnotify_change(dentry, ia_valid); ima_inode_post_setattr(dentry); evm_inode_post_setattr(dentry, ia_valid); } return error; } EXPORT_SYMBOL(notify_change); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 | #ifndef _LINUX_MMAP_LOCK_H #define _LINUX_MMAP_LOCK_H #include <linux/mmdebug.h> #define MMAP_LOCK_INITIALIZER(name) \ .mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock), static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); } static inline void mmap_write_lock(struct mm_struct *mm) { down_write(&mm->mmap_lock); } static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass) { down_write_nested(&mm->mmap_lock, subclass); } static inline int mmap_write_lock_killable(struct mm_struct *mm) { return down_write_killable(&mm->mmap_lock); } static inline bool mmap_write_trylock(struct mm_struct *mm) { return down_write_trylock(&mm->mmap_lock) != 0; } static inline void mmap_write_unlock(struct mm_struct *mm) { up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { downgrade_write(&mm->mmap_lock); } static inline void mmap_read_lock(struct mm_struct *mm) { down_read(&mm->mmap_lock); } static inline int mmap_read_lock_killable(struct mm_struct *mm) { return down_read_killable(&mm->mmap_lock); } static inline bool mmap_read_trylock(struct mm_struct *mm) { return down_read_trylock(&mm->mmap_lock) != 0; } static inline void mmap_read_unlock(struct mm_struct *mm) { up_read(&mm->mmap_lock); } static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) { if (down_read_trylock(&mm->mmap_lock)) { rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); return true; } return false; } static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { up_read_non_owner(&mm->mmap_lock); } static inline void mmap_assert_locked(struct mm_struct *mm) { lockdep_assert_held(&mm->mmap_lock); VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } static inline void mmap_assert_write_locked(struct mm_struct *mm) { lockdep_assert_held_write(&mm->mmap_lock); VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); } static inline int mmap_lock_is_contended(struct mm_struct *mm) { return rwsem_is_contended(&mm->mmap_lock); } #endif /* _LINUX_MMAP_LOCK_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Type definitions for the multi-level security (MLS) policy. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * * Support for enhanced MLS infrastructure. * * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. */ #ifndef _SS_MLS_TYPES_H_ #define _SS_MLS_TYPES_H_ #include "security.h" #include "ebitmap.h" struct mls_level { u32 sens; /* sensitivity */ struct ebitmap cat; /* category set */ }; struct mls_range { struct mls_level level[2]; /* low == level[0], high == level[1] */ }; static inline int mls_level_eq(struct mls_level *l1, struct mls_level *l2) { return ((l1->sens == l2->sens) && ebitmap_cmp(&l1->cat, &l2->cat)); } static inline int mls_level_dom(struct mls_level *l1, struct mls_level *l2) { return ((l1->sens >= l2->sens) && ebitmap_contains(&l1->cat, &l2->cat, 0)); } #define mls_level_incomp(l1, l2) \ (!mls_level_dom((l1), (l2)) && !mls_level_dom((l2), (l1))) #define mls_level_between(l1, l2, l3) \ (mls_level_dom((l1), (l2)) && mls_level_dom((l3), (l1))) #define mls_range_contains(r1, r2) \ (mls_level_dom(&(r2).level[0], &(r1).level[0]) && \ mls_level_dom(&(r1).level[1], &(r2).level[1])) #endif /* _SS_MLS_TYPES_H_ */ |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_H #define _LINUX_MM_H #include <linux/errno.h> #ifdef __KERNEL__ #include <linux/mmdebug.h> #include <linux/gfp.h> #include <linux/bug.h> #include <linux/list.h> #include <linux/mmzone.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/debug_locks.h> #include <linux/mm_types.h> #include <linux/mmap_lock.h> #include <linux/range.h> #include <linux/pfn.h> #include <linux/percpu-refcount.h> #include <linux/bit_spinlock.h> #include <linux/shrinker.h> #include <linux/resource.h> #include <linux/page_ext.h> #include <linux/err.h> #include <linux/page-flags.h> #include <linux/page_ref.h> #include <linux/memremap.h> #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/sched.h> #include <linux/pgtable.h> struct mempolicy; struct anon_vma; struct anon_vma_chain; struct file_ra_state; struct user_struct; struct writeback_control; struct bdi_writeback; struct pt_regs; extern int sysctl_page_lock_unfairness; void init_mm_internals(void); #ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; static inline void set_max_mapnr(unsigned long limit) { max_mapnr = limit; } #else static inline void set_max_mapnr(unsigned long limit) { } #endif extern atomic_long_t _totalram_pages; static inline unsigned long totalram_pages(void) { return (unsigned long)atomic_long_read(&_totalram_pages); } static inline void totalram_pages_inc(void) { atomic_long_inc(&_totalram_pages); } static inline void totalram_pages_dec(void) { atomic_long_dec(&_totalram_pages); } static inline void totalram_pages_add(long count) { atomic_long_add(count, &_totalram_pages); } extern void * high_memory; extern int page_cluster; #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; #else #define sysctl_legacy_va_layout 0 #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS extern const int mmap_rnd_bits_min; extern const int mmap_rnd_bits_max; extern int mmap_rnd_bits __read_mostly; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS extern const int mmap_rnd_compat_bits_min; extern const int mmap_rnd_compat_bits_max; extern int mmap_rnd_compat_bits __read_mostly; #endif #include <asm/page.h> #include <asm/processor.h> /* * Architectures that support memory tagging (assigning tags to memory regions, * embedding these tags into addresses that point to these memory regions, and * checking that the memory and the pointer tags match on memory accesses) * redefine this macro to strip tags from pointers. * It's defined as noop for arcitectures that don't support memory tagging. */ #ifndef untagged_addr #define untagged_addr(addr) (addr) #endif #ifndef __pa_symbol #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #endif #ifndef page_to_virt #define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x))) #endif #ifndef lm_alias #define lm_alias(x) __va(__pa_symbol(x)) #endif /* * To prevent common memory management code establishing * a zero page mapping on a read fault. * This macro should be defined within <asm/pgtable.h>. * s390 does this to prevent multiplexing of hardware bits * related to the physical page in case of virtualization. */ #ifndef mm_forbids_zeropage #define mm_forbids_zeropage(X) (0) #endif /* * On some architectures it is expensive to call memset() for small sizes. * If an architecture decides to implement their own version of * mm_zero_struct_page they should wrap the defines below in a #ifndef and * define their own version of this macro in <asm/pgtable.h> */ #if BITS_PER_LONG == 64 /* This function must be updated when the size of struct page grows above 80 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can * combine write statments if they are both assignments and can be reordered, * this can result in several of the writes here being dropped. */ #define mm_zero_struct_page(pp) __mm_zero_struct_page(pp) static inline void __mm_zero_struct_page(struct page *page) { unsigned long *_pp = (void *)page; /* Check that struct page is either 56, 64, 72, or 80 bytes */ BUILD_BUG_ON(sizeof(struct page) & 7); BUILD_BUG_ON(sizeof(struct page) < 56); BUILD_BUG_ON(sizeof(struct page) > 80); switch (sizeof(struct page)) { case 80: _pp[9] = 0; fallthrough; case 72: _pp[8] = 0; fallthrough; case 64: _pp[7] = 0; fallthrough; case 56: _pp[6] = 0; _pp[5] = 0; _pp[4] = 0; _pp[3] = 0; _pp[2] = 0; _pp[1] = 0; _pp[0] = 0; } } #else #define mm_zero_struct_page(pp) ((void)memset((pp), 0, sizeof(struct page))) #endif /* * Default maximum number of active map areas, this limits the number of vmas * per mm struct. Users can overwrite this number by sysctl but there is a * problem. * * When a program's coredump is generated as ELF format, a section is created * per a vma. In ELF, the number of sections is represented in unsigned short. * This means the number of sections should be smaller than 65535 at coredump. * Because the kernel adds some informative sections to a image of program at * generating coredump, we need some margin. The number of extra sections is * 1-3 now and depends on arch. We use "5" as safe margin, here. * * ELF extended numbering allows more than 65535 sections, so 16-bit bound is * not a hard limit any more. Although some userspace tools can be surprised by * that. */ #define MAPCOUNT_ELF_CORE_MARGIN (5) #define DEFAULT_MAX_MAP_COUNT (USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN) extern int sysctl_max_map_count; extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, loff_t *); #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ #define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way * we have a virtual fs - giving a cleaner interface to the * mm details, and allowing different kinds of memory mappings * (from shared memory to executable loading to arbitrary * mmap() functions). */ struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif /* * vm_flags in vm_area_struct, see mm_types.h. * When changing, update also include/trace/events/mmflags.h */ #define VM_NONE 0x00000000 #define VM_READ 0x00000001 /* currently active flags */ #define VM_WRITE 0x00000002 #define VM_EXEC 0x00000004 #define VM_SHARED 0x00000008 /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ #define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */ #define VM_MAYWRITE 0x00000020 #define VM_MAYEXEC 0x00000040 #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ #define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */ #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ #define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */ #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ /* Used by sys_madvise() */ #define VM_SEQ_READ 0x00008000 /* App will access data sequentially */ #define VM_RAND_READ 0x00010000 /* App will not benefit from clustered reads */ #define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */ #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ #define VM_LOCKONFAULT 0x00080000 /* Lock the pages covered when they are faulted in */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_SYNC 0x00800000 /* Synchronous page faults */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */ #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ #ifdef CONFIG_MEM_SOFT_DIRTY # define VM_SOFTDIRTY 0x08000000 /* Not soft dirty clean area */ #else # define VM_SOFTDIRTY 0 #endif #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ #ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS #define VM_HIGH_ARCH_BIT_0 32 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) #define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) #define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) #define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) #define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #ifdef CONFIG_ARCH_HAS_PKEYS # define VM_PKEY_SHIFT VM_HIGH_ARCH_BIT_0 # define VM_PKEY_BIT0 VM_HIGH_ARCH_0 /* A protection key is a 4-bit value */ # define VM_PKEY_BIT1 VM_HIGH_ARCH_1 /* on x86 and 5-bit value on ppc64 */ # define VM_PKEY_BIT2 VM_HIGH_ARCH_2 # define VM_PKEY_BIT3 VM_HIGH_ARCH_3 #ifdef CONFIG_PPC # define VM_PKEY_BIT4 VM_HIGH_ARCH_4 #else # define VM_PKEY_BIT4 0 #endif #endif /* CONFIG_ARCH_HAS_PKEYS */ #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ #elif defined(CONFIG_PPC) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_IA64) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_SPARC64) # define VM_SPARC_ADI VM_ARCH_1 /* Uses ADI tag for access control */ # define VM_ARCH_CLEAR VM_SPARC_ADI #elif defined(CONFIG_ARM64) # define VM_ARM64_BTI VM_ARCH_1 /* BTI guarded page, a.k.a. GP bit */ # define VM_ARCH_CLEAR VM_ARM64_BTI #elif !defined(CONFIG_MMU) # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif #if defined(CONFIG_ARM64_MTE) # define VM_MTE VM_HIGH_ARCH_0 /* Use Tagged memory for access control */ # define VM_MTE_ALLOWED VM_HIGH_ARCH_1 /* Tagged memory permitted */ #else # define VM_MTE VM_NONE # define VM_MTE_ALLOWED VM_NONE #endif #ifndef VM_GROWSUP # define VM_GROWSUP VM_NONE #endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) #define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) /* Common data flag combinations */ #define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_FLAGS_NON_EXEC (VM_READ | VM_WRITE | VM_MAYREAD | \ VM_MAYWRITE | VM_MAYEXEC) #define VM_DATA_FLAGS_EXEC (VM_READ | VM_WRITE | VM_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) #ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */ #define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_EXEC #endif #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS #endif #ifdef CONFIG_STACK_GROWSUP #define VM_STACK VM_GROWSUP #else #define VM_STACK VM_GROWSDOWN #endif #define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) /* VMA basic access permission flags */ #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) /* * Special vmas that are non-mergable, non-mlock()able. */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) /* This mask prevents VMA from being scanned with khugepaged */ #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB) /* This mask defines which mm->def_flags a process can inherit its parent */ #define VM_INIT_DEF_MASK VM_NOHUGEPAGE /* This mask is used to clear all the VMA flags used by mlock */ #define VM_LOCKED_CLEAR_MASK (~(VM_LOCKED | VM_LOCKONFAULT)) /* Arch-specific flags to clear when updating VM flags on protection change */ #ifndef VM_ARCH_CLEAR # define VM_ARCH_CLEAR VM_NONE #endif #define VM_FLAGS_CLEAR (ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR) /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ extern pgprot_t protection_map[16]; /** * Fault flag definitions. * * @FAULT_FLAG_WRITE: Fault was a write fault. * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. * @FAULT_FLAG_TRIED: The fault has been tried once. * @FAULT_FLAG_USER: The fault originated in userspace. * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two * fault flags correctly. Currently there can be three legal combinations: * * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and * this is the first try * * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and * we've already tried at least once * * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry * * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never * be used. Note that page faults can be allowed to retry for multiple times, * in which case we'll have an initial fault with flags (a) then later on * continuous faults with flags (b). We should always try to detect pending * signals before a retry to make sure the continuous page faults can still be * interrupted if necessary. */ #define FAULT_FLAG_WRITE 0x01 #define FAULT_FLAG_MKWRITE 0x02 #define FAULT_FLAG_ALLOW_RETRY 0x04 #define FAULT_FLAG_RETRY_NOWAIT 0x08 #define FAULT_FLAG_KILLABLE 0x10 #define FAULT_FLAG_TRIED 0x20 #define FAULT_FLAG_USER 0x40 #define FAULT_FLAG_REMOTE 0x80 #define FAULT_FLAG_INSTRUCTION 0x100 #define FAULT_FLAG_INTERRUPTIBLE 0x200 /* * The default fault flags that should be used by most of the * arch-specific page fault handlers. */ #define FAULT_FLAG_DEFAULT (FAULT_FLAG_ALLOW_RETRY | \ FAULT_FLAG_KILLABLE | \ FAULT_FLAG_INTERRUPTIBLE) /** * fault_flag_allow_retry_first - check ALLOW_RETRY the first time * * This is mostly used for places where we want to try to avoid taking * the mmap_lock for too long a time when waiting for another condition * to change, in which case we can try to be polite to release the * mmap_lock in the first round to avoid potential starvation of other * processes that would also want the mmap_lock. * * Return: true if the page fault allows retry and this is the first * attempt of the fault handling; false otherwise. */ static inline bool fault_flag_allow_retry_first(unsigned int flags) { return (flags & FAULT_FLAG_ALLOW_RETRY) && (!(flags & FAULT_FLAG_TRIED)); } #define FAULT_FLAG_TRACE \ { FAULT_FLAG_WRITE, "WRITE" }, \ { FAULT_FLAG_MKWRITE, "MKWRITE" }, \ { FAULT_FLAG_ALLOW_RETRY, "ALLOW_RETRY" }, \ { FAULT_FLAG_RETRY_NOWAIT, "RETRY_NOWAIT" }, \ { FAULT_FLAG_KILLABLE, "KILLABLE" }, \ { FAULT_FLAG_TRIED, "TRIED" }, \ { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" } /* * vm_fault is filled by the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * * MM layer fills up gfp_mask for page allocations but fault handler might * alter it if its implementation requires a different allocation context. * * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { struct vm_area_struct *vma; /* Target VMA */ unsigned int flags; /* FAULT_FLAG_xxx flags */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ unsigned long address; /* Faulting virtual address */ pmd_t *pmd; /* Pointer to pmd entry matching * the 'address' */ pud_t *pud; /* Pointer to pud entry matching * the 'address' */ pte_t orig_pte; /* Value of PTE at the time of fault */ struct page *cow_page; /* Page handler may use for COW fault */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by * VM_FAULT_ERROR). */ /* These three entries are valid only while holding ptl lock */ pte_t *pte; /* Pointer to pte entry matching * the 'address'. NULL if the page * table hasn't been allocated. */ spinlock_t *ptl; /* Page table lock. * Protects pte page table if 'pte' * is not NULL, otherwise pmd. */ pgtable_t prealloc_pte; /* Pre-allocated pte page table. * vm_ops->map_pages() calls * alloc_set_pte() from atomic context. * do_fault_around() pre-allocates * page table to avoid allocation from * atomic context. */ }; /* page entry size for vm->huge_fault() */ enum page_entry_size { PE_SIZE_PTE = 0, PE_SIZE_PMD, PE_SIZE_PUD, }; /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer * to the functions called when a no-page or a wp-page exception occurs. */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); int (*split)(struct vm_area_struct * area, unsigned long addr); int (*mremap)(struct vm_area_struct * area); vm_fault_t (*fault)(struct vm_fault *vmf); vm_fault_t (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size); void (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); unsigned long (*pagesize)(struct vm_area_struct * area); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ vm_fault_t (*page_mkwrite)(struct vm_fault *vmf); /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */ vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically * for use by special VMAs that can switch between memory and hardware */ int (*access)(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); /* Called by the /proc/PID/maps code to ask the vma whether it * has a special name. Returning non-NULL will also cause this * vma to be dumped unconditionally. */ const char *(*name)(struct vm_area_struct *vma); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy * to hold the policy upon return. Caller should pass NULL @new to * remove a policy and fall back to surrounding context--i.e. do not * install a MPOL_DEFAULT policy, nor the task or system default * mempolicy. */ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); /* * get_policy() op must add reference [mpol_get()] to any policy at * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not * marked as MPOL_SHARED. vma policies are protected by the mmap_lock. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr); #endif /* * Called by vm_normal_page() for special PTEs to find the * page for @addr. This is useful if the default behavior * (using pte_page()) would not find the correct page. */ struct page *(*find_special_page)(struct vm_area_struct *vma, unsigned long addr); }; static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { static const struct vm_operations_struct dummy_vm_ops = {}; memset(vma, 0, sizeof(*vma)); vma->vm_mm = mm; vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); } static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; } static inline bool vma_is_anonymous(struct vm_area_struct *vma) { return !vma->vm_ops; } static inline bool vma_is_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); if (!maybe_stack) return false; if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) == VM_STACK_INCOMPLETE_SETUP) return true; return false; } static inline bool vma_is_foreign(struct vm_area_struct *vma) { if (!current->mm) return true; if (current->mm != vma->vm_mm) return true; return false; } static inline bool vma_is_accessible(struct vm_area_struct *vma) { return vma->vm_flags & VM_ACCESS_FLAGS; } static inline bool is_shared_maywrite(vm_flags_t vm_flags) { return (vm_flags & (VM_SHARED | VM_MAYWRITE)) == (VM_SHARED | VM_MAYWRITE); } static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma) { return is_shared_maywrite(vma->vm_flags); } #ifdef CONFIG_SHMEM /* * The vma_is_shmem is not inline because it is used only by slow * paths in userfault. */ bool vma_is_shmem(struct vm_area_struct *vma); #else static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } #endif int vma_is_stack_for_current(struct vm_area_struct *vma); /* flush_tlb_range() takes a vma, not a mm, and can care about flags */ #define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } struct mmu_gather; struct inode; #include <linux/huge_mm.h> /* * Methods to modify the page usage count. * * What counts for a page usage: * - cache mapping (page->mapping) * - private data (page->private) * - page mapped in a task's page tables, each mapping * is counted separately * * Also, many kernel routines increase the page count before a critical * routine so they can be sure the page doesn't go away from under them. */ /* * Drop a ref, return true if the refcount fell to zero (the page has no users) */ static inline int put_page_testzero(struct page *page) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); return page_ref_dec_and_test(page); } /* * Try to grab a ref unless the page has a refcount of zero, return false if * that is the case. * This can be called when MMU is off so it must not access * any of the virtual mappings. */ static inline int get_page_unless_zero(struct page *page) { return page_ref_add_unless(page, 1, 0); } extern int page_is_ram(unsigned long pfn); enum { REGION_INTERSECTS, REGION_DISJOINT, REGION_MIXED, }; int region_intersects(resource_size_t offset, size_t size, unsigned long flags, unsigned long desc); /* Support for virtually mapped pages */ struct page *vmalloc_to_page(const void *addr); unsigned long vmalloc_to_pfn(const void *addr); /* * Determine if an address is within the vmalloc range * * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ #ifndef is_ioremap_addr #define is_ioremap_addr(x) is_vmalloc_addr(x) #endif #ifdef CONFIG_MMU extern bool is_vmalloc_addr(const void *x); extern int is_vmalloc_or_module_addr(const void *x); #else static inline bool is_vmalloc_addr(const void *x) { return false; } static inline int is_vmalloc_or_module_addr(const void *x) { return 0; } #endif extern void *kvmalloc_node(size_t size, gfp_t flags, int node); static inline void *kvmalloc(size_t size, gfp_t flags) { return kvmalloc_node(size, flags, NUMA_NO_NODE); } static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) { return kvmalloc_node(size, flags | __GFP_ZERO, node); } static inline void *kvzalloc(size_t size, gfp_t flags) { return kvmalloc(size, flags | __GFP_ZERO); } static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return kvmalloc(bytes, flags); } static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) { return kvmalloc_array(n, size, flags | __GFP_ZERO); } extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags); extern void kvfree(const void *addr); extern void kvfree_sensitive(const void *addr, size_t len); static inline int head_compound_mapcount(struct page *head) { return atomic_read(compound_mapcount_ptr(head)) + 1; } /* * Mapcount of compound page as a whole, does not include mapped sub-pages. * * Must be called only for compound pages or any their tail sub-pages. */ static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); page = compound_head(page); return head_compound_mapcount(page); } /* * The atomic page->_mapcount, starts from -1: so that transitions * both from it and to it can be tracked, using atomic_inc_and_test * and atomic_add_negative(-1). */ static inline void page_mapcount_reset(struct page *page) { atomic_set(&(page)->_mapcount, -1); } int __page_mapcount(struct page *page); /* * Mapcount of 0-order page; when compound sub-page, includes * compound_mapcount(). * * Result is undefined for pages which cannot be mapped into userspace. * For example SLAB or special types of pages. See function page_has_type(). * They use this place in struct page differently. */ static inline int page_mapcount(struct page *page) { if (unlikely(PageCompound(page))) return __page_mapcount(page); return atomic_read(&page->_mapcount) + 1; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE int total_mapcount(struct page *page); int page_trans_huge_mapcount(struct page *page, int *total_mapcount); #else static inline int total_mapcount(struct page *page) { return page_mapcount(page); } static inline int page_trans_huge_mapcount(struct page *page, int *total_mapcount) { int mapcount = page_mapcount(page); if (total_mapcount) *total_mapcount = mapcount; return mapcount; } #endif static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); return compound_head(page); } void __put_page(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); /* * Compound pages have a destructor function. Provide a * prototype for that function and accessor functions. * These are _only_ valid on the head of a compound page. */ typedef void compound_page_dtor(struct page *); /* Keep the enum in sync with compound_page_dtors array in mm/page_alloc.c */ enum compound_dtor_id { NULL_COMPOUND_DTOR, COMPOUND_PAGE_DTOR, #ifdef CONFIG_HUGETLB_PAGE HUGETLB_PAGE_DTOR, #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE TRANSHUGE_PAGE_DTOR, #endif NR_COMPOUND_DTORS, }; extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS]; static inline void set_compound_page_dtor(struct page *page, enum compound_dtor_id compound_dtor) { VM_BUG_ON_PAGE(compound_dtor >= NR_COMPOUND_DTORS, page); page[1].compound_dtor = compound_dtor; } static inline void destroy_compound_page(struct page *page) { VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page); compound_page_dtors[page[1].compound_dtor](page); } static inline unsigned int compound_order(struct page *page) { if (!PageHead(page)) return 0; return page[1].compound_order; } static inline bool hpage_pincount_available(struct page *page) { /* * Can the page->hpage_pinned_refcount field be used? That field is in * the 3rd page of the compound page, so the smallest (2-page) compound * pages cannot support it. */ page = compound_head(page); return PageCompound(page) && compound_order(page) > 1; } static inline int head_compound_pincount(struct page *head) { return atomic_read(compound_pincount_ptr(head)); } static inline int compound_pincount(struct page *page) { VM_BUG_ON_PAGE(!hpage_pincount_available(page), page); page = compound_head(page); return head_compound_pincount(page); } static inline void set_compound_order(struct page *page, unsigned int order) { page[1].compound_order = order; page[1].compound_nr = 1U << order; } /* Returns the number of pages in this potentially compound page. */ static inline unsigned long compound_nr(struct page *page) { if (!PageHead(page)) return 1; return page[1].compound_nr; } /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { return PAGE_SIZE << compound_order(page); } /* Returns the number of bits needed for the number of bytes in a page */ static inline unsigned int page_shift(struct page *page) { return PAGE_SHIFT + compound_order(page); } void free_compound_page(struct page *page); #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when * servicing faults for write access. In the normal case, do always want * pte_mkwrite. But get_user_pages can cause write faults for mappings * that do not have writing enabled, when used by access_process_vm. */ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pte = pte_mkwrite(pte); return pte; } vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page); vm_fault_t finish_fault(struct vm_fault *vmf); vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #endif /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of * zeroes, and text pages of executables and shared libraries have * only one copy in memory, at most, normally. * * For the non-reserved pages, page_count(page) denotes a reference count. * page_count() == 0 means the page is free. page->lru is then used for * freelist management in the buddy allocator. * page_count() > 0 means the page has been allocated. * * Pages are allocated by the slab allocator in order to provide memory * to kmalloc and kmem_cache_alloc. In this case, the management of the * page, and the fields in 'struct page' are the responsibility of mm/slab.c * unless a particular usage is carefully commented. (the responsibility of * freeing the kmalloc memory is the caller's, of course). * * A page may be used by anyone else who does a __get_free_page(). * In this case, page_count still tracks the references, and should only * be used through the normal accessor functions. The top bits of page->flags * and page->virtual store page management information, but all other fields * are unused and could be used privately, carefully. The management of this * page is the responsibility of the one who allocated it, and those who have * subsequently been given references to it. * * The other pages (we may call them "pagecache pages") are completely * managed by the Linux memory manager: I/O, buffers, swapping etc. * The following discussion applies only to them. * * A pagecache page contains an opaque `private' member, which belongs to the * page's address_space. Usually, this is the address of a circular list of * the page's disk buffers. PG_private must be set to tell the VM to call * into the filesystem to release these pages. * * A page may belong to an inode's memory mapping. In this case, page->mapping * is the pointer to the inode, and page->index is the file offset of the page, * in units of PAGE_SIZE. * * If pagecache pages are not associated with an inode, they are said to be * anonymous pages. These may become associated with the swapcache, and in that * case PG_swapcache is set, and page->private is an offset into the swapcache. * * In either case (swapcache or inode backed), the pagecache itself holds one * reference to the page. Setting PG_private should also increment the * refcount. The each user mapping also has a reference to the page. * * The pagecache pages are stored in a per-mapping radix tree, which is * rooted at mapping->i_pages, and indexed by offset. * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space * lists, we instead now tag pages as dirty/writeback in the radix tree. * * All pagecache pages may be subject to I/O: * - inode pages may need to be read from disk, * - inode pages which have been modified and are MAP_SHARED may need * to be written back to the inode on disk, * - anonymous pages (including MAP_PRIVATE file mappings) which have been * modified may need to be swapped out to swap space and (later) to be read * back into memory. */ /* * The zone field is never updated after free_area_init_core() * sets it, so none of the operations on it need to be atomic. */ /* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_CPUPID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_CPUPID_PGOFF (ZONES_PGOFF - LAST_CPUPID_WIDTH) #define KASAN_TAG_PGOFF (LAST_CPUPID_PGOFF - KASAN_TAG_WIDTH) /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_CPUPID_PGSHIFT (LAST_CPUPID_PGOFF * (LAST_CPUPID_WIDTH != 0)) #define KASAN_TAG_PGSHIFT (KASAN_TAG_PGOFF * (KASAN_TAG_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF)? \ SECTIONS_PGOFF : ZONES_PGOFF) #else #define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF)? \ NODES_PGOFF : ZONES_PGOFF) #endif #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_CPUPID_MASK ((1UL << LAST_CPUPID_SHIFT) - 1) #define KASAN_TAG_MASK ((1UL << KASAN_TAG_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) { ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT); return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } #ifdef CONFIG_ZONE_DEVICE static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } extern void memmap_init_zone_device(struct zone *, unsigned long, unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { return false; } #endif #ifdef CONFIG_DEV_PAGEMAP_OPS void free_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); static inline bool page_is_devmap_managed(struct page *page) { if (!static_branch_unlikely(&devmap_managed_key)) return false; if (!is_zone_device_page(page)) return false; switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE: case MEMORY_DEVICE_FS_DAX: return true; default: break; } return false; } void put_devmap_managed_page(struct page *page); #else /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool page_is_devmap_managed(struct page *page) { return false; } static inline void put_devmap_managed_page(struct page *page) { } #endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool is_device_private_page(const struct page *page) { return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && IS_ENABLED(CONFIG_DEVICE_PRIVATE) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_DEV_PAGEMAP_OPS) && IS_ENABLED(CONFIG_PCI_P2PDMA) && is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } /* 127: arbitrary random number, small enough to assemble well */ #define page_ref_zero_or_close_to_overflow(page) \ ((unsigned int) page_ref_count(page) + 127u <= 127u) static inline void get_page(struct page *page) { page = compound_head(page); /* * Getting a normal page or the head of a compound page * requires to already have an elevated page->_refcount. */ VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page); page_ref_inc(page); } bool __must_check try_grab_page(struct page *page, unsigned int flags); static inline __must_check bool try_get_page(struct page *page) { page = compound_head(page); if (WARN_ON_ONCE(page_ref_count(page) <= 0)) return false; page_ref_inc(page); return true; } static inline void put_page(struct page *page) { page = compound_head(page); /* * For devmap managed pages we need to catch refcount transition from * 2 to 1, when refcount reach one it means the page is free and we * need to inform the device driver through callback. See * include/linux/memremap.h and HMM for details. */ if (page_is_devmap_managed(page)) { put_devmap_managed_page(page); return; } if (put_page_testzero(page)) __put_page(page); } /* * GUP_PIN_COUNTING_BIAS, and the associated functions that use it, overload * the page's refcount so that two separate items are tracked: the original page * reference count, and also a new count of how many pin_user_pages() calls were * made against the page. ("gup-pinned" is another term for the latter). * * With this scheme, pin_user_pages() becomes special: such pages are marked as * distinct from normal pages. As such, the unpin_user_page() call (and its * variants) must be used in order to release gup-pinned pages. * * Choice of value: * * By making GUP_PIN_COUNTING_BIAS a power of two, debugging of page reference * counts with respect to pin_user_pages() and unpin_user_page() becomes * simpler, due to the fact that adding an even power of two to the page * refcount has the effect of using only the upper N bits, for the code that * counts up using the bias value. This means that the lower bits are left for * the exclusive use of the original code that increments and decrements by one * (or at least, by much smaller values than the bias value). * * Of course, once the lower bits overflow into the upper bits (and this is * OK, because subtraction recovers the original values), then visual inspection * no longer suffices to directly view the separate counts. However, for normal * applications that don't have huge page reference counts, this won't be an * issue. * * Locking: the lockless algorithm described in page_cache_get_speculative() * and page_cache_gup_pin_speculative() provides safe operation for * get_user_pages and page_mkclean and other calls that race to set up page * table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) void unpin_user_page(struct page *page); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); /** * page_maybe_dma_pinned() - report if a page is pinned for DMA. * * This function checks if a page has been pinned via a call to * pin_user_pages*(). * * For non-huge pages, the return value is partially fuzzy: false is not fuzzy, * because it means "definitely not pinned for DMA", but true means "probably * pinned for DMA, but possibly a false positive due to having at least * GUP_PIN_COUNTING_BIAS worth of normal page references". * * False positives are OK, because: a) it's unlikely for a page to get that many * refcounts, and b) all the callers of this routine are expected to be able to * deal gracefully with a false positive. * * For huge pages, the result will be exactly correct. That's because we have * more tracking data available: the 3rd struct page in the compound page is * used to track the pincount (instead using of the GUP_PIN_COUNTING_BIAS * scheme). * * For more information, please see Documentation/core-api/pin_user_pages.rst. * * @page: pointer to page to be queried. * @Return: True, if it is likely that the page has been "dma-pinned". * False, if the page is definitely not dma-pinned. */ static inline bool page_maybe_dma_pinned(struct page *page) { if (hpage_pincount_available(page)) return compound_pincount(page) > 0; /* * page_ref_count() is signed. If that refcount overflows, then * page_ref_count() returns a negative value, and callers will avoid * further incrementing the refcount. * * Here, for that overflow case, use the signed bit to count a little * bit higher via unsigned math, and thus still get an accurate result. */ return ((unsigned int)page_ref_count(compound_head(page))) >= GUP_PIN_COUNTING_BIAS; } #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif /* * The identification function is mainly used by the buddy allocator for * determining if two pages could be buddies. We are not really identifying * the zone since we could be using the section number id if we do not have * node id available in page flags. * We only guarantee that it will return the same value for two combinable * pages in a zone. */ static inline int page_zone_id(struct page *page) { return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; } #ifdef NODE_NOT_IN_PAGE_FLAGS extern int page_to_nid(const struct page *page); #else static inline int page_to_nid(const struct page *page) { struct page *p = (struct page *)page; return (PF_POISONED_CHECK(p)->flags >> NODES_PGSHIFT) & NODES_MASK; } #endif #ifdef CONFIG_NUMA_BALANCING static inline int cpu_pid_to_cpupid(int cpu, int pid) { return ((cpu & LAST__CPU_MASK) << LAST__PID_SHIFT) | (pid & LAST__PID_MASK); } static inline int cpupid_to_pid(int cpupid) { return cpupid & LAST__PID_MASK; } static inline int cpupid_to_cpu(int cpupid) { return (cpupid >> LAST__PID_SHIFT) & LAST__CPU_MASK; } static inline int cpupid_to_nid(int cpupid) { return cpu_to_node(cpupid_to_cpu(cpupid)); } static inline bool cpupid_pid_unset(int cpupid) { return cpupid_to_pid(cpupid) == (-1 & LAST__PID_MASK); } static inline bool cpupid_cpu_unset(int cpupid) { return cpupid_to_cpu(cpupid) == (-1 & LAST__CPU_MASK); } static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) { return (task_pid & LAST__PID_MASK) == cpupid_to_pid(cpupid); } #define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid) #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK); } static inline int page_cpupid_last(struct page *page) { return page->_last_cpupid; } static inline void page_cpupid_reset_last(struct page *page) { page->_last_cpupid = -1 & LAST_CPUPID_MASK; } #else static inline int page_cpupid_last(struct page *page) { return (page->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK; } extern int page_cpupid_xchg_last(struct page *page, int cpupid); static inline void page_cpupid_reset_last(struct page *page) { page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT; } #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */ #else /* !CONFIG_NUMA_BALANCING */ static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { return page_to_nid(page); /* XXX */ } static inline int page_cpupid_last(struct page *page) { return page_to_nid(page); /* XXX */ } static inline int cpupid_to_nid(int cpupid) { return -1; } static inline int cpupid_to_pid(int cpupid) { return -1; } static inline int cpupid_to_cpu(int cpupid) { return -1; } static inline int cpu_pid_to_cpupid(int nid, int pid) { return -1; } static inline bool cpupid_pid_unset(int cpupid) { return true; } static inline void page_cpupid_reset_last(struct page *page) { } static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_KASAN_SW_TAGS /* * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid * setting tags for all pages to native kernel tag value 0xff, as the default * value 0x00 maps to 0xff. */ static inline u8 page_kasan_tag(const struct page *page) { u8 tag; tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; tag ^= 0xff; return tag; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { tag ^= 0xff; page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; } static inline void page_kasan_tag_reset(struct page *page) { page_kasan_tag_set(page, 0xff); } #else static inline u8 page_kasan_tag(const struct page *page) { return 0xff; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { } static inline void page_kasan_tag_reset(struct page *page) { } #endif static inline struct zone *page_zone(const struct page *page) { return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } static inline pg_data_t *page_pgdat(const struct page *page) { return NODE_DATA(page_to_nid(page)); } #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } static inline unsigned long page_to_section(const struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } #endif static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT; } static inline void set_page_node(struct page *page, unsigned long node) { page->flags &= ~(NODES_MASK << NODES_PGSHIFT); page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; } static inline void set_page_links(struct page *page, enum zone_type zone, unsigned long node, unsigned long pfn) { set_page_zone(page, zone); set_page_node(page, node); #ifdef SECTION_IN_PAGE_FLAGS set_page_section(page, pfn_to_section_nr(pfn)); #endif } #ifdef CONFIG_MEMCG static inline struct mem_cgroup *page_memcg(struct page *page) { return page->mem_cgroup; } static inline struct mem_cgroup *page_memcg_rcu(struct page *page) { WARN_ON_ONCE(!rcu_read_lock_held()); return READ_ONCE(page->mem_cgroup); } #else static inline struct mem_cgroup *page_memcg(struct page *page) { return NULL; } static inline struct mem_cgroup *page_memcg_rcu(struct page *page) { WARN_ON_ONCE(!rcu_read_lock_held()); return NULL; } #endif /* * Some inline functions in vmstat.h depend on page_zone() */ #include <linux/vmstat.h> static __always_inline void *lowmem_page_address(const struct page *page) { return page_to_virt(page); } #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) #define HASHED_PAGE_VIRTUAL #endif #if defined(WANT_PAGE_VIRTUAL) static inline void *page_address(const struct page *page) { return page->virtual; } static inline void set_page_address(struct page *page, void *address) { page->virtual = address; } #define page_address_init() do { } while(0) #endif #if defined(HASHED_PAGE_VIRTUAL) void *page_address(const struct page *page); void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) lowmem_page_address(page) #define set_page_address(page, address) do { } while(0) #define page_address_init() do { } while(0) #endif extern void *page_rmapping(struct page *page); extern struct anon_vma *page_anon_vma(struct page *page); extern struct address_space *page_mapping(struct page *page); extern struct address_space *__page_file_mapping(struct page *); static inline struct address_space *page_file_mapping(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_mapping(page); return page->mapping; } extern pgoff_t __page_file_index(struct page *page); /* * Return the pagecache index of the passed page. Regular pagecache pages * use ->index whereas swapcache pages use swp_offset(->private) */ static inline pgoff_t page_index(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_index(page); return page->index; } bool page_mapped(struct page *page); struct address_space *page_mapping(struct page *page); struct address_space *page_mapping_file(struct page *page); /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not * met implying that the system is under some pressure. */ static inline bool page_is_pfmemalloc(struct page *page) { /* * Page index cannot be this large so this must be * a pfmemalloc page. */ return page->index == -1UL; } /* * Only to be called by the page allocator on a freshly allocated * page. */ static inline void set_page_pfmemalloc(struct page *page) { page->index = -1UL; } static inline void clear_page_pfmemalloc(struct page *page) { page->index = 0; } /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. */ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) #define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1)) /* * Flags passed to show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ extern void show_free_areas(unsigned int flags, nodemask_t *nodemask); #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else static inline bool can_do_mlock(void) { return false; } #endif extern int user_shm_lock(size_t, struct user_struct *); extern void user_shm_unlock(size_t, struct user_struct *); /* * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ struct page *single_page; /* Locked page to be unmapped */ }; struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size); void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long start, unsigned long end); struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn); int follow_phys(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned long *prot, resource_size_t *phys); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs); extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); void unmap_mapping_page(struct page *page); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); #else static inline vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { /* should never happen if there's no MMU */ BUG(); return VM_FAULT_SIGBUS; } static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { /* should never happen if there's no MMU */ BUG(); return -EFAULT; } static inline void unmap_mapping_page(struct page *page) { } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { } #endif static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) { unmap_mapping_range(mapping, holebegin, holelen, 0); } extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long pin_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); /* Container for pinned pfns / pages */ struct frame_vector { unsigned int nr_allocated; /* Number of frames we have space for */ unsigned int nr_frames; /* Number of frames stored in ptrs array */ bool got_ref; /* Did we pin pages by getting page ref? */ bool is_pfns; /* Does array contain pages or pfns? */ void *ptrs[]; /* Array of pinned pfns / pages. Use * pfns_vector_pages() or pfns_vector_pfns() * for access */ }; struct frame_vector *frame_vector_create(unsigned int nr_frames); void frame_vector_destroy(struct frame_vector *vec); int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, unsigned int gup_flags, struct frame_vector *vec); void put_vaddr_frames(struct frame_vector *vec); int frame_vector_to_pages(struct frame_vector *vec); void frame_vector_to_pfns(struct frame_vector *vec); static inline unsigned int frame_vector_count(struct frame_vector *vec) { return vec->nr_frames; } static inline struct page **frame_vector_pages(struct frame_vector *vec) { if (vec->is_pfns) { int err = frame_vector_to_pages(vec); if (err) return ERR_PTR(err); } return (struct page **)(vec->ptrs); } static inline unsigned long *frame_vector_pfns(struct frame_vector *vec) { if (!vec->is_pfns) frame_vector_to_pfns(vec); return (unsigned long *)(vec->ptrs); } struct kvec; int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); int get_kernel_page(unsigned long start, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length); void __set_page_dirty(struct page *, struct address_space *, int warn); int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); void account_page_dirtied(struct page *page, struct address_space *mapping); void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb); int set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); void __cancel_dirty_page(struct page *page); static inline void cancel_dirty_page(struct page *page) { /* Avoid atomic ops, locking, etc. when not actually needed. */ if (PageDirty(page)) __cancel_dirty_page(page); } int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, bool need_rmap_locks); /* * Flags used by change_protection(). For now we make it a bitmap so * that we can pass in multiple flags just like parameters. However * for now all the callers are only use one of the flags at the same * time. */ /* Whether we should allow dirty bit accounting */ #define MM_CP_DIRTY_ACCT (1UL << 0) /* Whether this protection change is for NUMA hints */ #define MM_CP_PROT_NUMA (1UL << 1) /* Whether this change is for write protecting */ #define MM_CP_UFFD_WP (1UL << 2) /* do wp */ #define MM_CP_UFFD_WP_RESOLVE (1UL << 3) /* Resolve wp */ #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, unsigned long cp_flags); extern int mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long start, unsigned long end, unsigned long newflags); /* * doesn't attempt to fault and will return short. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); static inline bool get_user_page_fast_only(unsigned long addr, unsigned int gup_flags, struct page **pagep) { return get_user_pages_fast_only(addr, 1, gup_flags, pagep) == 1; } /* * per-process(per-mm_struct) statistics. */ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) { long val = atomic_long_read(&mm->rss_stat.count[member]); #ifdef SPLIT_RSS_COUNTING /* * counter is updated in asynchronous manner and may go to minus. * But it's never be expected number for users. */ if (val < 0) val = 0; #endif return (unsigned long)val; } void mm_trace_rss_stat(struct mm_struct *mm, int member, long count); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { long count = atomic_long_add_return(value, &mm->rss_stat.count[member]); mm_trace_rss_stat(mm, member, count); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { long count = atomic_long_inc_return(&mm->rss_stat.count[member]); mm_trace_rss_stat(mm, member, count); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { long count = atomic_long_dec_return(&mm->rss_stat.count[member]); mm_trace_rss_stat(mm, member, count); } /* Optimized variant when page is already known not to be PageAnon */ static inline int mm_counter_file(struct page *page) { if (PageSwapBacked(page)) return MM_SHMEMPAGES; return MM_FILEPAGES; } static inline int mm_counter(struct page *page) { if (PageAnon(page)) return MM_ANONPAGES; return mm_counter_file(page); } static inline unsigned long get_mm_rss(struct mm_struct *mm) { return get_mm_counter(mm, MM_FILEPAGES) + get_mm_counter(mm, MM_ANONPAGES) + get_mm_counter(mm, MM_SHMEMPAGES); } static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm) { return max(mm->hiwater_rss, get_mm_rss(mm)); } static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm) { return max(mm->hiwater_vm, mm->total_vm); } static inline void update_hiwater_rss(struct mm_struct *mm) { unsigned long _rss = get_mm_rss(mm); if ((mm)->hiwater_rss < _rss) (mm)->hiwater_rss = _rss; } static inline void update_hiwater_vm(struct mm_struct *mm) { if (mm->hiwater_vm < mm->total_vm) mm->hiwater_vm = mm->total_vm; } static inline void reset_mm_hiwater_rss(struct mm_struct *mm) { mm->hiwater_rss = get_mm_rss(mm); } static inline void setmax_mm_hiwater_rss(unsigned long *maxrss, struct mm_struct *mm) { unsigned long hiwater_rss = get_mm_hiwater_rss(mm); if (*maxrss < hiwater_rss) *maxrss = hiwater_rss; } #if defined(SPLIT_RSS_COUNTING) void sync_mm_rss(struct mm_struct *mm); #else static inline void sync_mm_rss(struct mm_struct *mm) { } #endif #ifndef CONFIG_ARCH_HAS_PTE_SPECIAL static inline int pte_special(pte_t pte) { return 0; } static inline pte_t pte_mkspecial(pte_t pte) { return pte; } #endif #ifndef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t pte) { return 0; } #endif int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pte_t *ptep; __cond_lock(*ptl, ptep = __get_locked_pte(mm, addr, ptl)); return ptep; } #ifdef __PAGETABLE_P4D_FOLDED static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return 0; } #else int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); #endif #if defined(__PAGETABLE_PUD_FOLDED) || !defined(CONFIG_MMU) static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return 0; } static inline void mm_inc_nr_puds(struct mm_struct *mm) {} static inline void mm_dec_nr_puds(struct mm_struct *mm) {} #else int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { if (mm_pud_folded(mm)) return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU) static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return 0; } static inline void mm_inc_nr_pmds(struct mm_struct *mm) {} static inline void mm_dec_nr_pmds(struct mm_struct *mm) {} #else int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { if (mm_pmd_folded(mm)) return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif #ifdef CONFIG_MMU static inline void mm_pgtables_bytes_init(struct mm_struct *mm) { atomic_long_set(&mm->pgtables_bytes, 0); } static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return atomic_long_read(&mm->pgtables_bytes); } static inline void mm_inc_nr_ptes(struct mm_struct *mm) { atomic_long_add(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_ptes(struct mm_struct *mm) { atomic_long_sub(PTRS_PER_PTE * sizeof(pte_t), &mm->pgtables_bytes); } #else static inline void mm_pgtables_bytes_init(struct mm_struct *mm) {} static inline unsigned long mm_pgtables_bytes(const struct mm_struct *mm) { return 0; } static inline void mm_inc_nr_ptes(struct mm_struct *mm) {} static inline void mm_dec_nr_ptes(struct mm_struct *mm) {} #endif int __pte_alloc(struct mm_struct *mm, pmd_t *pmd); int __pte_alloc_kernel(pmd_t *pmd); #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ? NULL : p4d_offset(pgd, address); } static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ? NULL : pud_offset(p4d, address); } static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } #endif /* CONFIG_MMU */ #if USE_SPLIT_PTE_PTLOCKS #if ALLOC_SPLIT_PTLOCKS void __init ptlock_cache_init(void); extern bool ptlock_alloc(struct page *page); extern void ptlock_free(struct page *page); static inline spinlock_t *ptlock_ptr(struct page *page) { return page->ptl; } #else /* ALLOC_SPLIT_PTLOCKS */ static inline void ptlock_cache_init(void) { } static inline bool ptlock_alloc(struct page *page) { return true; } static inline void ptlock_free(struct page *page) { } static inline spinlock_t *ptlock_ptr(struct page *page) { return &page->ptl; } #endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(pmd_page(*pmd)); } static inline bool ptlock_init(struct page *page) { /* * prep_new_page() initialize page->private (and therefore page->ptl) * with 0. Make sure nobody took it in use in between. * * It can happen if arch try to use slab for page table allocation: * slab code uses page->slab_cache, which share storage with page->ptl. */ VM_BUG_ON_PAGE(*(unsigned long *)&page->ptl, page); if (!ptlock_alloc(page)) return false; spin_lock_init(ptlock_ptr(page)); return true; } #else /* !USE_SPLIT_PTE_PTLOCKS */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct page *page) { return true; } static inline void ptlock_free(struct page *page) {} #endif /* USE_SPLIT_PTE_PTLOCKS */ static inline void pgtable_init(void) { ptlock_cache_init(); pgtable_cache_init(); } static inline bool pgtable_pte_page_ctor(struct page *page) { if (!ptlock_init(page)) return false; __SetPageTable(page); inc_zone_page_state(page, NR_PAGETABLE); return true; } static inline void pgtable_pte_page_dtor(struct page *page) { ptlock_free(page); __ClearPageTable(page); dec_zone_page_state(page, NR_PAGETABLE); } #define pte_offset_map_lock(mm, pmd, address, ptlp) \ ({ \ spinlock_t *__ptl = pte_lockptr(mm, pmd); \ pte_t *__pte = pte_offset_map(pmd, address); \ *(ptlp) = __ptl; \ spin_lock(__ptl); \ __pte; \ }) #define pte_unmap_unlock(pte, ptl) do { \ spin_unlock(ptl); \ pte_unmap(pte); \ } while (0) #define pte_alloc(mm, pmd) (unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, pmd)) #define pte_alloc_map(mm, pmd, address) \ (pte_alloc(mm, pmd) ? NULL : pte_offset_map(pmd, address)) #define pte_alloc_map_lock(mm, pmd, address, ptlp) \ (pte_alloc(mm, pmd) ? \ NULL : pte_offset_map_lock(mm, pmd, address, ptlp)) #define pte_alloc_kernel(pmd, address) \ ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \ NULL: pte_offset_kernel(pmd, address)) #if USE_SPLIT_PMD_PTLOCKS static struct page *pmd_to_page(pmd_t *pmd) { unsigned long mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1); return virt_to_page((void *)((unsigned long) pmd & mask)); } static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return ptlock_ptr(pmd_to_page(pmd)); } static inline bool pmd_ptlock_init(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE page->pmd_huge_pte = NULL; #endif return ptlock_init(page); } static inline void pmd_ptlock_free(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE VM_BUG_ON_PAGE(page->pmd_huge_pte, page); #endif ptlock_free(page); } #define pmd_huge_pte(mm, pmd) (pmd_to_page(pmd)->pmd_huge_pte) #else static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } static inline bool pmd_ptlock_init(struct page *page) { return true; } static inline void pmd_ptlock_free(struct page *page) {} #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte) #endif static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl = pmd_lockptr(mm, pmd); spin_lock(ptl); return ptl; } static inline bool pgtable_pmd_page_ctor(struct page *page) { if (!pmd_ptlock_init(page)) return false; __SetPageTable(page); #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE atomic_set(&page->pt_share_count, 0); #endif inc_zone_page_state(page, NR_PAGETABLE); return true; } static inline void pgtable_pmd_page_dtor(struct page *page) { pmd_ptlock_free(page); __ClearPageTable(page); dec_zone_page_state(page, NR_PAGETABLE); } /* * No scalability reason to split PUD locks yet, but follow the same pattern * as the PMD locks to make it easier if we decide to. The VM should not be * considered ready to switch to split PUD locks yet; there may be places * which need to be converted from page_table_lock. */ static inline spinlock_t *pud_lockptr(struct mm_struct *mm, pud_t *pud) { return &mm->page_table_lock; } static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) { spinlock_t *ptl = pud_lockptr(mm, pud); spin_lock(ptl); return ptl; } extern void __init pagecache_init(void); extern void __init free_area_init_memoryless_node(int nid); extern void free_initmem(void); /* * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK) * into the buddy system. The freed pages will be poisoned with pattern * "poison" if it's within range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); #ifdef CONFIG_HIGHMEM /* * Free a highmem page into the buddy system, adjusting totalhigh_pages * and totalram_pages. */ extern void free_highmem_page(struct page *page); #endif extern void adjust_managed_page_count(struct page *page, long count); extern void mem_init_print_info(const char *str); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); /* Free the reserved page into the buddy system, so it gets managed. */ static inline void __free_reserved_page(struct page *page) { ClearPageReserved(page); init_page_count(page); __free_page(page); } static inline void free_reserved_page(struct page *page) { __free_reserved_page(page); adjust_managed_page_count(page, 1); } static inline void mark_page_reserved(struct page *page) { SetPageReserved(page); adjust_managed_page_count(page, -1); } /* * Default method to free all the __init memory into the buddy system. * The freed pages will be poisoned with pattern "poison" if it's within * range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ static inline unsigned long free_initmem_default(int poison) { extern char __init_begin[], __init_end[]; return free_reserved_area(&__init_begin, &__init_end, poison, "unused kernel"); } static inline unsigned long get_num_physpages(void) { int nid; unsigned long phys_pages = 0; for_each_online_node(nid) phys_pages += node_present_pages(nid); return phys_pages; } /* * Using memblock node mappings, an architecture may initialise its * zones, allocate the backing mem_map and account for memory holes in an * architecture independent manner. * * An architecture is expected to register range of page frames backed by * physical memory with memblock_add[_node]() before calling * free_area_init() passing in the PFN each zone ends at. At a basic * usage, an architecture is expected to do something like * * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() * memblock_add_node(base, size, nid) * free_area_init(max_zone_pfns); */ void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, unsigned long end_pfn); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); #ifndef CONFIG_NEED_MULTIPLE_NODES static inline int early_pfn_to_nid(unsigned long pfn) { return 0; } #else /* please see mm/page_alloc.c */ extern int __meminit early_pfn_to_nid(unsigned long pfn); /* there is a per-arch backend function. */ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); extern void show_mem(unsigned int flags, nodemask_t *nodemask); extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); #ifdef __HAVE_ARCH_RESERVED_KERNEL_PAGES extern unsigned long arch_reserved_kernel_pages(void); #endif extern __printf(3, 4) void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); /* page_alloc.c */ extern int min_free_kbytes; extern int watermark_boost_factor; extern int watermark_scale_factor; extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); /* interval_tree.c */ void vma_interval_tree_insert(struct vm_area_struct *node, struct rb_root_cached *root); void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root); void vma_interval_tree_remove(struct vm_area_struct *node, struct rb_root_cached *root); struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, unsigned long start, unsigned long last); #define vma_interval_tree_foreach(vma, root, start, last) \ for (vma = vma_interval_tree_iter_first(root, start, last); \ vma; vma = vma_interval_tree_iter_next(vma, start, last)) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root); struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct anon_vma_chain *anon_vma_interval_tree_iter_next( struct anon_vma_chain *node, unsigned long start, unsigned long last); #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node); #endif #define anon_vma_interval_tree_foreach(avc, root, start, last) \ for (avc = anon_vma_interval_tree_iter_first(root, start, last); \ avc; avc = anon_vma_interval_tree_iter_next(avc, start, last)) /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); extern int __vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, struct vm_area_struct *expand); static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) { return __vma_adjust(vma, start, end, pgoff, insert, NULL); } extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, struct mempolicy *, struct vm_userfaultfd_ctx); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); extern int split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *, struct rb_node **, struct rb_node *); extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); static inline int check_data_rlimit(unsigned long rlim, unsigned long new, unsigned long start, unsigned long end_data, unsigned long start_data) { if (rlim < RLIM_INFINITY) { if (((new - start) + (end_data - start_data)) > rlim) return -ENOSPC; } return 0; } extern int mm_take_all_locks(struct mm_struct *mm); extern void mm_drop_all_locks(struct mm_struct *mm); extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); extern struct file *get_task_exe_file(struct task_struct *task); extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages); extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); extern bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm); extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, const struct vm_special_mapping *spec); /* This is an obsolete alternative to _install_special_mapping. */ extern int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, struct page **pages); unsigned long randomize_stack_top(unsigned long stack_top); unsigned long randomize_page(unsigned long start, unsigned long range); extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); extern int __do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); static inline void mm_populate(unsigned long addr, unsigned long len) { /* Ignore errors */ (void) __mm_populate(addr, len, 1); } #else static inline void mm_populate(unsigned long addr, unsigned long len) {} #endif /* These take the mm semaphore themselves */ extern int __must_check vm_brk(unsigned long, unsigned long); extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); extern unsigned long __must_check vm_mmap(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); struct vm_unmapped_area_info { #define VM_UNMAPPED_AREA_TOPDOWN 1 unsigned long flags; unsigned long length; unsigned long low_limit; unsigned long high_limit; unsigned long align_mask; unsigned long align_offset; }; extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); /* truncate.c */ extern void truncate_inode_pages(struct address_space *, loff_t); extern void truncate_inode_pages_range(struct address_space *, loff_t lstart, loff_t lend); extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern vm_fault_t filemap_fault(struct vm_fault *vmf); extern void filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); /* mm/page-writeback.c */ int __must_check write_one_page(struct page *page); void task_dirty_inc(struct task_struct *tsk); extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); /* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */ extern int expand_downwards(struct vm_area_struct *vma, unsigned long address); #if VM_GROWSUP extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); #else #define expand_upwards(vma, address) (0) #endif /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, struct vm_area_struct **pprev); /* Look up the first VMA which intersects the interval start_addr..end_addr-1, NULL if none. Assume start_addr < end_addr. */ static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * mm, unsigned long start_addr, unsigned long end_addr) { struct vm_area_struct * vma = find_vma(mm,start_addr); if (vma && end_addr <= vma->vm_start) vma = NULL; return vma; } static inline unsigned long vm_start_gap(struct vm_area_struct *vma) { unsigned long vm_start = vma->vm_start; if (vma->vm_flags & VM_GROWSDOWN) { vm_start -= stack_guard_gap; if (vm_start > vma->vm_start) vm_start = 0; } return vm_start; } static inline unsigned long vm_end_gap(struct vm_area_struct *vma) { unsigned long vm_end = vma->vm_end; if (vma->vm_flags & VM_GROWSUP) { vm_end += stack_guard_gap; if (vm_end < vma->vm_end) vm_end = -PAGE_SIZE; } return vm_end; } static inline unsigned long vma_pages(struct vm_area_struct *vma) { return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; } /* Look up the first VMA which exactly match the interval vm_start ... vm_end */ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, unsigned long vm_start, unsigned long vm_end) { struct vm_area_struct *vma = find_vma(mm, vm_start); if (vma && (vma->vm_start != vm_start || vma->vm_end != vm_end)) vma = NULL; return vma; } static inline bool range_in_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { return (vma && vma->vm_start <= start && end <= vma->vm_end); } #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); #else static inline pgprot_t vm_get_page_prot(unsigned long vm_flags) { return __pgprot(0); } static inline void vma_set_page_prot(struct vm_area_struct *vma) { vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); } #endif #ifdef CONFIG_NUMA_BALANCING unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long start, unsigned long end); #endif struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num); int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num); int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num); vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { int err = vm_insert_page(vma, addr, page); if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } #ifndef io_remap_pfn_range static inline int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot)); } #endif static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) return VM_FAULT_OOM; return VM_FAULT_SIGBUS; } struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags); #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ #define FOLL_GET 0x04 /* do get_page on page */ #define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ #define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO * and return without waiting upon it */ #define FOLL_POPULATE 0x40 /* fault in page */ #define FOLL_SPLIT 0x80 /* don't return transhuge pages, split them */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_MLOCK 0x1000 /* lock present pages */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ #define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */ #define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */ /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each * other. Here is what they mean, and how to use them: * * FOLL_LONGTERM indicates that the page will be held for an indefinite time * period _often_ under userspace control. This is in contrast to * iov_iter_get_pages(), whose usages are transient. * * FIXME: For pages which are part of a filesystem, mappings are subject to the * lifetime enforced by the filesystem and we need guarantees that longterm * users like RDMA and V4L2 only establish mappings which coordinate usage with * the filesystem. Ideas for this coordination include revoking the longterm * pin, delaying writeback, bounce buffer page writeback, etc. As FS DAX was * added after the problem with filesystems was found FS DAX VMAs are * specifically failed. Filesystem pages are still subject to bugs and use of * FOLL_LONGTERM should be avoided on those pages. * * FIXME: Also NOTE that FOLL_LONGTERM is not supported in every GUP call. * Currently only get_user_pages() and get_user_pages_fast() support this flag * and calls to get_user_pages_[un]locked are specifically not allowed. This * is due to an incompatibility with the FS DAX check and * FAULT_FLAG_ALLOW_RETRY. * * In the CMA case: long term pins in a CMA region would unnecessarily fragment * that region. And so, CMA attempts to migrate the page before pinning, when * FOLL_LONGTERM is specified. * * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount, * but an additional pin counting system) will be invoked. This is intended for * anything that gets a page reference and then touches page data (for example, * Direct IO). This lets the filesystem know that some non-file-system entity is * potentially changing the pages' data. In contrast to FOLL_GET (whose pages * are released via put_page()), FOLL_PIN pages must be released, ultimately, by * a call to unpin_user_page(). * * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different * and separate refcounting mechanisms, however, and that means that each has * its own acquire and release mechanisms: * * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. * * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release. * * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based * calls applied to them, and that's perfectly OK. This is a constraint on the * callers, not on the pages.) * * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never * directly by the caller. That's in order to help avoid mismatches when * releasing pages: get_user_pages*() pages must be released via put_page(), * while pin_user_pages*() pages must be released via unpin_user_page(). * * Please see Documentation/core-api/pin_user_pages.rst for more information. */ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { if (vm_fault & VM_FAULT_OOM) return -ENOMEM; if (vm_fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return (foll_flags & FOLL_HWPOISON) ? -EHWPOISON : -EFAULT; if (vm_fault & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; return 0; } typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); extern void kernel_poison_pages(struct page *page, int numpages, int enable); #else static inline bool page_poisoning_enabled(void) { return false; } static inline void kernel_poison_pages(struct page *page, int numpages, int enable) { } #endif #ifdef CONFIG_INIT_ON_ALLOC_DEFAULT_ON DECLARE_STATIC_KEY_TRUE(init_on_alloc); #else DECLARE_STATIC_KEY_FALSE(init_on_alloc); #endif static inline bool want_init_on_alloc(gfp_t flags) { if (static_branch_unlikely(&init_on_alloc) && !page_poisoning_enabled()) return true; return flags & __GFP_ZERO; } #ifdef CONFIG_INIT_ON_FREE_DEFAULT_ON DECLARE_STATIC_KEY_TRUE(init_on_free); #else DECLARE_STATIC_KEY_FALSE(init_on_free); #endif static inline bool want_init_on_free(void) { return static_branch_unlikely(&init_on_free) && !page_poisoning_enabled(); } #ifdef CONFIG_DEBUG_PAGEALLOC extern void init_debug_pagealloc(void); #else static inline void init_debug_pagealloc(void) {} #endif extern bool _debug_pagealloc_enabled_early; DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); static inline bool debug_pagealloc_enabled(void) { return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled_early; } /* * For use in fast paths after init_debug_pagealloc() has run, or when a * false negative result is not harmful when called too early. */ static inline bool debug_pagealloc_enabled_static(void) { if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) return false; return static_branch_unlikely(&_debug_pagealloc_enabled); } #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP) extern void __kernel_map_pages(struct page *page, int numpages, int enable); /* * When called in DEBUG_PAGEALLOC context, the call should most likely be * guarded by debug_pagealloc_enabled() or debug_pagealloc_enabled_static() */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) { __kernel_map_pages(page, numpages, enable); } #ifdef CONFIG_HIBERNATION extern bool kernel_page_present(struct page *page); #endif /* CONFIG_HIBERNATION */ #else /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) {} #ifdef CONFIG_HIBERNATION static inline bool kernel_page_present(struct page *page) { return true; } #endif /* CONFIG_HIBERNATION */ #endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); extern int in_gate_area_no_mm(unsigned long addr); extern int in_gate_area(struct mm_struct *mm, unsigned long addr); #else static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { return NULL; } static inline int in_gate_area_no_mm(unsigned long addr) { return 0; } static inline int in_gate_area(struct mm_struct *mm, unsigned long addr) { return 0; } #endif /* __HAVE_ARCH_GATE_AREA */ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); #ifdef CONFIG_SYSCTL extern int sysctl_drop_caches; int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); #endif void drop_slab(void); void drop_slab_node(int nid); #ifndef CONFIG_MMU #define randomize_va_space 0 #else extern int randomize_va_space; #endif const char * arch_vma_name(struct vm_area_struct *vma); #ifdef CONFIG_MMU void print_vma_addr(char *prefix, unsigned long rip); #else static inline void print_vma_addr(char *prefix, unsigned long rip) { } #endif void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, struct vmem_altmap *altmap); void *vmemmap_alloc_block(unsigned long size, int node); struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); void vmemmap_populate_print_last(void); #ifdef CONFIG_MEMORY_HOTPLUG void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long nr_pages); enum mf_flags { MF_COUNT_INCREASED = 1 << 0, MF_ACTION_REQUIRED = 1 << 1, MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, }; extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); /* * Error handlers for various types of pages. */ enum mf_result { MF_IGNORED, /* Error: cannot be handled */ MF_FAILED, /* Error: handling failed */ MF_DELAYED, /* Will be handled later */ MF_RECOVERED, /* Successfully recovered */ }; enum mf_action_page_type { MF_MSG_KERNEL, MF_MSG_KERNEL_HIGH_ORDER, MF_MSG_SLAB, MF_MSG_DIFFERENT_COMPOUND, MF_MSG_POISONED_HUGE, MF_MSG_HUGE, MF_MSG_FREE_HUGE, MF_MSG_NON_PMD_HUGE, MF_MSG_UNMAP_FAILED, MF_MSG_DIRTY_SWAPCACHE, MF_MSG_CLEAN_SWAPCACHE, MF_MSG_DIRTY_MLOCKED_LRU, MF_MSG_CLEAN_MLOCKED_LRU, MF_MSG_DIRTY_UNEVICTABLE_LRU, MF_MSG_CLEAN_UNEVICTABLE_LRU, MF_MSG_DIRTY_LRU, MF_MSG_CLEAN_LRU, MF_MSG_TRUNCATED_LRU, MF_MSG_BUDDY, MF_MSG_BUDDY_2ND, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, MF_MSG_UNKNOWN, }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) extern void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page); extern void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr_hint, struct vm_area_struct *vma, unsigned int pages_per_huge_page); extern long copy_huge_page_from_user(struct page *dst_page, const void __user *usr_src, unsigned int pages_per_huge_page, bool allow_pagefault); /** * vma_is_special_huge - Are transhuge page-table entries considered special? * @vma: Pointer to the struct vm_area_struct to consider * * Whether transhuge page-table entries are considered "special" following * the definition in vm_normal_page(). * * Return: true if transhuge page-table entries should be considered special, * false otherwise. */ static inline bool vma_is_special_huge(const struct vm_area_struct *vma) { return vma_is_dax(vma) || (vma->vm_file && (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #ifdef CONFIG_DEBUG_PAGEALLOC extern unsigned int _debug_guardpage_minorder; DECLARE_STATIC_KEY_FALSE(_debug_guardpage_enabled); static inline unsigned int debug_guardpage_minorder(void) { return _debug_guardpage_minorder; } static inline bool debug_guardpage_enabled(void) { return static_branch_unlikely(&_debug_guardpage_enabled); } static inline bool page_is_guard(struct page *page) { if (!debug_guardpage_enabled()) return false; return PageGuard(page); } #else static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool debug_guardpage_enabled(void) { return false; } static inline bool page_is_guard(struct page *page) { return false; } #endif /* CONFIG_DEBUG_PAGEALLOC */ #if MAX_NUMNODES > 1 void __init setup_nr_node_ids(void); #else static inline void setup_nr_node_ids(void) {} #endif extern int memcmp_pages(struct page *page1, struct page *page2); static inline int pages_identical(struct page *page1, struct page *page2) { return !memcmp_pages(page1, page2); } #ifdef CONFIG_MAPPING_DIRTY_HELPERS unsigned long clean_record_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr, pgoff_t bitmap_pgoff, unsigned long *bitmap, pgoff_t *start, pgoff_t *end); unsigned long wp_shared_mapping_range(struct address_space *mapping, pgoff_t first_index, pgoff_t nr); #endif extern int sysctl_nr_trim_pages; static inline bool is_write_sealed(int seals) { return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE); } /** * is_readonly_sealed - Checks whether write-sealed but mapped read-only, * in which case writes should be disallowing moving * forwards. * @seals: the seals to check * @vm_flags: the VMA flags to check * * Returns whether readonly sealed, in which case writess should be disallowed * going forward. */ static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags) { /* * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as * MAP_SHARED and read-only, take care to not allow mprotect to * revert protections on such mappings. Do this only for shared * mappings. For private mappings, don't need to mask * VM_MAYWRITE as we still want them to be COW-writable. */ if (is_write_sealed(seals) && ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED)) return true; return false; } /** * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and * handle them. * @seals: the seals to check * @vma: the vma to operate on * * Check whether F_SEAL_WRITE or F_SEAL_FUTURE_WRITE are set; if so, do proper * check/handling on the vma flags. Return 0 if check pass, or <0 for errors. */ static inline int seal_check_write(int seals, struct vm_area_struct *vma) { if (!is_write_sealed(seals)) return 0; /* * New PROT_WRITE and MAP_SHARED mmaps are not allowed when * write seals are active. */ if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) return -EPERM; return 0; } #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 | /* * include/linux/topology.h * * Written by: Matthew Dobson, IBM Corporation * * Copyright (C) 2002, IBM Corp. * * All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or * NON INFRINGEMENT. See the GNU General Public License for more * details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * Send feedback to <colpatch@us.ibm.com> */ #ifndef _LINUX_TOPOLOGY_H #define _LINUX_TOPOLOGY_H #include <linux/arch_topology.h> #include <linux/cpumask.h> #include <linux/bitops.h> #include <linux/mmzone.h> #include <linux/smp.h> #include <linux/percpu.h> #include <asm/topology.h> #ifndef nr_cpus_node #define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node)) #endif #define for_each_node_with_cpus(node) \ for_each_online_node(node) \ if (nr_cpus_node(node)) int arch_update_cpu_topology(void); /* Conform to ACPI 2.0 SLIT distance definitions */ #define LOCAL_DISTANCE 10 #define REMOTE_DISTANCE 20 #define DISTANCE_BITS 8 #ifndef node_distance #define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE) #endif #ifndef RECLAIM_DISTANCE /* * If the distance between nodes in a system is larger than RECLAIM_DISTANCE * (in whatever arch specific measurement units returned by node_distance()) * and node_reclaim_mode is enabled then the VM will only call node_reclaim() * on nodes within this distance. */ #define RECLAIM_DISTANCE 30 #endif /* * The following tunable allows platforms to override the default node * reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are * sufficiently fast that the default value actually hurts * performance. * * AMD EPYC machines use this because even though the 2-hop distance * is 32 (3.2x slower than a local memory access) performance actually * *improves* if allowed to reclaim memory and load balance tasks * between NUMA nodes 2-hops apart. */ extern int __read_mostly node_reclaim_distance; #ifndef PENALTY_FOR_NODE_WITH_CPUS #define PENALTY_FOR_NODE_WITH_CPUS (1) #endif #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DECLARE_PER_CPU(int, numa_node); #ifndef numa_node_id /* Returns the number of the current Node. */ static inline int numa_node_id(void) { return raw_cpu_read(numa_node); } #endif #ifndef cpu_to_node static inline int cpu_to_node(int cpu) { return per_cpu(numa_node, cpu); } #endif #ifndef set_numa_node static inline void set_numa_node(int node) { this_cpu_write(numa_node, node); } #endif #ifndef set_cpu_numa_node static inline void set_cpu_numa_node(int cpu, int node) { per_cpu(numa_node, cpu) = node; } #endif #else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */ /* Returns the number of the current Node. */ #ifndef numa_node_id static inline int numa_node_id(void) { return cpu_to_node(raw_smp_processor_id()); } #endif #endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */ #ifdef CONFIG_HAVE_MEMORYLESS_NODES /* * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem(). */ DECLARE_PER_CPU(int, _numa_mem_); #ifndef set_numa_mem static inline void set_numa_mem(int node) { this_cpu_write(_numa_mem_, node); } #endif #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return raw_cpu_read(_numa_mem_); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return per_cpu(_numa_mem_, cpu); } #endif #ifndef set_cpu_numa_mem static inline void set_cpu_numa_mem(int cpu, int node) { per_cpu(_numa_mem_, cpu) = node; } #endif #else /* !CONFIG_HAVE_MEMORYLESS_NODES */ #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return numa_node_id(); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return cpu_to_node(cpu); } #endif #endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */ #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_die_id #define topology_die_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif #ifndef topology_sibling_cpumask #define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif #if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) { return topology_sibling_cpumask(cpu); } #endif static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); } #endif /* _LINUX_TOPOLOGY_H */ |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SPINLOCK_H #define __LINUX_SPINLOCK_H /* * include/linux/spinlock.h - generic spinlock/rwlock declarations * * here's the role of the various spinlock/rwlock related include files: * * on SMP builds: * * asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the * initializers * * linux/spinlock_types.h: * defines the generic type and initializers * * asm/spinlock.h: contains the arch_spin_*()/etc. lowlevel * implementations, mostly inline assembly code * * (also included on UP-debug builds:) * * linux/spinlock_api_smp.h: * contains the prototypes for the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. * * on UP builds: * * linux/spinlock_type_up.h: * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * * linux/spinlock_types.h: * defines the generic type and initializers * * linux/spinlock_up.h: * contains the arch_spin_*()/etc. version of UP * builds. (which are NOPs on non-debug, non-preempt * builds) * * (included on UP-non-debug builds:) * * linux/spinlock_api_up.h: * builds the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. */ #include <linux/typecheck.h> #include <linux/preempt.h> #include <linux/linkage.h> #include <linux/compiler.h> #include <linux/irqflags.h> #include <linux/thread_info.h> #include <linux/kernel.h> #include <linux/stringify.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <asm/barrier.h> #include <asm/mmiowb.h> /* * Must define these before including other files, inline functions need them */ #define LOCK_SECTION_NAME ".text..lock."KBUILD_BASENAME #define LOCK_SECTION_START(extra) \ ".subsection 1\n\t" \ extra \ ".ifndef " LOCK_SECTION_NAME "\n\t" \ LOCK_SECTION_NAME ":\n\t" \ ".endif\n" #define LOCK_SECTION_END \ ".previous\n\t" #define __lockfunc __section(".spinlock.text") /* * Pull the arch_spinlock_t and arch_rwlock_t definitions: */ #include <linux/spinlock_types.h> /* * Pull the arch_spin*() functions/declarations (UP-nondebug doesn't need them): */ #ifdef CONFIG_SMP # include <asm/spinlock.h> #else # include <linux/spinlock_up.h> #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, struct lock_class_key *key, short inner); # define raw_spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init((lock), #lock, &__key, LD_WAIT_SPIN); \ } while (0) #else # define raw_spin_lock_init(lock) \ do { *(lock) = __RAW_SPIN_LOCK_UNLOCKED(lock); } while (0) #endif #define raw_spin_is_locked(lock) arch_spin_is_locked(&(lock)->raw_lock) #ifdef arch_spin_is_contended #define raw_spin_is_contended(lock) arch_spin_is_contended(&(lock)->raw_lock) #else #define raw_spin_is_contended(lock) (((void)(lock), 0)) #endif /*arch_spin_is_contended*/ /* * smp_mb__after_spinlock() provides the equivalent of a full memory barrier * between program-order earlier lock acquisitions and program-order later * memory accesses. * * This guarantees that the following two properties hold: * * 1) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 * * WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1); * spin_lock(S); smp_mb(); * smp_mb__after_spinlock(); r1 = READ_ONCE(X); * r0 = READ_ONCE(Y); * spin_unlock(S); * * it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0) * and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments * preceding the call to smp_mb__after_spinlock() in __schedule() and in * try_to_wake_up(). * * 2) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 CPU2 * * spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y); * WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb(); * spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X); * WRITE_ONCE(Y, 1); * spin_unlock(S); * * it is forbidden that CPU0's critical section executes before CPU1's * critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1) * and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments * preceding the calls to smp_rmb() in try_to_wake_up() for similar * snippets but "projected" onto two CPUs. * * Property (2) upgrades the lock to an RCsc lock. * * Since most load-store architectures implement ACQUIRE with an smp_mb() after * the LL/SC loop, they need no further barriers. Similarly all our TSO * architectures imply an smp_mb() for each atomic instruction and equally don't * need more. * * Architectures that can implement ACQUIRE better need to take care. */ #ifndef smp_mb__after_spinlock #define smp_mb__after_spinlock() do { } while (0) #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); #define do_raw_spin_lock_flags(lock, flags) do_raw_spin_lock(lock) extern int do_raw_spin_trylock(raw_spinlock_t *lock); extern void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock); #else static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock) { __acquire(lock); arch_spin_lock(&lock->raw_lock); mmiowb_spin_lock(); } #ifndef arch_spin_lock_flags #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) #endif static inline void do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lock) { __acquire(lock); arch_spin_lock_flags(&lock->raw_lock, *flags); mmiowb_spin_lock(); } static inline int do_raw_spin_trylock(raw_spinlock_t *lock) { int ret = arch_spin_trylock(&(lock)->raw_lock); if (ret) mmiowb_spin_lock(); return ret; } static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) { mmiowb_spin_unlock(); arch_spin_unlock(&lock->raw_lock); __release(lock); } #endif /* * Define the various spin_lock methods. Note we define these * regardless of whether CONFIG_SMP or CONFIG_PREEMPTION are set. The * various methods are defined as nops in the case they are not * required. */ #define raw_spin_trylock(lock) __cond_lock(lock, _raw_spin_trylock(lock)) #define raw_spin_lock(lock) _raw_spin_lock(lock) #ifdef CONFIG_DEBUG_LOCK_ALLOC # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock_nested(lock, subclass) # define raw_spin_lock_nest_lock(lock, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map);\ _raw_spin_lock_nest_lock(lock, &(nest_lock)->dep_map); \ } while (0) #else /* * Always evaluate the 'subclass' argument to avoid that the compiler * warns about set-but-not-used variables when building with * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1. */ # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock(((void)(subclass), (lock))) # define raw_spin_lock_nest_lock(lock, nest_lock) _raw_spin_lock(lock) #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave_nested(lock, subclass); \ } while (0) #else #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #endif #else #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_lock_irqsave(lock, flags); \ } while (0) #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ raw_spin_lock_irqsave(lock, flags) #endif #define raw_spin_lock_irq(lock) _raw_spin_lock_irq(lock) #define raw_spin_lock_bh(lock) _raw_spin_lock_bh(lock) #define raw_spin_unlock(lock) _raw_spin_unlock(lock) #define raw_spin_unlock_irq(lock) _raw_spin_unlock_irq(lock) #define raw_spin_unlock_irqrestore(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_unlock_irqrestore(lock, flags); \ } while (0) #define raw_spin_unlock_bh(lock) _raw_spin_unlock_bh(lock) #define raw_spin_trylock_bh(lock) \ __cond_lock(lock, _raw_spin_trylock_bh(lock)) #define raw_spin_trylock_irq(lock) \ ({ \ local_irq_disable(); \ raw_spin_trylock(lock) ? \ 1 : ({ local_irq_enable(); 0; }); \ }) #define raw_spin_trylock_irqsave(lock, flags) \ ({ \ local_irq_save(flags); \ raw_spin_trylock(lock) ? \ 1 : ({ local_irq_restore(flags); 0; }); \ }) /* Include rwlock functions */ #include <linux/rwlock.h> /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) # include <linux/spinlock_api_smp.h> #else # include <linux/spinlock_api_up.h> #endif /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ static __always_inline raw_spinlock_t *spinlock_check(spinlock_t *lock) { return &lock->rlock; } #ifdef CONFIG_DEBUG_SPINLOCK # define spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init(spinlock_check(lock), \ #lock, &__key, LD_WAIT_CONFIG); \ } while (0) #else # define spin_lock_init(_lock) \ do { \ spinlock_check(_lock); \ *(_lock) = __SPIN_LOCK_UNLOCKED(_lock); \ } while (0) #endif static __always_inline void spin_lock(spinlock_t *lock) { raw_spin_lock(&lock->rlock); } static __always_inline void spin_lock_bh(spinlock_t *lock) { raw_spin_lock_bh(&lock->rlock); } static __always_inline int spin_trylock(spinlock_t *lock) { return raw_spin_trylock(&lock->rlock); } #define spin_lock_nested(lock, subclass) \ do { \ raw_spin_lock_nested(spinlock_check(lock), subclass); \ } while (0) #define spin_lock_nest_lock(lock, nest_lock) \ do { \ raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock); \ } while (0) static __always_inline void spin_lock_irq(spinlock_t *lock) { raw_spin_lock_irq(&lock->rlock); } #define spin_lock_irqsave(lock, flags) \ do { \ raw_spin_lock_irqsave(spinlock_check(lock), flags); \ } while (0) #define spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ raw_spin_lock_irqsave_nested(spinlock_check(lock), flags, subclass); \ } while (0) static __always_inline void spin_unlock(spinlock_t *lock) { raw_spin_unlock(&lock->rlock); } static __always_inline void spin_unlock_bh(spinlock_t *lock) { raw_spin_unlock_bh(&lock->rlock); } static __always_inline void spin_unlock_irq(spinlock_t *lock) { raw_spin_unlock_irq(&lock->rlock); } static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) { raw_spin_unlock_irqrestore(&lock->rlock, flags); } static __always_inline int spin_trylock_bh(spinlock_t *lock) { return raw_spin_trylock_bh(&lock->rlock); } static __always_inline int spin_trylock_irq(spinlock_t *lock) { return raw_spin_trylock_irq(&lock->rlock); } #define spin_trylock_irqsave(lock, flags) \ ({ \ raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) /** * spin_is_locked() - Check whether a spinlock is locked. * @lock: Pointer to the spinlock. * * This function is NOT required to provide any memory ordering * guarantees; it could be used for debugging purposes or, when * additional synchronization is needed, accompanied with other * constructs (memory barriers) enforcing the synchronization. * * Returns: 1 if @lock is locked, 0 otherwise. * * Note that the function only tells you that the spinlock is * seen to be locked, not that it is locked on your CPU. * * Further, on CONFIG_SMP=n builds with CONFIG_DEBUG_SPINLOCK=n, * the return value is always 0 (see include/linux/spinlock_up.h). * Therefore you should not rely heavily on the return value. */ static __always_inline int spin_is_locked(spinlock_t *lock) { return raw_spin_is_locked(&lock->rlock); } static __always_inline int spin_is_contended(spinlock_t *lock) { return raw_spin_is_contended(&lock->rlock); } #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) /* * Pull the atomic_t declaration: * (asm-mips/atomic.h needs above definitions) */ #include <linux/atomic.h> /** * atomic_dec_and_lock - lock on reaching reference count zero * @atomic: the atomic counter * @lock: the spinlock in question * * Decrements @atomic by 1. If the result is 0, returns true and locks * @lock. Returns false for all other cases. */ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); #define atomic_dec_and_lock(atomic, lock) \ __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags); #define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp, const char *name, struct lock_class_key *key); #define alloc_bucket_spinlocks(locks, lock_mask, max_size, cpu_mult, gfp) \ ({ \ static struct lock_class_key key; \ int ret; \ \ ret = __alloc_bucket_spinlocks(locks, lock_mask, max_size, \ cpu_mult, gfp, #locks, &key); \ ret; \ }) void free_bucket_spinlocks(spinlock_t *locks); #endif /* __LINUX_SPINLOCK_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _DELAYED_CALL_H #define _DELAYED_CALL_H /* * Poor man's closures; I wish we could've done them sanely polymorphic, * but... */ struct delayed_call { void (*fn)(void *); void *arg; }; #define DEFINE_DELAYED_CALL(name) struct delayed_call name = {NULL, NULL} /* I really wish we had closures with sane typechecking... */ static inline void set_delayed_call(struct delayed_call *call, void (*fn)(void *), void *arg) { call->fn = fn; call->arg = arg; } static inline void do_delayed_call(struct delayed_call *call) { if (call->fn) call->fn(call->arg); } static inline void clear_delayed_call(struct delayed_call *call) { call->fn = NULL; } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 | #ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H #define _LINUX_UNALIGNED_PACKED_STRUCT_H #include <linux/kernel.h> struct __una_u16 { u16 x; } __packed; struct __una_u32 { u32 x; } __packed; struct __una_u64 { u64 x; } __packed; static inline u16 __get_unaligned_cpu16(const void *p) { const struct __una_u16 *ptr = (const struct __una_u16 *)p; return ptr->x; } static inline u32 __get_unaligned_cpu32(const void *p) { const struct __una_u32 *ptr = (const struct __una_u32 *)p; return ptr->x; } static inline u64 __get_unaligned_cpu64(const void *p) { const struct __una_u64 *ptr = (const struct __una_u64 *)p; return ptr->x; } static inline void __put_unaligned_cpu16(u16 val, void *p) { struct __una_u16 *ptr = (struct __una_u16 *)p; ptr->x = val; } static inline void __put_unaligned_cpu32(u32 val, void *p) { struct __una_u32 *ptr = (struct __una_u32 *)p; ptr->x = val; } static inline void __put_unaligned_cpu64(u64 val, void *p) { struct __una_u64 *ptr = (struct __una_u64 *)p; ptr->x = val; } #endif /* _LINUX_UNALIGNED_PACKED_STRUCT_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> #include <linux/sched.h> #include <linux/thread_info.h> #include <asm/uaccess.h> #ifdef CONFIG_SET_FS /* * Force the uaccess routines to be wired up for actual userspace access, * overriding any possible set_fs(KERNEL_DS) still lingering around. Undone * using force_uaccess_end below. */ static inline mm_segment_t force_uaccess_begin(void) { mm_segment_t fs = get_fs(); set_fs(USER_DS); return fs; } static inline void force_uaccess_end(mm_segment_t oldfs) { set_fs(oldfs); } #else /* CONFIG_SET_FS */ typedef struct { /* empty dummy */ } mm_segment_t; #ifndef TASK_SIZE_MAX #define TASK_SIZE_MAX TASK_SIZE #endif #define uaccess_kernel() (false) #define user_addr_max() (TASK_SIZE_MAX) static inline mm_segment_t force_uaccess_begin(void) { return (mm_segment_t) { }; } static inline void force_uaccess_end(mm_segment_t oldfs) { } #endif /* CONFIG_SET_FS */ /* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). * * raw_copy_{to,from}_user(to, from, size) should copy up to size bytes and * return the amount left to copy. They should assume that access_ok() has * already been checked (and succeeded); they should *not* zero-pad anything. * No KASAN or object size checks either - those belong here. * * Both of these functions should attempt to copy size bytes starting at from * into the area starting at to. They must not fetch or store anything * outside of those areas. Return value must be between 0 (everything * copied successfully) and size (nothing copied). * * If raw_copy_{to,from}_user(to, from, size) returns N, size - N bytes starting * at to must become equal to the bytes fetched from the corresponding area * starting at from. All data past to + size - N must be left unmodified. * * If copying succeeds, the return value must be 0. If some data cannot be * fetched, it is permitted to copy less than had been fetched; the only * hard requirement is that not storing anything at all (i.e. returning size) * should happen only when nothing could be copied. In other words, you don't * have to squeeze as much as possible - it is allowed, but not necessary. * * For raw_copy_from_user() to always points to kernel memory and no faults * on store should happen. Interpretation of from is affected by set_fs(). * For raw_copy_to_user() it's the other way round. * * Both can be inlined - it's up to architectures whether it wants to bother * with that. They should not be used directly; they are used to implement * the 6 functions (copy_{to,from}_user(), __copy_{to,from}_user_inatomic()) * that are used instead. Out of those, __... ones are inlined. Plain * copy_{to,from}_user() might or might not be inlined. If you want them * inlined, have asm/uaccess.h define INLINE_COPY_{TO,FROM}_USER. * * NOTE: only copy_from_user() zero-pads the destination in case of short copy. * Neither __copy_from_user() nor __copy_from_user_inatomic() zero anything * at all; their callers absolutely must check the return value. * * Biarch ones should also provide raw_copy_in_user() - similar to the above, * but both source and destination are __user pointers (affected by set_fs() * as usual) and both source and destination can trigger faults. */ static __always_inline __must_check unsigned long __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) { instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); } static __always_inline __must_check unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_from_user(to, from, n); check_object_size(to, n, false); return raw_copy_from_user(to, from, n); } /** * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking. * @to: Destination address, in user space. * @from: Source address, in kernel space. * @n: Number of bytes to copy. * * Context: User context only. * * Copy data from kernel space to user space. Caller must check * the specified block with access_ok() before calling this function. * The caller should also make sure he pins the user space address * so that we don't result in page fault and sleep. */ static __always_inline __must_check unsigned long __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } static __always_inline __must_check unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; instrument_copy_to_user(to, from, n); check_object_size(from, n, true); return raw_copy_to_user(to, from, n); } #ifdef INLINE_COPY_FROM_USER static inline __must_check unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { instrument_copy_from_user(to, from, n); res = raw_copy_from_user(to, from, n); } if (unlikely(res)) memset(to + (n - res), 0, res); return res; } #else extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); #endif #ifdef INLINE_COPY_TO_USER static inline __must_check unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } #else extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); #endif static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { if (likely(check_copy_size(to, n, false))) n = _copy_from_user(to, from, n); return n; } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { if (likely(check_copy_size(from, n, true))) n = _copy_to_user(to, from, n); return n; } #ifdef CONFIG_COMPAT static __always_inline unsigned long __must_check copy_in_user(void __user *to, const void __user *from, unsigned long n) { might_fault(); if (access_ok(to, n) && access_ok(from, n)) n = raw_copy_in_user(to, from, n); return n; } #endif #ifndef copy_mc_to_kernel /* * Without arch opt-in this generic copy_mc_to_kernel() will not handle * #MC (or arch equivalent) during source read. */ static inline unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); return 0; } #endif static __always_inline void pagefault_disabled_inc(void) { current->pagefault_disabled++; } static __always_inline void pagefault_disabled_dec(void) { current->pagefault_disabled--; } /* * These routines enable/disable the pagefault handler. If disabled, it will * not take any locks and go straight to the fixup table. * * User access methods will not sleep when called from a pagefault_disabled() * environment. */ static inline void pagefault_disable(void) { pagefault_disabled_inc(); /* * make sure to have issued the store before a pagefault * can hit. */ barrier(); } static inline void pagefault_enable(void) { /* * make sure to issue those last loads/stores before enabling * the pagefault handler again. */ barrier(); pagefault_disabled_dec(); } /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ static inline bool pagefault_disabled(void) { return current->pagefault_disabled != 0; } /* * The pagefault handler is in general disabled by pagefault_disable() or * when in irq context (via in_atomic()). * * This function should only be used by the fault handlers. Other users should * stick to pagefault_disabled(). * Please NEVER use preempt_disable() to disable the fault handler. With * !CONFIG_PREEMPT_COUNT, this is like a NOP. So the handler won't be disabled. * in_atomic() will report different values based on !CONFIG_PREEMPT_COUNT. */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long __copy_from_user_inatomic_nocache(void *to, const void __user *from, unsigned long n) { return __copy_from_user_inatomic(to, from, n); } #endif /* ARCH_HAS_NOCACHE_UACCESS */ extern __must_check int check_zeroed_user(const void __user *from, size_t size); /** * copy_struct_from_user: copy a struct from userspace * @dst: Destination address, in kernel space. This buffer must be @ksize * bytes long. * @ksize: Size of @dst struct. * @src: Source address, in userspace. * @usize: (Alleged) size of @src struct. * * Copies a struct from userspace to kernel space, in a way that guarantees * backwards-compatibility for struct syscall arguments (as long as future * struct extensions are made such that all new fields are *appended* to the * old struct, and zeroed-out new fields have the same meaning as the old * struct). * * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. * The recommended usage is something like the following: * * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) * { * int err; * struct foo karg = {}; * * if (usize > PAGE_SIZE) * return -E2BIG; * if (usize < FOO_SIZE_VER0) * return -EINVAL; * * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); * if (err) * return err; * * // ... * } * * There are three cases to consider: * * If @usize == @ksize, then it's copied verbatim. * * If @usize < @ksize, then the userspace has passed an old struct to a * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) * are to be zero-filled. * * If @usize > @ksize, then the userspace has passed a new struct to an * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) * are checked to ensure they are zeroed, otherwise -E2BIG is returned. * * Returns (in all cases, some data may have been copied): * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. * * -EFAULT: access to userspace failed. */ static __always_inline __must_check int copy_struct_from_user(void *dst, size_t ksize, const void __user *src, size_t usize) { size_t size = min(ksize, usize); size_t rest = max(ksize, usize) - size; /* Double check if ksize is larger than a known object size. */ if (WARN_ON_ONCE(ksize > __builtin_object_size(dst, 1))) return -E2BIG; /* Deal with trailing bytes. */ if (usize < ksize) { memset(dst + size, 0, rest); } else if (usize > ksize) { int ret = check_zeroed_user(src + size, rest); if (ret <= 0) return ret ?: -E2BIG; } /* Copy the interoperable parts of the struct. */ if (copy_from_user(dst, src, size)) return -EFAULT; return 0; } bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size); long copy_from_kernel_nofault(void *dst, const void *src, size_t size); long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size); long copy_from_user_nofault(void *dst, const void __user *src, size_t size); long notrace copy_to_user_nofault(void __user *dst, const void *src, size_t size); long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count); long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); /** * get_kernel_nofault(): safely attempt to read from a location * @val: read into this variable * @ptr: address to read from * * Returns 0 on success, or -EFAULT. */ #define get_kernel_nofault(val, ptr) ({ \ const typeof(val) *__gk_ptr = (ptr); \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) #define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) #define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) #define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end #endif #ifndef user_read_access_begin #define user_read_access_begin user_access_begin #define user_read_access_end user_access_end #endif #ifdef CONFIG_HARDENED_USERCOPY void usercopy_warn(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len); #endif #endif /* __LINUX_UACCESS_H__ */ |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/export.h> #include <linux/fault-inject-usercopy.h> #include <linux/kasan-checks.h> #include <linux/thread_info.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/mm.h> #include <asm/byteorder.h> #include <asm/word-at-a-time.h> #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS #define IS_UNALIGNED(src, dst) 0 #else #define IS_UNALIGNED(src, dst) \ (((long) dst | (long) src) & (sizeof(long) - 1)) #endif /* * Do a strncpy, return length of string without final '\0'. * 'count' is the user-supplied count (return 'count' if we * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ static inline long do_strncpy_from_user(char *dst, const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long res = 0; if (IS_UNALIGNED(src, dst)) goto byte_at_a_time; while (max >= sizeof(unsigned long)) { unsigned long c, data, mask; /* Fall back to byte-at-a-time if we get a page fault */ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); /* * Note that we mask out the bytes following the NUL. This is * important to do because string oblivious code may read past * the NUL. For those routines, we don't want to give them * potentially random bytes after the NUL in `src`. * * One example of such code is BPF map keys. BPF treats map keys * as an opaque set of bytes. Without the post-NUL mask, any BPF * maps keyed by strings returned from strncpy_from_user() may * have multiple entries for semantically identical strings. */ if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); mask = zero_bytemask(data); *(unsigned long *)(dst+res) = c & mask; return res + find_zero(data); } *(unsigned long *)(dst+res) = c; res += sizeof(unsigned long); max -= sizeof(unsigned long); } byte_at_a_time: while (max) { char c; unsafe_get_user(c,src+res, efault); dst[res] = c; if (!c) return res; res++; max--; } /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, that's ok - we got as much as the user asked for. */ if (res >= count) return res; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's an EFAULT. */ efault: return -EFAULT; } /** * strncpy_from_user: - Copy a NUL terminated string from userspace. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @src: Source address, in user space. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from userspace to kernel space. * * On success, returns the length of the string (not including the trailing * NUL). * * If access to userspace fails, returns -EFAULT (some data may have been * copied). * * If @count is smaller than the length of the string, copies @count bytes * and returns @count. */ long strncpy_from_user(char *dst, const char __user *src, long count) { unsigned long max_addr, src_addr; might_fault(); if (should_fail_usercopy()) return -EFAULT; if (unlikely(count <= 0)) return 0; max_addr = user_addr_max(); src_addr = (unsigned long)untagged_addr(src); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; kasan_check_write(dst, count); check_object_size(dst, count, false); if (user_read_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max); user_read_access_end(); return retval; } } return -EFAULT; } EXPORT_SYMBOL(strncpy_from_user); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_DEFS_H #define _ASM_X86_PGTABLE_DEFS_H #include <linux/const.h> #include <linux/mem_encrypt.h> #include <asm/page_types.h> #define FIRST_USER_ADDRESS 0UL #define _PAGE_BIT_PRESENT 0 /* is present */ #define _PAGE_BIT_RW 1 /* writeable */ #define _PAGE_BIT_USER 2 /* userspace addressable */ #define _PAGE_BIT_PWT 3 /* page write through */ #define _PAGE_BIT_PCD 4 /* page cache disabled */ #define _PAGE_BIT_ACCESSED 5 /* was accessed (raised by CPU) */ #define _PAGE_BIT_DIRTY 6 /* was written to (raised by CPU) */ #define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */ #define _PAGE_BIT_PAT 7 /* on 4KB pages */ #define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */ #define _PAGE_BIT_SOFTW1 9 /* available for programmer */ #define _PAGE_BIT_SOFTW2 10 /* " */ #define _PAGE_BIT_SOFTW3 11 /* " */ #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ #define _PAGE_BIT_SOFTW4 58 /* available for programmer */ #define _PAGE_BIT_PKEY_BIT0 59 /* Protection Keys, bit 1/4 */ #define _PAGE_BIT_PKEY_BIT1 60 /* Protection Keys, bit 2/4 */ #define _PAGE_BIT_PKEY_BIT2 61 /* Protection Keys, bit 3/4 */ #define _PAGE_BIT_PKEY_BIT3 62 /* Protection Keys, bit 4/4 */ #define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ #define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 #define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 #define _PAGE_BIT_UFFD_WP _PAGE_BIT_SOFTW2 /* userfaultfd wrprotected */ #define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ #define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4 /* If _PAGE_BIT_PRESENT is clear, we use these: */ /* - if the user mapped it with PROT_NONE; pte_present gives true */ #define _PAGE_BIT_PROTNONE _PAGE_BIT_GLOBAL #define _PAGE_PRESENT (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT) #define _PAGE_RW (_AT(pteval_t, 1) << _PAGE_BIT_RW) #define _PAGE_USER (_AT(pteval_t, 1) << _PAGE_BIT_USER) #define _PAGE_PWT (_AT(pteval_t, 1) << _PAGE_BIT_PWT) #define _PAGE_PCD (_AT(pteval_t, 1) << _PAGE_BIT_PCD) #define _PAGE_ACCESSED (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED) #define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY) #define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE) #define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) #define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1) #define _PAGE_SOFTW2 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2) #define _PAGE_SOFTW3 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW3) #define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT) #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) #define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL) #define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST) #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS #define _PAGE_PKEY_BIT0 (_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT0) #define _PAGE_PKEY_BIT1 (_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT1) #define _PAGE_PKEY_BIT2 (_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT2) #define _PAGE_PKEY_BIT3 (_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT3) #else #define _PAGE_PKEY_BIT0 (_AT(pteval_t, 0)) #define _PAGE_PKEY_BIT1 (_AT(pteval_t, 0)) #define _PAGE_PKEY_BIT2 (_AT(pteval_t, 0)) #define _PAGE_PKEY_BIT3 (_AT(pteval_t, 0)) #endif #define _PAGE_PKEY_MASK (_PAGE_PKEY_BIT0 | \ _PAGE_PKEY_BIT1 | \ _PAGE_PKEY_BIT2 | \ _PAGE_PKEY_BIT3) #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) #define _PAGE_KNL_ERRATUM_MASK (_PAGE_DIRTY | _PAGE_ACCESSED) #else #define _PAGE_KNL_ERRATUM_MASK 0 #endif #ifdef CONFIG_MEM_SOFT_DIRTY #define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY) #else #define _PAGE_SOFT_DIRTY (_AT(pteval_t, 0)) #endif /* * Tracking soft dirty bit when a page goes to a swap is tricky. * We need a bit which can be stored in pte _and_ not conflict * with swap entry format. On x86 bits 1-4 are *not* involved * into swap entry computation, but bit 7 is used for thp migration, * so we borrow bit 1 for soft dirty tracking. * * Please note that this bit must be treated as swap dirty page * mark if and only if the PTE/PMD has present bit clear! */ #ifdef CONFIG_MEM_SOFT_DIRTY #define _PAGE_SWP_SOFT_DIRTY _PAGE_RW #else #define _PAGE_SWP_SOFT_DIRTY (_AT(pteval_t, 0)) #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP #define _PAGE_UFFD_WP (_AT(pteval_t, 1) << _PAGE_BIT_UFFD_WP) #define _PAGE_SWP_UFFD_WP _PAGE_USER #else #define _PAGE_UFFD_WP (_AT(pteval_t, 0)) #define _PAGE_SWP_UFFD_WP (_AT(pteval_t, 0)) #endif #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) #define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX) #define _PAGE_DEVMAP (_AT(u64, 1) << _PAGE_BIT_DEVMAP) #else #define _PAGE_NX (_AT(pteval_t, 0)) #define _PAGE_DEVMAP (_AT(pteval_t, 0)) #endif #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) /* * Set of bits not changed in pte_modify. The pte's * protection key is treated like _PAGE_RW, for * instance, and is *not* included in this mask since * pte_modify() does modify it. */ #define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |\ _PAGE_SOFT_DIRTY | _PAGE_DEVMAP | _PAGE_ENC | \ _PAGE_UFFD_WP) #define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT) #define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE) /* * The cache modes defined here are used to translate between pure SW usage * and the HW defined cache mode bits and/or PAT entries. * * The resulting bits for PWT, PCD and PAT should be chosen in a way * to have the WB mode at index 0 (all bits clear). This is the default * right now and likely would break too much if changed. */ #ifndef __ASSEMBLY__ enum page_cache_mode { _PAGE_CACHE_MODE_WB = 0, _PAGE_CACHE_MODE_WC = 1, _PAGE_CACHE_MODE_UC_MINUS = 2, _PAGE_CACHE_MODE_UC = 3, _PAGE_CACHE_MODE_WT = 4, _PAGE_CACHE_MODE_WP = 5, _PAGE_CACHE_MODE_NUM = 8 }; #endif #define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) #define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT) #define _PAGE_LARGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT_LARGE) #define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) #define _PAGE_CACHE_WP (cachemode2protval(_PAGE_CACHE_MODE_WP)) #define __PP _PAGE_PRESENT #define __RW _PAGE_RW #define _USR _PAGE_USER #define ___A _PAGE_ACCESSED #define ___D _PAGE_DIRTY #define ___G _PAGE_GLOBAL #define __NX _PAGE_NX #define _ENC _PAGE_ENC #define __WP _PAGE_CACHE_WP #define __NC _PAGE_NOCACHE #define _PSE _PAGE_PSE #define pgprot_val(x) ((x).pgprot) #define __pgprot(x) ((pgprot_t) { (x) } ) #define __pg(x) __pgprot(x) #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) #define PAGE_NONE __pg( 0| 0| 0|___A| 0| 0| 0|___G) #define PAGE_SHARED __pg(__PP|__RW|_USR|___A|__NX| 0| 0| 0) #define PAGE_SHARED_EXEC __pg(__PP|__RW|_USR|___A| 0| 0| 0| 0) #define PAGE_COPY_NOEXEC __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0) #define PAGE_COPY_EXEC __pg(__PP| 0|_USR|___A| 0| 0| 0| 0) #define PAGE_COPY __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0) #define PAGE_READONLY __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0) #define PAGE_READONLY_EXEC __pg(__PP| 0|_USR|___A| 0| 0| 0| 0) #define __PAGE_KERNEL (__PP|__RW| 0|___A|__NX|___D| 0|___G) #define __PAGE_KERNEL_EXEC (__PP|__RW| 0|___A| 0|___D| 0|___G) #define _KERNPG_TABLE_NOENC (__PP|__RW| 0|___A| 0|___D| 0| 0) #define _KERNPG_TABLE (__PP|__RW| 0|___A| 0|___D| 0| 0| _ENC) #define _PAGE_TABLE_NOENC (__PP|__RW|_USR|___A| 0|___D| 0| 0) #define _PAGE_TABLE (__PP|__RW|_USR|___A| 0|___D| 0| 0| _ENC) #define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX|___D| 0|___G) #define __PAGE_KERNEL_ROX (__PP| 0| 0|___A| 0|___D| 0|___G) #define __PAGE_KERNEL_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC) #define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX|___D| 0|___G) #define __PAGE_KERNEL_LARGE (__PP|__RW| 0|___A|__NX|___D|_PSE|___G) #define __PAGE_KERNEL_LARGE_EXEC (__PP|__RW| 0|___A| 0|___D|_PSE|___G) #define __PAGE_KERNEL_WP (__PP|__RW| 0|___A|__NX|___D| 0|___G| __WP) #define __PAGE_KERNEL_IO __PAGE_KERNEL #define __PAGE_KERNEL_IO_NOCACHE __PAGE_KERNEL_NOCACHE #ifndef __ASSEMBLY__ #define __PAGE_KERNEL_ENC (__PAGE_KERNEL | _ENC) #define __PAGE_KERNEL_ENC_WP (__PAGE_KERNEL_WP | _ENC) #define __PAGE_KERNEL_NOENC (__PAGE_KERNEL | 0) #define __PAGE_KERNEL_NOENC_WP (__PAGE_KERNEL_WP | 0) #define __pgprot_mask(x) __pgprot((x) & __default_kernel_pte_mask) #define PAGE_KERNEL __pgprot_mask(__PAGE_KERNEL | _ENC) #define PAGE_KERNEL_NOENC __pgprot_mask(__PAGE_KERNEL | 0) #define PAGE_KERNEL_RO __pgprot_mask(__PAGE_KERNEL_RO | _ENC) #define PAGE_KERNEL_EXEC __pgprot_mask(__PAGE_KERNEL_EXEC | _ENC) #define PAGE_KERNEL_EXEC_NOENC __pgprot_mask(__PAGE_KERNEL_EXEC | 0) #define PAGE_KERNEL_ROX __pgprot_mask(__PAGE_KERNEL_ROX | _ENC) #define PAGE_KERNEL_NOCACHE __pgprot_mask(__PAGE_KERNEL_NOCACHE | _ENC) #define PAGE_KERNEL_LARGE __pgprot_mask(__PAGE_KERNEL_LARGE | _ENC) #define PAGE_KERNEL_LARGE_EXEC __pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC) #define PAGE_KERNEL_VVAR __pgprot_mask(__PAGE_KERNEL_VVAR | _ENC) #define PAGE_KERNEL_IO __pgprot_mask(__PAGE_KERNEL_IO) #define PAGE_KERNEL_IO_NOCACHE __pgprot_mask(__PAGE_KERNEL_IO_NOCACHE) #endif /* __ASSEMBLY__ */ /* xwr */ #define __P000 PAGE_NONE #define __P001 PAGE_READONLY #define __P010 PAGE_COPY #define __P011 PAGE_COPY #define __P100 PAGE_READONLY_EXEC #define __P101 PAGE_READONLY_EXEC #define __P110 PAGE_COPY_EXEC #define __P111 PAGE_COPY_EXEC #define __S000 PAGE_NONE #define __S001 PAGE_READONLY #define __S010 PAGE_SHARED #define __S011 PAGE_SHARED #define __S100 PAGE_READONLY_EXEC #define __S101 PAGE_READONLY_EXEC #define __S110 PAGE_SHARED_EXEC #define __S111 PAGE_SHARED_EXEC /* * early identity mapping pte attrib macros. */ #ifdef CONFIG_X86_64 #define __PAGE_KERNEL_IDENT_LARGE_EXEC __PAGE_KERNEL_LARGE_EXEC #else #define PTE_IDENT_ATTR 0x003 /* PRESENT+RW */ #define PDE_IDENT_ATTR 0x063 /* PRESENT+RW+DIRTY+ACCESSED */ #define PGD_IDENT_ATTR 0x001 /* PRESENT (no other attributes) */ #endif #ifdef CONFIG_X86_32 # include <asm/pgtable_32_types.h> #else # include <asm/pgtable_64_types.h> #endif #ifndef __ASSEMBLY__ #include <linux/types.h> /* Extracts the PFN from a (pte|pmd|pud|pgd)val_t of a 4KB page */ #define PTE_PFN_MASK ((pteval_t)PHYSICAL_PAGE_MASK) /* * Extracts the flags from a (pte|pmd|pud|pgd)val_t * This includes the protection key value. */ #define PTE_FLAGS_MASK (~PTE_PFN_MASK) typedef struct pgprot { pgprotval_t pgprot; } pgprot_t; typedef struct { pgdval_t pgd; } pgd_t; static inline pgprot_t pgprot_nx(pgprot_t prot) { return __pgprot(pgprot_val(prot) | _PAGE_NX); } #define pgprot_nx pgprot_nx #ifdef CONFIG_X86_PAE /* * PHYSICAL_PAGE_MASK might be non-constant when SME is compiled in, so we can't * use it here. */ #define PGD_PAE_PAGE_MASK ((signed long)PAGE_MASK) #define PGD_PAE_PHYS_MASK (((1ULL << __PHYSICAL_MASK_SHIFT)-1) & PGD_PAE_PAGE_MASK) /* * PAE allows Base Address, P, PWT, PCD and AVL bits to be set in PGD entries. * All other bits are Reserved MBZ */ #define PGD_ALLOWED_BITS (PGD_PAE_PHYS_MASK | _PAGE_PRESENT | \ _PAGE_PWT | _PAGE_PCD | \ _PAGE_SOFTW1 | _PAGE_SOFTW2 | _PAGE_SOFTW3) #else /* No need to mask any bits for !PAE */ #define PGD_ALLOWED_BITS (~0ULL) #endif static inline pgd_t native_make_pgd(pgdval_t val) { return (pgd_t) { val & PGD_ALLOWED_BITS }; } static inline pgdval_t native_pgd_val(pgd_t pgd) { return pgd.pgd & PGD_ALLOWED_BITS; } static inline pgdval_t pgd_flags(pgd_t pgd) { return native_pgd_val(pgd) & PTE_FLAGS_MASK; } #if CONFIG_PGTABLE_LEVELS > 4 typedef struct { p4dval_t p4d; } p4d_t; static inline p4d_t native_make_p4d(pudval_t val) { return (p4d_t) { val }; } static inline p4dval_t native_p4d_val(p4d_t p4d) { return p4d.p4d; } #else #include <asm-generic/pgtable-nop4d.h> static inline p4d_t native_make_p4d(pudval_t val) { return (p4d_t) { .pgd = native_make_pgd((pgdval_t)val) }; } static inline p4dval_t native_p4d_val(p4d_t p4d) { return native_pgd_val(p4d.pgd); } #endif #if CONFIG_PGTABLE_LEVELS > 3 typedef struct { pudval_t pud; } pud_t; static inline pud_t native_make_pud(pmdval_t val) { return (pud_t) { val }; } static inline pudval_t native_pud_val(pud_t pud) { return pud.pud; } #else #include <asm-generic/pgtable-nopud.h> static inline pud_t native_make_pud(pudval_t val) { return (pud_t) { .p4d.pgd = native_make_pgd(val) }; } static inline pudval_t native_pud_val(pud_t pud) { return native_pgd_val(pud.p4d.pgd); } #endif #if CONFIG_PGTABLE_LEVELS > 2 typedef struct { pmdval_t pmd; } pmd_t; static inline pmd_t native_make_pmd(pmdval_t val) { return (pmd_t) { val }; } static inline pmdval_t native_pmd_val(pmd_t pmd) { return pmd.pmd; } #else #include <asm-generic/pgtable-nopmd.h> static inline pmd_t native_make_pmd(pmdval_t val) { return (pmd_t) { .pud.p4d.pgd = native_make_pgd(val) }; } static inline pmdval_t native_pmd_val(pmd_t pmd) { return native_pgd_val(pmd.pud.p4d.pgd); } #endif static inline p4dval_t p4d_pfn_mask(p4d_t p4d) { /* No 512 GiB huge pages yet */ return PTE_PFN_MASK; } static inline p4dval_t p4d_flags_mask(p4d_t p4d) { return ~p4d_pfn_mask(p4d); } static inline p4dval_t p4d_flags(p4d_t p4d) { return native_p4d_val(p4d) & p4d_flags_mask(p4d); } static inline pudval_t pud_pfn_mask(pud_t pud) { if (native_pud_val(pud) & _PAGE_PSE) return PHYSICAL_PUD_PAGE_MASK; else return PTE_PFN_MASK; } static inline pudval_t pud_flags_mask(pud_t pud) { return ~pud_pfn_mask(pud); } static inline pudval_t pud_flags(pud_t pud) { return native_pud_val(pud) & pud_flags_mask(pud); } static inline pmdval_t pmd_pfn_mask(pmd_t pmd) { if (native_pmd_val(pmd) & _PAGE_PSE) return PHYSICAL_PMD_PAGE_MASK; else return PTE_PFN_MASK; } static inline pmdval_t pmd_flags_mask(pmd_t pmd) { return ~pmd_pfn_mask(pmd); } static inline pmdval_t pmd_flags(pmd_t pmd) { return native_pmd_val(pmd) & pmd_flags_mask(pmd); } static inline pte_t native_make_pte(pteval_t val) { return (pte_t) { .pte = val }; } static inline pteval_t native_pte_val(pte_t pte) { return pte.pte; } static inline pteval_t pte_flags(pte_t pte) { return native_pte_val(pte) & PTE_FLAGS_MASK; } #define __pte2cm_idx(cb) \ ((((cb) >> (_PAGE_BIT_PAT - 2)) & 4) | \ (((cb) >> (_PAGE_BIT_PCD - 1)) & 2) | \ (((cb) >> _PAGE_BIT_PWT) & 1)) #define __cm_idx2pte(i) \ ((((i) & 4) << (_PAGE_BIT_PAT - 2)) | \ (((i) & 2) << (_PAGE_BIT_PCD - 1)) | \ (((i) & 1) << _PAGE_BIT_PWT)) unsigned long cachemode2protval(enum page_cache_mode pcm); static inline pgprotval_t protval_4k_2_large(pgprotval_t val) { return (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); } static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot) { return __pgprot(protval_4k_2_large(pgprot_val(pgprot))); } static inline pgprotval_t protval_large_2_4k(pgprotval_t val) { return (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT_LARGE) >> (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); } static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot) { return __pgprot(protval_large_2_4k(pgprot_val(pgprot))); } typedef struct page *pgtable_t; extern pteval_t __supported_pte_mask; extern pteval_t __default_kernel_pte_mask; extern void set_nx(void); extern int nx_enabled; #define pgprot_writecombine pgprot_writecombine extern pgprot_t pgprot_writecombine(pgprot_t prot); #define pgprot_writethrough pgprot_writethrough extern pgprot_t pgprot_writethrough(pgprot_t prot); /* Indicate that x86 has its own track and untrack pfn vma functions */ #define __HAVE_PFNMAP_TRACKING #define __HAVE_PHYS_MEM_ACCESS_PROT struct file; pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); /* Install a pte for a particular vaddr in kernel space. */ void set_pte_vaddr(unsigned long vaddr, pte_t pte); #ifdef CONFIG_X86_32 extern void native_pagetable_init(void); #else #define native_pagetable_init paging_init #endif struct seq_file; extern void arch_report_meminfo(struct seq_file *m); enum pg_level { PG_LEVEL_NONE, PG_LEVEL_4K, PG_LEVEL_2M, PG_LEVEL_1G, PG_LEVEL_512G, PG_LEVEL_NUM }; #ifdef CONFIG_PROC_FS extern void update_page_count(int level, unsigned long pages); #else static inline void update_page_count(int level, unsigned long pages) { } #endif /* * Helper function that returns the kernel pagetable entry controlling * the virtual address 'address'. NULL means no pagetable entry present. * NOTE: the return type is pte_t but if the pmd is PSE then we return it * as a pte too. */ extern pte_t *lookup_address(unsigned long address, unsigned int *level); extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level); struct mm_struct; extern pte_t *lookup_address_in_mm(struct mm_struct *mm, unsigned long address, unsigned int *level); extern pmd_t *lookup_pmd_address(unsigned long address); extern phys_addr_t slow_virt_to_phys(void *__address); extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, unsigned numpages, unsigned long page_flags); extern int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address, unsigned long numpages); #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_DEFS_H */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Access vector cache interface for object managers. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ #ifndef _SELINUX_AVC_H_ #define _SELINUX_AVC_H_ #include <linux/stddef.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/kdev_t.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/audit.h> #include <linux/lsm_audit.h> #include <linux/in6.h> #include "flask.h" #include "av_permissions.h" #include "security.h" /* * An entry in the AVC. */ struct avc_entry; struct task_struct; struct inode; struct sock; struct sk_buff; /* * AVC statistics */ struct avc_cache_stats { unsigned int lookups; unsigned int misses; unsigned int allocations; unsigned int reclaims; unsigned int frees; }; /* * We only need this data after we have decided to send an audit message. */ struct selinux_audit_data { u32 ssid; u32 tsid; u16 tclass; u32 requested; u32 audited; u32 denied; int result; struct selinux_state *state; }; /* * AVC operations */ void __init avc_init(void); static inline u32 avc_audit_required(u32 requested, struct av_decision *avd, int result, u32 auditdeny, u32 *deniedp) { u32 denied, audited; denied = requested & ~avd->allowed; if (unlikely(denied)) { audited = denied & avd->auditdeny; /* * auditdeny is TRICKY! Setting a bit in * this field means that ANY denials should NOT be audited if * the policy contains an explicit dontaudit rule for that * permission. Take notice that this is unrelated to the * actual permissions that were denied. As an example lets * assume: * * denied == READ * avd.auditdeny & ACCESS == 0 (not set means explicit rule) * auditdeny & ACCESS == 1 * * We will NOT audit the denial even though the denied * permission was READ and the auditdeny checks were for * ACCESS */ if (auditdeny && !(auditdeny & avd->auditdeny)) audited = 0; } else if (result) audited = denied = requested; else audited = requested & avd->auditallow; *deniedp = denied; return audited; } int slow_avc_audit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u32 audited, u32 denied, int result, struct common_audit_data *a); /** * avc_audit - Audit the granting or denial of permissions. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions * @avd: access vector decisions * @result: result from avc_has_perm_noaudit * @a: auxiliary audit data * @flags: VFS walk flags * * Audit the granting or denial of permissions in accordance * with the policy. This function is typically called by * avc_has_perm() after a permission check, but can also be * called directly by callers who use avc_has_perm_noaudit() * in order to separate the permission check from the auditing. * For example, this separation is useful when the permission check must * be performed under a lock, to allow the lock to be released * before calling the auditing code. */ static inline int avc_audit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct av_decision *avd, int result, struct common_audit_data *a, int flags) { u32 audited, denied; audited = avc_audit_required(requested, avd, result, 0, &denied); if (likely(!audited)) return 0; /* fall back to ref-walk if we have to generate audit */ if (flags & MAY_NOT_BLOCK) return -ECHILD; return slow_avc_audit(state, ssid, tsid, tclass, requested, audited, denied, result, a); } #define AVC_STRICT 1 /* Ignore permissive mode. */ #define AVC_EXTENDED_PERMS 2 /* update extended permissions */ #define AVC_NONBLOCKING 4 /* non blocking */ int avc_has_perm_noaudit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, unsigned flags, struct av_decision *avd); int avc_has_perm(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata); int avc_has_perm_flags(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata, int flags); int avc_has_extended_perms(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u8 driver, u8 perm, struct common_audit_data *ad); u32 avc_policy_seqno(struct selinux_state *state); #define AVC_CALLBACK_GRANT 1 #define AVC_CALLBACK_TRY_REVOKE 2 #define AVC_CALLBACK_REVOKE 4 #define AVC_CALLBACK_RESET 8 #define AVC_CALLBACK_AUDITALLOW_ENABLE 16 #define AVC_CALLBACK_AUDITALLOW_DISABLE 32 #define AVC_CALLBACK_AUDITDENY_ENABLE 64 #define AVC_CALLBACK_AUDITDENY_DISABLE 128 #define AVC_CALLBACK_ADD_XPERMS 256 int avc_add_callback(int (*callback)(u32 event), u32 events); /* Exported to selinuxfs */ struct selinux_avc; int avc_get_hash_stats(struct selinux_avc *avc, char *page); unsigned int avc_get_cache_threshold(struct selinux_avc *avc); void avc_set_cache_threshold(struct selinux_avc *avc, unsigned int cache_threshold); /* Attempt to free avc node cache */ void avc_disable(void); #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS DECLARE_PER_CPU(struct avc_cache_stats, avc_cache_stats); #endif #endif /* _SELINUX_AVC_H_ */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM kmem #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KMEM_H #include <linux/types.h> #include <linux/tracepoint.h> #include <trace/events/mmflags.h> DECLARE_EVENT_CLASS(kmem_alloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( gfp_t, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = gfp_flags; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); DEFINE_EVENT(kmem_alloc, kmalloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags) ); DEFINE_EVENT(kmem_alloc, kmem_cache_alloc, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags) ); DECLARE_EVENT_CLASS(kmem_alloc_node, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) __field( size_t, bytes_req ) __field( size_t, bytes_alloc ) __field( gfp_t, gfp_flags ) __field( int, node ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; __entry->bytes_req = bytes_req; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = gfp_flags; __entry->node = node; ), TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d", (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags), __entry->node) ); DEFINE_EVENT(kmem_alloc_node, kmalloc_node, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node) ); DEFINE_EVENT(kmem_alloc_node, kmem_cache_alloc_node, TP_PROTO(unsigned long call_site, const void *ptr, size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags, int node), TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node) ); DECLARE_EVENT_CLASS(kmem_free, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( const void *, ptr ) ), TP_fast_assign( __entry->call_site = call_site; __entry->ptr = ptr; ), TP_printk("call_site=%pS ptr=%p", (void *)__entry->call_site, __entry->ptr) ); DEFINE_EVENT(kmem_free, kfree, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr) ); DEFINE_EVENT(kmem_free, kmem_cache_free, TP_PROTO(unsigned long call_site, const void *ptr), TP_ARGS(call_site, ptr) ); TRACE_EVENT(mm_page_free, TP_PROTO(struct page *page, unsigned int order), TP_ARGS(page, order), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->order = order; ), TP_printk("page=%p pfn=%lu order=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order) ); TRACE_EVENT(mm_page_free_batched, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field( unsigned long, pfn ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); ), TP_printk("page=%p pfn=%lu order=0", pfn_to_page(__entry->pfn), __entry->pfn) ); TRACE_EVENT(mm_page_alloc, TP_PROTO(struct page *page, unsigned int order, gfp_t gfp_flags, int migratetype), TP_ARGS(page, order, gfp_flags, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( gfp_t, gfp_flags ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->gfp_flags = gfp_flags; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=%lu order=%d migratetype=%d gfp_flags=%s", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, show_gfp_flags(__entry->gfp_flags)) ); DECLARE_EVENT_CLASS(mm_page, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=%lu order=%u migratetype=%d percpu_refill=%d", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, __entry->migratetype, __entry->order == 0) ); DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype) ); TRACE_EVENT(mm_page_pcpu_drain, TP_PROTO(struct page *page, unsigned int order, int migratetype), TP_ARGS(page, order, migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( unsigned int, order ) __field( int, migratetype ) ), TP_fast_assign( __entry->pfn = page ? page_to_pfn(page) : -1UL; __entry->order = order; __entry->migratetype = migratetype; ), TP_printk("page=%p pfn=%lu order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) ); TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( unsigned long, pfn ) __field( int, alloc_order ) __field( int, fallback_order ) __field( int, alloc_migratetype ) __field( int, fallback_migratetype ) __field( int, change_ownership ) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->alloc_order = alloc_order; __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; __entry->change_ownership = (alloc_migratetype == get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->alloc_order, __entry->fallback_order, pageblock_order, __entry->alloc_migratetype, __entry->fallback_migratetype, __entry->fallback_order < pageblock_order, __entry->change_ownership) ); /* * Required for uniquely and securely identifying mm in rss_stat tracepoint. */ #ifndef __PTR_TO_HASHVAL static unsigned int __maybe_unused mm_ptr_to_hash(const void *ptr) { int ret; unsigned long hashval; ret = ptr_to_hashval(ptr, &hashval); if (ret) return 0; /* The hashed value is only 32-bit */ return (unsigned int)hashval; } #define __PTR_TO_HASHVAL #endif TRACE_EVENT(rss_stat, TP_PROTO(struct mm_struct *mm, int member, long count), TP_ARGS(mm, member, count), TP_STRUCT__entry( __field(unsigned int, mm_id) __field(unsigned int, curr) __field(int, member) __field(long, size) ), TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); __entry->curr = !!(current->mm == mm); __entry->member = member; __entry->size = (count << PAGE_SHIFT); ), TP_printk("mm_id=%u curr=%d member=%d size=%ldB", __entry->mm_id, __entry->curr, __entry->member, __entry->size) ); #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MM_TYPES_H #define _LINUX_MM_TYPES_H #include <linux/mm_types_task.h> #include <linux/auxvec.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rbtree.h> #include <linux/rwsem.h> #include <linux/completion.h> #include <linux/cpumask.h> #include <linux/uprobes.h> #include <linux/page-flags-layout.h> #include <linux/workqueue.h> #include <linux/seqlock.h> #include <asm/mmu.h> #ifndef AT_VECTOR_SIZE_ARCH #define AT_VECTOR_SIZE_ARCH 0 #endif #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1)) #define INIT_PASID 0 struct address_space; struct mem_cgroup; /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the * moment. Note that we have no way to track which tasks are using * a page, though if it is a pagecache page, rmap structures can tell us * who is mapping it. * * If you allocate the page using alloc_pages(), you can use some of the * space in struct page for your own purposes. The five words in the main * union are available, except for bit 0 of the first word which must be * kept clear. Many users use this word to store a pointer to an object * which is guaranteed to be aligned. If you use the same storage as * page->mapping, you must restore it to NULL before freeing the page. * * If your page will not be mapped to userspace, you can also use the four * bytes in the mapcount union, but you must call page_mapcount_reset() * before freeing it. * * If you want to use the refcount field, it must be used in such a way * that other CPUs temporarily incrementing and then decrementing the * refcount does not cause problems. On receiving the page from * alloc_pages(), the refcount will be positive. * * If you allocate pages of order > 0, you can use some of the fields * in each subpage, but you may need to restore some of their values * afterwards. * * SLUB uses cmpxchg_double() to atomically update its freelist and * counters. That requires that freelist & counters be adjacent and * double-word aligned. We align all struct pages to double-word * boundaries, and ensure that 'freelist' is aligned within the * struct. */ #ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE #define _struct_page_alignment __aligned(2 * sizeof(unsigned long)) #else #define _struct_page_alignment #endif struct page { unsigned long flags; /* Atomic flags, some possibly * updated asynchronously */ /* * Five words (20/40 bytes) are available in this union. * WARNING: bit 0 of the first word is used for PageTail(). That * means the other users of this union MUST NOT use the bit to * avoid collision and false-positive PageTail(). */ union { struct { /* Page cache and anonymous pages */ /** * @lru: Pageout list, eg. active_list protected by * pgdat->lru_lock. Sometimes used as a generic list * by the page owner. */ struct list_head lru; /* See page-flags.h for PAGE_MAPPING_FLAGS */ struct address_space *mapping; pgoff_t index; /* Our offset within mapping. */ /** * @private: Mapping-private opaque data. * Usually used for buffer_heads if PagePrivate. * Used for swp_entry_t if PageSwapCache. * Indicates order in the buddy system if PageBuddy. */ unsigned long private; }; struct { /* page_pool used by netstack */ /** * @dma_addr: might require a 64-bit value on * 32-bit architectures. */ unsigned long dma_addr[2]; }; struct { /* slab, slob and slub */ union { struct list_head slab_list; struct { /* Partial pages */ struct page *next; #ifdef CONFIG_64BIT int pages; /* Nr of pages left */ int pobjects; /* Approximate count */ #else short int pages; short int pobjects; #endif }; }; struct kmem_cache *slab_cache; /* not slob */ /* Double-word boundary */ void *freelist; /* first free object */ union { void *s_mem; /* slab: first object */ unsigned long counters; /* SLUB */ struct { /* SLUB */ unsigned inuse:16; unsigned objects:15; unsigned frozen:1; }; }; }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ /* First tail page only */ unsigned char compound_dtor; unsigned char compound_order; atomic_t compound_mapcount; unsigned int compound_nr; /* 1 << compound_order */ }; struct { /* Second tail page of compound page */ unsigned long _compound_pad_1; /* compound_head */ atomic_t hpage_pinned_refcount; /* For both global and memcg */ struct list_head deferred_list; }; struct { /* Page table pages */ unsigned long _pt_pad_1; /* compound_head */ pgtable_t pmd_huge_pte; /* protected by page->ptl */ unsigned long _pt_pad_2; /* mapping */ union { struct mm_struct *pt_mm; /* x86 pgds only */ atomic_t pt_frag_refcount; /* powerpc */ #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE atomic_t pt_share_count; #endif }; #if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else spinlock_t ptl; #endif }; struct { /* ZONE_DEVICE pages */ /** @pgmap: Points to the hosting device page map. */ struct dev_pagemap *pgmap; void *zone_device_data; /* * ZONE_DEVICE private pages are counted as being * mapped so the next 3 words hold the mapping, index, * and private fields from the source anonymous or * page cache page while the page is migrated to device * private memory. * ZONE_DEVICE MEMORY_DEVICE_FS_DAX pages also * use the mapping, index, and private fields when * pmem backed DAX files are mapped. */ }; /** @rcu_head: You can use this to free a page by RCU. */ struct rcu_head rcu_head; }; union { /* This union is 4 bytes in size. */ /* * If the page can be mapped to userspace, encodes the number * of times this page is referenced by a page table. */ atomic_t _mapcount; /* * If the page is neither PageSlab nor mappable to userspace, * the value stored here may help determine what this page * is used for. See page-flags.h for a list of page types * which are currently stored here. */ unsigned int page_type; unsigned int active; /* SLAB */ int units; /* SLOB */ }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ atomic_t _refcount; #ifdef CONFIG_MEMCG union { struct mem_cgroup *mem_cgroup; struct obj_cgroup **obj_cgroups; }; #endif /* * On machines where all RAM is mapped into kernel address space, * we can simply calculate the virtual address. On machines with * highmem some memory is mapped into kernel virtual memory * dynamically, so we need a place to store that address. * Note that this field could be 16 bits on x86 ... ;) * * Architectures with slow multiplication can define * WANT_PAGE_VIRTUAL in asm/page.h */ #if defined(WANT_PAGE_VIRTUAL) void *virtual; /* Kernel virtual address (NULL if not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS int _last_cpupid; #endif } _struct_page_alignment; static inline atomic_t *compound_mapcount_ptr(struct page *page) { return &page[1].compound_mapcount; } static inline atomic_t *compound_pincount_ptr(struct page *page) { return &page[2].hpage_pinned_refcount; } /* * Used for sizing the vmemmap region on some architectures */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) #define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) #define page_private(page) ((page)->private) static inline void set_page_private(struct page *page, unsigned long private) { page->private = private; } struct page_frag_cache { void * va; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) __u16 offset; __u16 size; #else __u32 offset; #endif /* we maintain a pagecount bias, so that we dont dirty cache line * containing page->_refcount every time we allocate a fragment. */ unsigned int pagecnt_bias; bool pfmemalloc; }; typedef unsigned long vm_flags_t; /* * A region containing a mapping of a non-memory backed file under NOMMU * conditions. These are held in a global tree and are pinned by the VMAs that * map parts of them. */ struct vm_region { struct rb_node vm_rb; /* link in global region tree */ vm_flags_t vm_flags; /* VMA vm_flags */ unsigned long vm_start; /* start address of region */ unsigned long vm_end; /* region initialised to here */ unsigned long vm_top; /* region allocated to here */ unsigned long vm_pgoff; /* the offset in vm_file corresponding to vm_start */ struct file *vm_file; /* the backing file or NULL */ int vm_usage; /* region usage count (access under nommu_region_sem) */ bool vm_icache_flushed : 1; /* true if the icache has been flushed for * this region */ }; #ifdef CONFIG_USERFAULTFD #define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) { NULL, }) struct vm_userfaultfd_ctx { struct userfaultfd_ctx *ctx; }; #else /* CONFIG_USERFAULTFD */ #define NULL_VM_UFFD_CTX ((struct vm_userfaultfd_ctx) {}) struct vm_userfaultfd_ctx {}; #endif /* CONFIG_USERFAULTFD */ /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory * space that has a special rule for the page-fault handlers (ie a shared * library, the executable area etc). */ struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ unsigned long vm_start; /* Our start address within vm_mm. */ unsigned long vm_end; /* The first byte after our end address within vm_mm. */ /* linked list of VM areas per task, sorted by address */ struct vm_area_struct *vm_next, *vm_prev; struct rb_node vm_rb; /* * Largest free memory gap in bytes to the left of this VMA. * Either between this VMA and vma->vm_prev, or between one of the * VMAs below us in the VMA rbtree and its ->vm_prev. This helps * get_unmapped_area find a free area of the right size. */ unsigned long rb_subtree_gap; /* Second cache line starts here. */ struct mm_struct *vm_mm; /* The address space we belong to. */ /* * Access permissions of this VMA. * See vmf_insert_mixed_prot() for discussion. */ pgprot_t vm_page_prot; unsigned long vm_flags; /* Flags, see mm.h. */ /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. */ struct { struct rb_node rb; unsigned long rb_subtree_last; } shared; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma * list, after a COW of one of the file pages. A MAP_SHARED vma * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack * or brk vma (with NULL file) can only be in an anon_vma list. */ struct list_head anon_vma_chain; /* Serialized by mmap_lock & * page_table_lock */ struct anon_vma *anon_vma; /* Serialized by page_table_lock */ /* Function pointers to deal with this struct. */ const struct vm_operations_struct *vm_ops; /* Information about our backing store: */ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE units */ struct file * vm_file; /* File we map to (can be NULL). */ void * vm_private_data; /* was vm_pte (shared mem) */ #ifdef CONFIG_SWAP atomic_long_t swap_readahead_info; #endif #ifndef CONFIG_MMU struct vm_region *vm_region; /* NOMMU mapping region */ #endif #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; struct core_thread { struct task_struct *task; struct core_thread *next; }; struct core_state { atomic_t nr_threads; struct core_thread dumper; struct completion startup; }; struct kioctx_table; struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #endif unsigned long mmap_base; /* base of mmap area */ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES /* Base adresses for compatible mmap() */ unsigned long mmap_compat_base; unsigned long mmap_compat_legacy_base; #endif unsigned long task_size; /* size of task vm space */ unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; #ifdef CONFIG_MEMBARRIER /** * @membarrier_state: Flags controlling membarrier behavior. * * This field is close to @pgd to hopefully fit in the same * cache-line, which needs to be touched by switch_mm(). */ atomic_t membarrier_state; #endif /** * @mm_users: The number of users including userspace. * * Use mmget()/mmget_not_zero()/mmput() to modify. When this * drops to 0 (i.e. when the task exits and there are no other * temporary reference holders), we also release a reference on * @mm_count (which may then free the &struct mm_struct if * @mm_count also drops to 0). */ atomic_t mm_users; /** * @mm_count: The number of references to &struct mm_struct * (@mm_users count as 1). * * Use mmgrab()/mmdrop() to modify. When this drops to 0, the * &struct mm_struct is freed. */ atomic_t mm_count; /** * @has_pinned: Whether this mm has pinned any pages. This can * be either replaced in the future by @pinned_vm when it * becomes stable, or grow into a counter on its own. We're * aggresive on this bit now - even if the pinned pages were * unpinned later on, we'll still keep this bit set for the * lifecycle of this mm just for simplicity. */ atomic_t has_pinned; #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif int map_count; /* number of VMAs */ spinlock_t page_table_lock; /* Protects page tables and some * counters */ /* * With some kernel config, the current mmap_lock's offset * inside 'mm_struct' is at 0x120, which is very optimal, as * its two hot fields 'count' and 'owner' sit in 2 different * cachelines, and when mmap_lock is highly contended, both * of the 2 fields will be accessed frequently, current layout * will help to reduce cache bouncing. * * So please be careful with adding new fields before * mmap_lock, which can easily push the 2 fields into one * cacheline. */ struct rw_semaphore mmap_lock; struct list_head mmlist; /* List of maybe swapped mm's. These * are globally strung together off * init_mm.mmlist, and are protected * by mmlist_lock */ unsigned long hiwater_rss; /* High-watermark of RSS usage */ unsigned long hiwater_vm; /* High-water virtual memory usage */ unsigned long total_vm; /* Total pages mapped */ unsigned long locked_vm; /* Pages that have PG_mlocked set */ atomic64_t pinned_vm; /* Refcount permanently increased */ unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ unsigned long stack_vm; /* VM_STACK */ unsigned long def_flags; /** * @write_protect_seq: Locked when any thread is write * protecting pages mapped by this mm to enforce a later COW, * for instance during page table copying for fork(). */ seqcount_t write_protect_seq; spinlock_t arg_lock; /* protect the below fields */ unsigned long start_code, end_code, start_data, end_data; unsigned long start_brk, brk, start_stack; unsigned long arg_start, arg_end, env_start, env_end; unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ /* * Special counters, in some configurations protected by the * page_table_lock, in other configurations by being atomic. */ struct mm_rss_stat rss_stat; struct linux_binfmt *binfmt; /* Architecture-specific MM context */ mm_context_t context; unsigned long flags; /* Must use atomic bitops to access */ struct core_state *core_state; /* coredumping support */ #ifdef CONFIG_AIO spinlock_t ioctx_lock; struct kioctx_table __rcu *ioctx_table; #endif #ifdef CONFIG_MEMCG /* * "owner" points to a task that is regarded as the canonical * user/owner of this mm. All of the following must be true in * order for it to be changed: * * current == mm->owner * current->mm != mm * new_owner->mm == mm * new_owner->alloc_lock is held */ struct task_struct __rcu *owner; #endif struct user_namespace *user_ns; /* store ref to file /proc/<pid>/exe symlink points to */ struct file __rcu *exe_file; #ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_subscriptions *notifier_subscriptions; #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS pgtable_t pmd_huge_pte; /* protected by page_table_lock */ #endif #ifdef CONFIG_NUMA_BALANCING /* * numa_next_scan is the next time that the PTEs will be marked * pte_numa. NUMA hinting faults will gather statistics and * migrate pages to new nodes if necessary. */ unsigned long numa_next_scan; /* Restart point for scanning and setting pte_numa */ unsigned long numa_scan_offset; /* numa_scan_seq prevents two threads setting pte_numa */ int numa_scan_seq; #endif /* * An operation with batched TLB flushing is going on. Anything * that can move process memory needs to flush the TLB when * moving a PROT_NONE or PROT_NUMA mapped page. */ atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ bool tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; #ifdef CONFIG_IOMMU_SUPPORT u32 pasid; #endif } __randomize_layout; /* * The mm_cpumask needs to be at the end of mm_struct, because it * is dynamically sized based on nr_cpu_ids. */ unsigned long cpu_bitmap[]; }; extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ static inline void mm_init_cpumask(struct mm_struct *mm) { unsigned long cpu_bitmap = (unsigned long)mm; cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap); cpumask_clear((struct cpumask *)cpu_bitmap); } /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) { return (struct cpumask *)&mm->cpu_bitmap; } struct mmu_gather; extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end); extern void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end); static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); } static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which * requires the PTL. * * So the ordering here is: * * atomic_inc(&mm->tlb_flush_pending); * spin_lock(&ptl); * ... * set_pte_at(); * spin_unlock(&ptl); * * spin_lock(&ptl) * mm_tlb_flush_pending(); * .... * spin_unlock(&ptl); * * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * * Where the increment if constrained by the PTL unlock, it thus * ensures that the increment is visible if the PTE modification is * visible. After all, if there is no PTE modification, nobody cares * about TLB flushes either. * * This very much relies on users (mm_tlb_flush_pending() and * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc * locks (PPC) the unlock of one doesn't order against the lock of * another PTL. * * The decrement is ordered by the flush_tlb_range(), such that * mm_tlb_flush_pending() will not return false unless all flushes have * completed. */ } static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* * See inc_tlb_flush_pending(). * * This cannot be smp_mb__before_atomic() because smp_mb() simply does * not order against TLB invalidate completion, which is what we need. * * Therefore we must rely on tlb_flush_*() to guarantee order. */ atomic_dec(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { /* * Must be called after having acquired the PTL; orders against that * PTLs release and therefore ensures that if we observe the modified * PTE we must also observe the increment from inc_tlb_flush_pending(). * * That is, it only guarantees to return true if there is a flush * pending for _this_ PTL. */ return atomic_read(&mm->tlb_flush_pending); } static inline bool mm_tlb_flush_nested(struct mm_struct *mm) { /* * Similar to mm_tlb_flush_pending(), we must have acquired the PTL * for which there is a TLB flush pending in order to guarantee * we've seen both that PTE modification and the increment. * * (no requirement on actually still holding the PTL, that is irrelevant) */ return atomic_read(&mm->tlb_flush_pending) > 1; } struct vm_fault; /** * typedef vm_fault_t - Return type for page fault handlers. * * Page fault handlers return a bitmask of %VM_FAULT values. */ typedef __bitwise unsigned int vm_fault_t; /** * enum vm_fault_reason - Page fault handlers return a bitmask of * these values to tell the core VM what happened when handling the * fault. Used to decide whether a process gets delivered SIGBUS or * just gets major/minor fault counters bumped up. * * @VM_FAULT_OOM: Out Of Memory * @VM_FAULT_SIGBUS: Bad access * @VM_FAULT_MAJOR: Page read from storage * @VM_FAULT_WRITE: Special case for get_user_pages * @VM_FAULT_HWPOISON: Hit poisoned small page * @VM_FAULT_HWPOISON_LARGE: Hit poisoned large page. Index encoded * in upper bits * @VM_FAULT_SIGSEGV: segmentation fault * @VM_FAULT_NOPAGE: ->fault installed the pte, not return page * @VM_FAULT_LOCKED: ->fault locked the returned page * @VM_FAULT_RETRY: ->fault blocked, must retry * @VM_FAULT_FALLBACK: huge page fault failed, fall back to small * @VM_FAULT_DONE_COW: ->fault has fully handled COW * @VM_FAULT_NEEDDSYNC: ->fault did not modify page tables and needs * fsync() to complete (for synchronous page faults * in DAX) * @VM_FAULT_HINDEX_MASK: mask HINDEX value * */ enum vm_fault_reason { VM_FAULT_OOM = (__force vm_fault_t)0x000001, VM_FAULT_SIGBUS = (__force vm_fault_t)0x000002, VM_FAULT_MAJOR = (__force vm_fault_t)0x000004, VM_FAULT_WRITE = (__force vm_fault_t)0x000008, VM_FAULT_HWPOISON = (__force vm_fault_t)0x000010, VM_FAULT_HWPOISON_LARGE = (__force vm_fault_t)0x000020, VM_FAULT_SIGSEGV = (__force vm_fault_t)0x000040, VM_FAULT_NOPAGE = (__force vm_fault_t)0x000100, VM_FAULT_LOCKED = (__force vm_fault_t)0x000200, VM_FAULT_RETRY = (__force vm_fault_t)0x000400, VM_FAULT_FALLBACK = (__force vm_fault_t)0x000800, VM_FAULT_DONE_COW = (__force vm_fault_t)0x001000, VM_FAULT_NEEDDSYNC = (__force vm_fault_t)0x002000, VM_FAULT_HINDEX_MASK = (__force vm_fault_t)0x0f0000, }; /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((__force vm_fault_t)((x) << 16)) #define VM_FAULT_GET_HINDEX(x) (((__force unsigned int)(x) >> 16) & 0xf) #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | \ VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON | \ VM_FAULT_HWPOISON_LARGE | VM_FAULT_FALLBACK) #define VM_FAULT_RESULT_TRACE \ { VM_FAULT_OOM, "OOM" }, \ { VM_FAULT_SIGBUS, "SIGBUS" }, \ { VM_FAULT_MAJOR, "MAJOR" }, \ { VM_FAULT_WRITE, "WRITE" }, \ { VM_FAULT_HWPOISON, "HWPOISON" }, \ { VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \ { VM_FAULT_SIGSEGV, "SIGSEGV" }, \ { VM_FAULT_NOPAGE, "NOPAGE" }, \ { VM_FAULT_LOCKED, "LOCKED" }, \ { VM_FAULT_RETRY, "RETRY" }, \ { VM_FAULT_FALLBACK, "FALLBACK" }, \ { VM_FAULT_DONE_COW, "DONE_COW" }, \ { VM_FAULT_NEEDDSYNC, "NEEDDSYNC" } struct vm_special_mapping { const char *name; /* The name, e.g. "[vdso]". */ /* * If .fault is not provided, this points to a * NULL-terminated array of pages that back the special mapping. * * This must not be NULL unless .fault is provided. */ struct page **pages; /* * If non-NULL, then this is called to resolve page faults * on the special mapping. If used, .pages is not checked. */ vm_fault_t (*fault)(const struct vm_special_mapping *sm, struct vm_area_struct *vma, struct vm_fault *vmf); int (*mremap)(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma); }; enum tlb_flush_reason { TLB_FLUSH_ON_TASK_SWITCH, TLB_REMOTE_SHOOTDOWN, TLB_LOCAL_SHOOTDOWN, TLB_LOCAL_MM_SHOOTDOWN, TLB_REMOTE_SEND_IPI, NR_TLB_FLUSH_REASONS, }; /* * A swap entry has to fit into a "unsigned long", as the entry is hidden * in the "index" field of the swapper address space. */ typedef struct { unsigned long val; } swp_entry_t; #endif /* _LINUX_MM_TYPES_H */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 | // SPDX-License-Identifier: GPL-2.0 #include <linux/spinlock.h> #include <linux/task_work.h> #include <linux/tracehook.h> static struct callback_head work_exited; /* all we need is ->next == NULL */ /** * task_work_add - ask the @task to execute @work->func() * @task: the task which should run the callback * @work: the callback to run * @notify: how to notify the targeted task * * Queue @work for task_work_run() below and notify the @task if @notify * is @TWA_RESUME or @TWA_SIGNAL. @TWA_SIGNAL works like signals, in that the * it will interrupt the targeted task and run the task_work. @TWA_RESUME * work is run only when the task exits the kernel and returns to user mode, * or before entering guest mode. Fails if the @task is exiting/exited and thus * it can't process this @work. Otherwise @work->func() will be called when the * @task goes through one of the aforementioned transitions, or exits. * * If the targeted task is exiting, then an error is returned and the work item * is not queued. It's up to the caller to arrange for an alternative mechanism * in that case. * * Note: there is no ordering guarantee on works queued here. The task_work * list is LIFO. * * RETURNS: * 0 if succeeds or -ESRCH. */ int task_work_add(struct task_struct *task, struct callback_head *work, enum task_work_notify_mode notify) { struct callback_head *head; do { head = READ_ONCE(task->task_works); if (unlikely(head == &work_exited)) return -ESRCH; work->next = head; } while (cmpxchg(&task->task_works, head, work) != head); switch (notify) { case TWA_NONE: break; case TWA_RESUME: set_notify_resume(task); break; case TWA_SIGNAL: set_notify_signal(task); break; default: WARN_ON_ONCE(1); break; } return 0; } /** * task_work_cancel_match - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @match: match function to call * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data) { struct callback_head **pprev = &task->task_works; struct callback_head *work; unsigned long flags; if (likely(!task->task_works)) return NULL; /* * If cmpxchg() fails we continue without updating pprev. * Either we raced with task_work_add() which added the * new entry before this work, we will find it again. Or * we raced with task_work_run(), *pprev == NULL/exited. */ raw_spin_lock_irqsave(&task->pi_lock, flags); while ((work = READ_ONCE(*pprev))) { if (!match(work, data)) pprev = &work->next; else if (cmpxchg(pprev, work, work->next) == work) break; } raw_spin_unlock_irqrestore(&task->pi_lock, flags); return work; } static bool task_work_func_match(struct callback_head *cb, void *data) { return cb->func == data; } /** * task_work_cancel_func - cancel a pending work matching a function added by task_work_add() * @task: the task which should execute the func's work * @func: identifies the func to match with a work to remove * * Find the last queued pending work with ->func == @func and remove * it from queue. * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel_func(struct task_struct *task, task_work_func_t func) { return task_work_cancel_match(task, task_work_func_match, func); } static bool task_work_match(struct callback_head *cb, void *data) { return cb == data; } /** * task_work_cancel - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @cb: the callback to remove if queued * * Remove a callback from a task's queue if queued. * * RETURNS: * True if the callback was queued and got cancelled, false otherwise. */ bool task_work_cancel(struct task_struct *task, struct callback_head *cb) { struct callback_head *ret; ret = task_work_cancel_match(task, task_work_match, cb); return ret == cb; } /** * task_work_run - execute the works added by task_work_add() * * Flush the pending works. Should be used by the core kernel code. * Called before the task returns to the user-mode or stops, or when * it exits. In the latter case task_work_add() can no longer add the * new work after task_work_run() returns. */ void task_work_run(void) { struct task_struct *task = current; struct callback_head *work, *head, *next; for (;;) { /* * work->func() can do task_work_add(), do not set * work_exited unless the list is empty. */ do { head = NULL; work = READ_ONCE(task->task_works); if (!work) { if (task->flags & PF_EXITING) head = &work_exited; else break; } } while (cmpxchg(&task->task_works, work, head) != work); if (!work) break; /* * Synchronize with task_work_cancel_match(). It can not remove * the first entry == work, cmpxchg(task_works) must fail. * But it can remove another entry from the ->next list. */ raw_spin_lock_irq(&task->pi_lock); raw_spin_unlock_irq(&task->pi_lock); do { next = work->next; work->func(work); work = next; cond_resched(); } while (work); } } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 | // SPDX-License-Identifier: GPL-2.0 /* * preemptoff and irqoff tracepoints * * Copyright (C) Joel Fernandes (Google) <joel@joelfernandes.org> */ #include <linux/kallsyms.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/ftrace.h> #include <linux/kprobes.h> #include "trace.h" #define CREATE_TRACE_POINTS #include <trace/events/preemptirq.h> #ifdef CONFIG_TRACE_IRQFLAGS /* Per-cpu variable to prevent redundant calls when IRQs already off */ static DEFINE_PER_CPU(int, tracing_irq_cpu); /* * Like trace_hardirqs_on() but without the lockdep invocation. This is * used in the low level entry code where the ordering vs. RCU is important * and lockdep uses a staged approach which splits the lockdep hardirq * tracking into a RCU on and a RCU off section. */ void trace_hardirqs_on_prepare(void) { if (this_cpu_read(tracing_irq_cpu)) { if (!in_nmi()) trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1); tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1); this_cpu_write(tracing_irq_cpu, 0); } } EXPORT_SYMBOL(trace_hardirqs_on_prepare); NOKPROBE_SYMBOL(trace_hardirqs_on_prepare); void trace_hardirqs_on(void) { if (this_cpu_read(tracing_irq_cpu)) { if (!in_nmi()) trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1); this_cpu_write(tracing_irq_cpu, 0); } lockdep_hardirqs_on_prepare(CALLER_ADDR0); lockdep_hardirqs_on(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_on); NOKPROBE_SYMBOL(trace_hardirqs_on); /* * Like trace_hardirqs_off() but without the lockdep invocation. This is * used in the low level entry code where the ordering vs. RCU is important * and lockdep uses a staged approach which splits the lockdep hardirq * tracking into a RCU on and a RCU off section. */ void trace_hardirqs_off_finish(void) { if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1); if (!in_nmi()) trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1); } } EXPORT_SYMBOL(trace_hardirqs_off_finish); NOKPROBE_SYMBOL(trace_hardirqs_off_finish); void trace_hardirqs_off(void) { lockdep_hardirqs_off(CALLER_ADDR0); if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1); if (!in_nmi()) trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); } } EXPORT_SYMBOL(trace_hardirqs_off); NOKPROBE_SYMBOL(trace_hardirqs_off); __visible void trace_hardirqs_on_caller(unsigned long caller_addr) { if (this_cpu_read(tracing_irq_cpu)) { if (!in_nmi()) trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr); tracer_hardirqs_on(CALLER_ADDR0, caller_addr); this_cpu_write(tracing_irq_cpu, 0); } lockdep_hardirqs_on_prepare(caller_addr); lockdep_hardirqs_on(caller_addr); } EXPORT_SYMBOL(trace_hardirqs_on_caller); NOKPROBE_SYMBOL(trace_hardirqs_on_caller); __visible void trace_hardirqs_off_caller(unsigned long caller_addr) { lockdep_hardirqs_off(caller_addr); if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, caller_addr); if (!in_nmi()) trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); } } EXPORT_SYMBOL(trace_hardirqs_off_caller); NOKPROBE_SYMBOL(trace_hardirqs_off_caller); #endif /* CONFIG_TRACE_IRQFLAGS */ #ifdef CONFIG_TRACE_PREEMPT_TOGGLE void trace_preempt_on(unsigned long a0, unsigned long a1) { if (!in_nmi()) trace_preempt_enable_rcuidle(a0, a1); tracer_preempt_on(a0, a1); } void trace_preempt_off(unsigned long a0, unsigned long a1) { if (!in_nmi()) trace_preempt_disable_rcuidle(a0, a1); tracer_preempt_off(a0, a1); } #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/memory.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * demand-loading started 01.12.91 - seems it is high on the list of * things wanted, and it should be easy to implement. - Linus */ /* * Ok, demand-loading was easy, shared pages a little bit tricker. Shared * pages started 02.12.91, seems to work. - Linus. * * Tested sharing by executing about 30 /bin/sh: under the old kernel it * would have taken more than the 6M I have free, but it worked well as * far as I could see. * * Also corrected some "invalidate()"s - I wasn't doing enough of them. */ /* * Real VM (paging to/from disk) started 18.12.91. Much more work and * thought has to go into this. Oh, well.. * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why. * Found it. Everything seems to work now. * 20.12.91 - Ok, making the swap-device changeable like the root. */ /* * 05.04.94 - Multi-page memory management added for v1.1. * Idea by Alex Bligh (alex@cconcepts.co.uk) * * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG * (Gerhard.Wichert@pdb.siemens.de) * * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) */ #include <linux/kernel_stat.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/export.h> #include <linux/delayacct.h> #include <linux/init.h> #include <linux/pfn_t.h> #include <linux/writeback.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/swapops.h> #include <linux/elf.h> #include <linux/gfp.h> #include <linux/migrate.h> #include <linux/string.h> #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> #include <linux/dax.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/vmalloc.h> #include <trace/events/kmem.h> #include <asm/io.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include "pgalloc-track.h" #include "internal.h" #if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST) #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif #ifndef CONFIG_NEED_MULTIPLE_NODES /* use the per-pgdat data instead for discontigmem - mbligh */ unsigned long max_mapnr; EXPORT_SYMBOL(max_mapnr); struct page *mem_map; EXPORT_SYMBOL(mem_map); #endif /* * A number of key systems in x86 including ioremap() rely on the assumption * that high_memory defines the upper bound on direct map memory, then end * of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL * and ZONE_HIGHMEM. */ void *high_memory; EXPORT_SYMBOL(high_memory); /* * Randomize the address space (stacks, mmaps, brk, etc.). * * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization, * as ancient (libc5 based) binaries can segfault. ) */ int randomize_va_space __read_mostly = #ifdef CONFIG_COMPAT_BRK 1; #else 2; #endif #ifndef arch_faults_on_old_pte static inline bool arch_faults_on_old_pte(void) { /* * Those arches which don't have hw access flag feature need to * implement their own helper. By default, "true" means pagefault * will be hit on old pte. */ return true; } #endif static int __init disable_randmaps(char *s) { randomize_va_space = 0; return 1; } __setup("norandmaps", disable_randmaps); unsigned long zero_pfn __read_mostly; EXPORT_SYMBOL(zero_pfn); unsigned long highest_memmap_pfn __read_mostly; /* * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() */ static int __init init_zero_pfn(void) { zero_pfn = page_to_pfn(ZERO_PAGE(0)); return 0; } early_initcall(init_zero_pfn); void mm_trace_rss_stat(struct mm_struct *mm, int member, long count) { trace_rss_stat(mm, member, count); } #if defined(SPLIT_RSS_COUNTING) void sync_mm_rss(struct mm_struct *mm) { int i; for (i = 0; i < NR_MM_COUNTERS; i++) { if (current->rss_stat.count[i]) { add_mm_counter(mm, i, current->rss_stat.count[i]); current->rss_stat.count[i] = 0; } } current->rss_stat.events = 0; } static void add_mm_counter_fast(struct mm_struct *mm, int member, int val) { struct task_struct *task = current; if (likely(task->mm == mm)) task->rss_stat.count[member] += val; else add_mm_counter(mm, member, val); } #define inc_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, 1) #define dec_mm_counter_fast(mm, member) add_mm_counter_fast(mm, member, -1) /* sync counter once per 64 page faults */ #define TASK_RSS_EVENTS_THRESH (64) static void check_sync_rss_stat(struct task_struct *task) { if (unlikely(task != current)) return; if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH)) sync_mm_rss(task->mm); } #else /* SPLIT_RSS_COUNTING */ #define inc_mm_counter_fast(mm, member) inc_mm_counter(mm, member) #define dec_mm_counter_fast(mm, member) dec_mm_counter(mm, member) static void check_sync_rss_stat(struct task_struct *task) { } #endif /* SPLIT_RSS_COUNTING */ /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. */ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) { pgtable_t token = pmd_pgtable(*pmd); pmd_clear(pmd); pte_free_tlb(tlb, token, addr); mm_dec_nr_ptes(tlb->mm); } static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pmd_t *pmd; unsigned long next; unsigned long start; start = addr; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_none_or_clear_bad(pmd)) continue; free_pte_range(tlb, pmd, addr); } while (pmd++, addr = next, addr != end); start &= PUD_MASK; if (start < floor) return; if (ceiling) { ceiling &= PUD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pud_t *pud; unsigned long next; unsigned long start; start = addr; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; free_pmd_range(tlb, pud, addr, next, floor, ceiling); } while (pud++, addr = next, addr != end); start &= P4D_MASK; if (start < floor) return; if (ceiling) { ceiling &= P4D_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; pud = pud_offset(p4d, start); p4d_clear(p4d); pud_free_tlb(tlb, pud, start); mm_dec_nr_puds(tlb->mm); } static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { p4d_t *p4d; unsigned long next; unsigned long start; start = addr; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; free_pud_range(tlb, p4d, addr, next, floor, ceiling); } while (p4d++, addr = next, addr != end); start &= PGDIR_MASK; if (start < floor) return; if (ceiling) { ceiling &= PGDIR_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) return; p4d = p4d_offset(pgd, start); pgd_clear(pgd); p4d_free_tlb(tlb, p4d, start); } /* * This function frees user-level page tables of a process. */ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { pgd_t *pgd; unsigned long next; /* * The next few lines have given us lots of grief... * * Why are we testing PMD* at this top level? Because often * there will be no work to do at all, and we'd prefer not to * go all the way down to the bottom just to discover that. * * Why all these "- 1"s? Because 0 represents both the bottom * of the address space and the top of it (using -1 for the * top wouldn't help much: the masks would do the wrong thing). * The rule is that addr 0 and floor 0 refer to the bottom of * the address space, but end 0 and ceiling 0 refer to the top * Comparisons need to use "end - 1" and "ceiling - 1" (though * that end 0 case should be mythical). * * Wherever addr is brought up or ceiling brought down, we must * be careful to reject "the opposite 0" before it confuses the * subsequent tests. But what about where end is brought down * by PMD_SIZE below? no, end can't go down to 0 there. * * Whereas we round start (addr) and ceiling down, by different * masks at different levels, in order to test whether a table * now has no other vmas using it, so can be freed, we don't * bother to round floor or end up - the tests don't need that. */ addr &= PMD_MASK; if (addr < floor) { addr += PMD_SIZE; if (!addr) return; } if (ceiling) { ceiling &= PMD_MASK; if (!ceiling) return; } if (end - 1 > ceiling - 1) end -= PMD_SIZE; if (addr > end - 1) return; /* * We add page table cache pages with PAGE_SIZE, * (see pte_free_tlb()), flush the tlb if we need */ tlb_change_page_size(tlb, PAGE_SIZE); pgd = pgd_offset(tlb->mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; free_p4d_range(tlb, pgd, addr, next, floor, ceiling); } while (pgd++, addr = next, addr != end); } void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long floor, unsigned long ceiling) { while (vma) { struct vm_area_struct *next = vma->vm_next; unsigned long addr = vma->vm_start; /* * Hide vma from rmap and truncate_pagecache before freeing * pgtables */ unlink_anon_vmas(vma); unlink_file_vma(vma); if (is_vm_hugetlb_page(vma)) { hugetlb_free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } else { /* * Optimization: gather nearby vmas into one call down */ while (next && next->vm_start <= vma->vm_end + PMD_SIZE && !is_vm_hugetlb_page(next)) { vma = next; next = vma->vm_next; unlink_anon_vmas(vma); unlink_file_vma(vma); } free_pgd_range(tlb, addr, vma->vm_end, floor, next ? next->vm_start : ceiling); } vma = next; } } int __pte_alloc(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl; pgtable_t new = pte_alloc_one(mm); if (!new) return -ENOMEM; /* * Ensure all pte setup (eg. pte page lock and page clearing) are * visible before the pte is made visible to other CPUs by being * put into page tables. * * The other side of the story is the pointer chasing in the page * table walking code (when walking the page table without locking; * ie. most of the time). Fortunately, these data accesses consist * of a chain of data-dependent loads, meaning most CPUs (alpha * being the notable exception) will already guarantee loads are * seen in-order. See the alpha page table accessors for the * smp_rmb() barriers in page table walking code. */ smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ ptl = pmd_lock(mm, pmd); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ mm_inc_nr_ptes(mm); pmd_populate(mm, pmd, new); new = NULL; } spin_unlock(ptl); if (new) pte_free(mm, new); return 0; } int __pte_alloc_kernel(pmd_t *pmd) { pte_t *new = pte_alloc_one_kernel(&init_mm); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&init_mm.page_table_lock); if (likely(pmd_none(*pmd))) { /* Has another populated it ? */ pmd_populate_kernel(&init_mm, pmd, new); new = NULL; } spin_unlock(&init_mm.page_table_lock); if (new) pte_free_kernel(&init_mm, new); return 0; } static inline void init_rss_vec(int *rss) { memset(rss, 0, sizeof(int) * NR_MM_COUNTERS); } static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) { int i; if (current->mm == mm) sync_mm_rss(mm); for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); } /* * This function is called to print an error when a bad pte * is found. For example, we might have a PFN-mapped pte in * a region that doesn't allow it. * * The calling function must still handle the error. */ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr, pte_t pte, struct page *page) { pgd_t *pgd = pgd_offset(vma->vm_mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); pmd_t *pmd = pmd_offset(pud, addr); struct address_space *mapping; pgoff_t index; static unsigned long resume; static unsigned long nr_shown; static unsigned long nr_unshown; /* * Allow a burst of 60 reports, then keep quiet for that minute; * or allow a steady drip of one report per second. */ if (nr_shown == 60) { if (time_before(jiffies, resume)) { nr_unshown++; return; } if (nr_unshown) { pr_alert("BUG: Bad page map: %lu messages suppressed\n", nr_unshown); nr_unshown = 0; } nr_shown = 0; } if (nr_shown++ == 0) resume = jiffies + 60 * HZ; mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL; index = linear_page_index(vma, addr); pr_alert("BUG: Bad page map in process %s pte:%08llx pmd:%08llx\n", current->comm, (long long)pte_val(pte), (long long)pmd_val(*pmd)); if (page) dump_page(page, "bad pte"); pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n", (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index); pr_alert("file:%pD fault:%ps mmap:%ps readpage:%ps\n", vma->vm_file, vma->vm_ops ? vma->vm_ops->fault : NULL, vma->vm_file ? vma->vm_file->f_op->mmap : NULL, mapping ? mapping->a_ops->readpage : NULL); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } /* * vm_normal_page -- This function gets the "struct page" associated with a pte. * * "Special" mappings do not wish to be associated with a "struct page" (either * it doesn't exist, or it exists but they don't want to touch it). In this * case, NULL is returned here. "Normal" mappings do have a struct page. * * There are 2 broad cases. Firstly, an architecture may define a pte_special() * pte bit, in which case this function is trivial. Secondly, an architecture * may not have a spare pte bit, which requires a more complicated scheme, * described below. * * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a * special mapping (even if there are underlying and valid "struct pages"). * COWed pages of a VM_PFNMAP are always normal. * * The way we recognize COWed pages within VM_PFNMAP mappings is through the * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit * set, and the vm_pgoff will point to the first PFN mapped: thus every special * mapping will always honor the rule * * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) * * And for normal mappings this is false. * * This restricts such mappings to be a linear translation from virtual address * to pfn. To get around this restriction, we allow arbitrary mappings so long * as the vma is not a COW mapping; in that case, we know that all ptes are * special (because none can have been COWed). * * * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. * * VM_MIXEDMAP mappings can likewise contain memory with or without "struct * page" backing, however the difference is that _all_ pages with a struct * page (that is, those where pfn_valid is true) are refcounted and considered * normal pages by the VM. The disadvantage is that pages are refcounted * (which can be slower and simply not an option for some PFNMAP users). The * advantage is that we don't have to follow the strict linearity rule of * PFNMAP mappings in order to support COWable mappings. * */ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { unsigned long pfn = pte_pfn(pte); if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { if (likely(!pte_special(pte))) goto check_pfn; if (vma->vm_ops && vma->vm_ops->find_special_page) return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (is_zero_pfn(pfn)) return NULL; if (pte_devmap(pte)) return NULL; print_bad_pte(vma, addr, pte, NULL); return NULL; } /* !CONFIG_ARCH_HAS_PTE_SPECIAL case follows: */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (is_zero_pfn(pfn)) return NULL; check_pfn: if (unlikely(pfn > highest_memmap_pfn)) { print_bad_pte(vma, addr, pte, NULL); return NULL; } /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { unsigned long pfn = pmd_pfn(pmd); /* * There is no pmd_special() but there may be special pmds, e.g. * in a direct-access (dax) mapping, so let's just replicate the * !CONFIG_ARCH_HAS_PTE_SPECIAL case from vm_normal_page() here. */ if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { if (!pfn_valid(pfn)) return NULL; goto out; } else { unsigned long off; off = (addr - vma->vm_start) >> PAGE_SHIFT; if (pfn == vma->vm_pgoff + off) return NULL; if (!is_cow_mapping(vma->vm_flags)) return NULL; } } if (pmd_devmap(pmd)) return NULL; if (is_huge_zero_pmd(pmd)) return NULL; if (unlikely(pfn > highest_memmap_pfn)) return NULL; /* * NOTE! We still have PageReserved() pages in the page tables. * eg. VDSO mappings can cause them to exist. */ out: return pfn_to_page(pfn); } #endif /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range * covered by this vma. */ static unsigned long copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long addr, int *rss) { unsigned long vm_flags = dst_vma->vm_flags; pte_t pte = *src_pte; struct page *page; swp_entry_t entry = pte_to_swp_entry(pte); if (likely(!non_swap_entry(entry))) { if (swap_duplicate(entry) < 0) return entry.val; /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); if (list_empty(&dst_mm->mmlist)) list_add(&dst_mm->mmlist, &src_mm->mmlist); spin_unlock(&mmlist_lock); } rss[MM_SWAPENTS]++; } else if (is_migration_entry(entry)) { page = migration_entry_to_page(entry); rss[mm_counter(page)]++; if (is_write_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* * COW mappings require pages in both * parent and child to be set to read. */ make_migration_entry_read(&entry); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(*src_pte)) pte = pte_swp_mksoft_dirty(pte); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_private_entry(entry)) { page = device_private_entry_to_page(entry); /* * Update rss count even for unaddressable pages, as * they should treated just like normal pages in this * respect. * * We will likely want to have some new rss counters * for unaddressable pages, at some point. But for now * keep things as they are. */ get_page(page); rss[mm_counter(page)]++; page_dup_rmap(page, false); /* * We do not preserve soft-dirty information, because so * far, checkpoint/restore is the only feature that * requires that. And checkpoint/restore does not work * when a device driver is involved (you cannot easily * save and restore device driver state). */ if (is_write_device_private_entry(entry) && is_cow_mapping(vm_flags)) { make_device_private_entry_read(&entry); pte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } } if (!userfaultfd_wp(dst_vma)) pte = pte_swp_clear_uffd_wp(pte); set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } /* * Copy a present and normal page if necessary. * * NOTE! The usual case is that this doesn't need to do * anything, and can just return a positive value. That * will let the caller know that it can just increase * the page refcount and re-use the pte the traditional * way. * * But _if_ we need to copy it because it needs to be * pinned in the parent (and the child should get its own * copy rather than just a reference to the same page), * we'll do that here and return zero to let the caller * know we're done. * * And if we need a pre-allocated page but don't yet have * one, return a negative error to let the preallocation * code know so that it can do so outside the page table * lock. */ static inline int copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc, pte_t pte, struct page *page) { struct mm_struct *src_mm = src_vma->vm_mm; struct page *new_page; if (!is_cow_mapping(src_vma->vm_flags)) return 1; /* * What we want to do is to check whether this page may * have been pinned by the parent process. If so, * instead of wrprotect the pte on both sides, we copy * the page immediately so that we'll always guarantee * the pinned page won't be randomly replaced in the * future. * * The page pinning checks are just "has this mm ever * seen pinning", along with the (inexact) check of * the page count. That might give false positives for * for pinning, but it will work correctly. */ if (likely(!atomic_read(&src_mm->has_pinned))) return 1; if (likely(!page_maybe_dma_pinned(page))) return 1; /* * The vma->anon_vma of the child process may be NULL * because the entire vma does not contain anonymous pages. * A BUG will occur when the copy_present_page() passes * a copy of a non-anonymous page of that vma to the * page_add_new_anon_rmap() to set up new anonymous rmap. * Return 1 if the page is not an anonymous page. */ if (!PageAnon(page)) return 1; new_page = *prealloc; if (!new_page) return -EAGAIN; /* * We have a prealloc page, all good! Take it * over and copy the page & arm it. */ *prealloc = NULL; copy_user_highpage(new_page, page, addr, src_vma); __SetPageUptodate(new_page); page_add_new_anon_rmap(new_page, dst_vma, addr, false); lru_cache_add_inactive_or_unevictable(new_page, dst_vma); rss[mm_counter(new_page)]++; /* All done, just insert the new page copy in the child */ pte = mk_pte(new_page, dst_vma->vm_page_prot); pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); if (userfaultfd_pte_wp(dst_vma, *src_pte)) /* Uffd-wp needs to be delivered to dest pte as well */ pte = pte_wrprotect(pte_mkuffd_wp(pte)); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } /* * Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page * is required to copy this pte. */ static inline int copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss, struct page **prealloc) { struct mm_struct *src_mm = src_vma->vm_mm; unsigned long vm_flags = src_vma->vm_flags; pte_t pte = *src_pte; struct page *page; page = vm_normal_page(src_vma, addr, pte); if (page) { int retval; retval = copy_present_page(dst_vma, src_vma, dst_pte, src_pte, addr, rss, prealloc, pte, page); if (retval <= 0) return retval; get_page(page); page_dup_rmap(page, false); rss[mm_counter(page)]++; } /* * If it's a COW mapping, write protect it both * in the parent and the child */ if (is_cow_mapping(vm_flags) && pte_write(pte)) { ptep_set_wrprotect(src_mm, addr, src_pte); pte = pte_wrprotect(pte); } /* * If it's a shared mapping, mark it clean in * the child */ if (vm_flags & VM_SHARED) pte = pte_mkclean(pte); pte = pte_mkold(pte); if (!userfaultfd_wp(dst_vma)) pte = pte_clear_uffd_wp(pte); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } static inline struct page * page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, unsigned long addr) { struct page *new_page; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr); if (!new_page) return NULL; if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { put_page(new_page); return NULL; } cgroup_throttle_swaprate(new_page, GFP_KERNEL); return new_page; } static int copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; int progress, ret = 0; int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; struct page *prealloc = NULL; again: progress = 0; init_rss_vec(rss); dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); if (!dst_pte) { ret = -ENOMEM; goto out; } src_pte = pte_offset_map(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); orig_src_pte = src_pte; orig_dst_pte = dst_pte; arch_enter_lazy_mmu_mode(); do { /* * We are holding two locks at this point - either of them * could generate latencies in another task on another CPU. */ if (progress >= 32) { progress = 0; if (need_resched() || spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) break; } if (pte_none(*src_pte)) { progress++; continue; } if (unlikely(!pte_present(*src_pte))) { entry.val = copy_nonpresent_pte(dst_mm, src_mm, dst_pte, src_pte, dst_vma, src_vma, addr, rss); if (entry.val) break; progress += 8; continue; } /* copy_present_pte() will clear `*prealloc' if consumed */ ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, addr, rss, &prealloc); /* * If we need a pre-allocated page for this pte, drop the * locks, allocate, and try again. */ if (unlikely(ret == -EAGAIN)) break; if (unlikely(prealloc)) { /* * pre-alloc page cannot be reused by next time so as * to strictly follow mempolicy (e.g., alloc_page_vma() * will allocate page according to address). This * could only happen if one pinned pte changed. */ put_page(prealloc); prealloc = NULL; } progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); pte_unmap(orig_src_pte); add_mm_rss_vec(dst_mm, rss); pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); if (entry.val) { if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { ret = -ENOMEM; goto out; } entry.val = 0; } else if (ret) { WARN_ON_ONCE(ret != -EAGAIN); prealloc = page_copy_prealloc(src_mm, src_vma, addr); if (!prealloc) return -ENOMEM; /* We've captured and resolved the error. Reset, try again. */ ret = 0; } if (addr != end) goto again; out: if (unlikely(prealloc)) put_page(prealloc); return ret; } static inline int copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pmd_t *src_pmd, *dst_pmd; unsigned long next; dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); if (!dst_pmd) return -ENOMEM; src_pmd = pmd_offset(src_pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, addr, dst_vma, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_vma, src_vma, dst_pmd, src_pmd, addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; } static inline int copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, p4d_t *dst_p4d, p4d_t *src_p4d, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; pud_t *src_pud, *dst_pud; unsigned long next; dst_pud = pud_alloc(dst_mm, dst_p4d, addr); if (!dst_pud) return -ENOMEM; src_pud = pud_offset(src_p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma); err = copy_huge_pud(dst_mm, src_mm, dst_pud, src_pud, addr, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) continue; /* fall through */ } if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_vma, src_vma, dst_pud, src_pud, addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; } static inline int copy_p4d_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pgd_t *dst_pgd, pgd_t *src_pgd, unsigned long addr, unsigned long end) { struct mm_struct *dst_mm = dst_vma->vm_mm; p4d_t *src_p4d, *dst_p4d; unsigned long next; dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr); if (!dst_p4d) return -ENOMEM; src_p4d = p4d_offset(src_pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(src_p4d)) continue; if (copy_pud_range(dst_vma, src_vma, dst_p4d, src_p4d, addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pgd_t *src_pgd, *dst_pgd; unsigned long next; unsigned long addr = src_vma->vm_start; unsigned long end = src_vma->vm_end; struct mm_struct *dst_mm = dst_vma->vm_mm; struct mm_struct *src_mm = src_vma->vm_mm; struct mmu_notifier_range range; bool is_cow; int ret; /* * Don't copy ptes where a page fault will fill them correctly. * Fork becomes much lighter when there are big shared or private * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ if (!(src_vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && !src_vma->anon_vma) return 0; if (is_vm_hugetlb_page(src_vma)) return copy_hugetlb_page_range(dst_mm, src_mm, src_vma); if (unlikely(src_vma->vm_flags & VM_PFNMAP)) { /* * We do not free on error cases below as remove_vma * gets called on error from higher level routine */ ret = track_pfn_copy(src_vma); if (ret) return ret; } /* * We need to invalidate the secondary MMU mappings only when * there could be a permission downgrade on the ptes of the * parent mm. And a permission downgrade will only happen if * is_cow_mapping() returns true. */ is_cow = is_cow_mapping(src_vma->vm_flags); if (is_cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, src_vma, src_mm, addr, end); mmu_notifier_invalidate_range_start(&range); /* * Disabling preemption is not needed for the write side, as * the read side doesn't spin, but goes to the mmap_lock. * * Use the raw variant of the seqcount_t write API to avoid * lockdep complaining about preemptibility. */ mmap_assert_write_locked(src_mm); raw_write_seqcount_begin(&src_mm->write_protect_seq); } ret = 0; dst_pgd = pgd_offset(dst_mm, addr); src_pgd = pgd_offset(src_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(src_pgd)) continue; if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd, addr, next))) { ret = -ENOMEM; break; } } while (dst_pgd++, src_pgd++, addr = next, addr != end); if (is_cow) { raw_write_seqcount_end(&src_mm->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } return ret; } /* Whether we should zap all COWed (private) pages too */ static inline bool should_zap_cows(struct zap_details *details) { /* By default, zap all pages */ if (!details) return true; /* Or, we zap COWed pages only if the caller wants to */ return !details->check_mapping; } static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, struct zap_details *details) { struct mm_struct *mm = tlb->mm; int force_flush = 0; int rss[NR_MM_COUNTERS]; spinlock_t *ptl; pte_t *start_pte; pte_t *pte; swp_entry_t entry; tlb_change_page_size(tlb, PAGE_SIZE); again: init_rss_vec(rss); start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl); pte = start_pte; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; if (pte_none(ptent)) continue; if (need_resched()) break; if (pte_present(ptent)) { struct page *page; page = vm_normal_page(vma, addr, ptent); if (unlikely(details) && page) { /* * unmap_shared_mapping_pages() wants to * invalidate cache without truncating: * unmap shared but keep private pages. */ if (details->check_mapping && details->check_mapping != page_rmapping(page)) continue; } ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; if (!PageAnon(page)) { if (pte_dirty(ptent)) { force_flush = 1; set_page_dirty(page); } if (pte_young(ptent) && likely(!(vma->vm_flags & VM_SEQ_READ))) mark_page_accessed(page); } rss[mm_counter(page)]--; page_remove_rmap(page, false); if (unlikely(page_mapcount(page) < 0)) print_bad_pte(vma, addr, ptent, page); if (unlikely(__tlb_remove_page(tlb, page))) { force_flush = 1; addr += PAGE_SIZE; break; } continue; } entry = pte_to_swp_entry(ptent); if (is_device_private_entry(entry)) { struct page *page = device_private_entry_to_page(entry); if (unlikely(details && details->check_mapping)) { /* * unmap_shared_mapping_pages() wants to * invalidate cache without truncating: * unmap shared but keep private pages. */ if (details->check_mapping != page_rmapping(page)) continue; } pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); rss[mm_counter(page)]--; page_remove_rmap(page, false); put_page(page); continue; } if (!non_swap_entry(entry)) { /* Genuine swap entry, hence a private anon page */ if (!should_zap_cows(details)) continue; rss[MM_SWAPENTS]--; } else if (is_migration_entry(entry)) { struct page *page; page = migration_entry_to_page(entry); if (details && details->check_mapping && details->check_mapping != page_rmapping(page)) continue; rss[mm_counter(page)]--; } if (unlikely(!free_swap_and_cache(entry))) print_bad_pte(vma, addr, ptent, NULL); pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, addr != end); add_mm_rss_vec(mm, rss); arch_leave_lazy_mmu_mode(); /* Do the actual TLB flush before dropping ptl */ if (force_flush) tlb_flush_mmu_tlbonly(tlb); pte_unmap_unlock(start_pte, ptl); /* * If we forced a TLB flush (either due to running out of * batch buffers or because we needed to flush dirty TLB * entries before releasing the ptl), free the batched * memory too. Restart if we didn't do everything. */ if (force_flush) { force_flush = 0; tlb_flush_mmu(tlb); } if (addr != end) { cond_resched(); goto again; } return addr; } static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, struct zap_details *details) { pmd_t *pmd; unsigned long next; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) __split_huge_pmd(vma, pmd, addr, false, NULL); else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ } else if (details && details->single_page && PageTransCompound(details->single_page) && next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { spinlock_t *ptl = pmd_lock(tlb->mm, pmd); /* * Take and drop THP pmd lock so that we cannot return * prematurely, while zap_huge_pmd() has cleared *pmd, * but not yet decremented compound_mapcount(). */ spin_unlock(ptl); } /* * Here there can be other concurrent MADV_DONTNEED or * trans huge page faults running, and if the pmd is * none or trans huge it can change under us. This is * because MADV_DONTNEED holds the mmap_lock in read * mode. */ if (pmd_none_or_trans_huge_or_clear_bad(pmd)) goto next; next = zap_pte_range(tlb, vma, pmd, addr, next, details); next: cond_resched(); } while (pmd++, addr = next, addr != end); return addr; } static inline unsigned long zap_pud_range(struct mmu_gather *tlb, struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, struct zap_details *details) { pud_t *pud; unsigned long next; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_trans_huge(*pud) || pud_devmap(*pud)) { if (next - addr != HPAGE_PUD_SIZE) { mmap_assert_locked(tlb->mm); split_huge_pud(vma, pud, addr); } else if (zap_huge_pud(tlb, vma, pud, addr)) goto next; /* fall through */ } if (pud_none_or_clear_bad(pud)) continue; next = zap_pmd_range(tlb, vma, pud, addr, next, details); next: cond_resched(); } while (pud++, addr = next, addr != end); return addr; } static inline unsigned long zap_p4d_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, struct zap_details *details) { p4d_t *p4d; unsigned long next; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; next = zap_pud_range(tlb, vma, p4d, addr, next, details); } while (p4d++, addr = next, addr != end); return addr; } void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details) { pgd_t *pgd; unsigned long next; BUG_ON(addr >= end); tlb_start_vma(tlb, vma); pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; next = zap_p4d_range(tlb, vma, pgd, addr, next, details); } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); } static void unmap_single_vma(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { unsigned long start = max(vma->vm_start, start_addr); unsigned long end; if (start >= vma->vm_end) return; end = min(vma->vm_end, end_addr); if (end <= vma->vm_start) return; if (vma->vm_file) uprobe_munmap(vma, start, end); if (unlikely(vma->vm_flags & VM_PFNMAP)) untrack_pfn(vma, 0, 0); if (start != end) { if (unlikely(is_vm_hugetlb_page(vma))) { /* * It is undesirable to test vma->vm_file as it * should be non-null for valid hugetlb area. * However, vm_file will be NULL in the error * cleanup path of mmap_region. When * hugetlbfs ->mmap method fails, * mmap_region() nullifies vma->vm_file * before calling this function to clean up. * Since no pte has actually been setup, it is * safe to do nothing in this case. */ if (vma->vm_file) { i_mmap_lock_write(vma->vm_file->f_mapping); __unmap_hugepage_range_final(tlb, vma, start, end, NULL); i_mmap_unlock_write(vma->vm_file->f_mapping); } } else unmap_page_range(tlb, vma, start, end, details); } } /** * unmap_vmas - unmap a range of memory covered by a list of vma's * @tlb: address of the caller's struct mmu_gather * @vma: the starting vma * @start_addr: virtual address at which to start unmapping * @end_addr: virtual address at which to end unmapping * * Unmap all pages in the vma list. * * Only addresses between `start' and `end' will be unmapped. * * The VMA list must be sorted in ascending virtual address order. * * unmap_vmas() assumes that the caller will flush the whole unmapped address * range after unmap_vmas() returns. So the only responsibility here is to * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr) { struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) unmap_single_vma(tlb, vma, start_addr, end_addr, NULL); mmu_notifier_invalidate_range_end(&range); } /** * zap_page_range - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @start: starting address of pages to zap * @size: number of bytes to zap * * Caller must protect the VMA list */ void zap_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long size) { struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, start, start + size); tlb_gather_mmu(&tlb, vma->vm_mm, start, range.end); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); for ( ; vma && vma->vm_start < range.end; vma = vma->vm_next) unmap_single_vma(&tlb, vma, start, range.end, NULL); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, start, range.end); } /** * zap_page_range_single - remove user pages in a given range * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap * @details: details of shared cache invalidation * * The range must fit into one VMA. */ static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { struct mmu_notifier_range range; struct mmu_gather tlb; lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, address + size); tlb_gather_mmu(&tlb, vma->vm_mm, address, range.end); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); unmap_single_vma(&tlb, vma, address, range.end, details); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, address, range.end); } /** * zap_vma_ptes - remove ptes mapping the vma * @vma: vm_area_struct holding ptes to be zapped * @address: starting address of pages to zap * @size: number of bytes to zap * * This function only unmaps ptes assigned to VM_PFNMAP vmas. * * The entire address range must be fully contained within the vma. * */ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size) { if (address < vma->vm_start || address + size > vma->vm_end || !(vma->vm_flags & VM_PFNMAP)) return; zap_page_range_single(vma, address, size, NULL); } EXPORT_SYMBOL_GPL(zap_vma_ptes); static pmd_t *walk_to_pmd(struct mm_struct *mm, unsigned long addr) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (!pud) return NULL; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return NULL; VM_BUG_ON(pmd_trans_huge(*pmd)); return pmd; } pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl) { pmd_t *pmd = walk_to_pmd(mm, addr); if (!pmd) return NULL; return pte_alloc_map_lock(mm, pmd, addr, ptl); } static int validate_page_before_insert(struct page *page) { if (PageAnon(page) || PageSlab(page) || page_has_type(page)) return -EINVAL; flush_dcache_page(page); return 0; } static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { if (!pte_none(*pte)) return -EBUSY; /* Ok, finally just insert the thing.. */ get_page(page); inc_mm_counter_fast(mm, mm_counter_file(page)); page_add_file_rmap(page, false); set_pte_at(mm, addr, pte, mk_pte(page, prot)); return 0; } /* * This is the old fallback for page remapping. * * For historical reasons, it only allows reserved pages. Only * old drivers should use this, and they needed to mark their * pages reserved for the old functions anyway. */ static int insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot) { struct mm_struct *mm = vma->vm_mm; int retval; pte_t *pte; spinlock_t *ptl; retval = validate_page_before_insert(page); if (retval) goto out; retval = -ENOMEM; pte = get_locked_pte(mm, addr, &ptl); if (!pte) goto out; retval = insert_page_into_pte_locked(mm, pte, addr, page, prot); pte_unmap_unlock(pte, ptl); out: return retval; } #ifdef pte_index static int insert_page_in_batch_locked(struct mm_struct *mm, pte_t *pte, unsigned long addr, struct page *page, pgprot_t prot) { int err; if (!page_count(page)) return -EINVAL; err = validate_page_before_insert(page); if (err) return err; return insert_page_into_pte_locked(mm, pte, addr, page, prot); } /* insert_pages() amortizes the cost of spinlock operations * when inserting pages in a loop. Arch *must* define pte_index. */ static int insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num, pgprot_t prot) { pmd_t *pmd = NULL; pte_t *start_pte, *pte; spinlock_t *pte_lock; struct mm_struct *const mm = vma->vm_mm; unsigned long curr_page_idx = 0; unsigned long remaining_pages_total = *num; unsigned long pages_to_write_in_pmd; int ret; more: ret = -EFAULT; pmd = walk_to_pmd(mm, addr); if (!pmd) goto out; pages_to_write_in_pmd = min_t(unsigned long, remaining_pages_total, PTRS_PER_PTE - pte_index(addr)); /* Allocate the PTE if necessary; takes PMD lock once only. */ ret = -ENOMEM; if (pte_alloc(mm, pmd)) goto out; while (pages_to_write_in_pmd) { int pte_idx = 0; const int batch_size = min_t(int, pages_to_write_in_pmd, 8); start_pte = pte_offset_map_lock(mm, pmd, addr, &pte_lock); for (pte = start_pte; pte_idx < batch_size; ++pte, ++pte_idx) { int err = insert_page_in_batch_locked(mm, pte, addr, pages[curr_page_idx], prot); if (unlikely(err)) { pte_unmap_unlock(start_pte, pte_lock); ret = err; remaining_pages_total -= pte_idx; goto out; } addr += PAGE_SIZE; ++curr_page_idx; } pte_unmap_unlock(start_pte, pte_lock); pages_to_write_in_pmd -= batch_size; remaining_pages_total -= batch_size; } if (remaining_pages_total) goto more; ret = 0; out: *num = remaining_pages_total; return ret; } #endif /* ifdef pte_index */ /** * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock. * @vma: user vma to map to * @addr: target start user address of these pages * @pages: source kernel pages * @num: in: number of pages to map. out: number of pages that were *not* * mapped. (0 means all pages were successfully mapped). * * Preferred over vm_insert_page() when inserting multiple pages. * * In case of error, we may have mapped a subset of the provided * pages. It is the caller's responsibility to account for this case. * * The same restrictions apply as in vm_insert_page(). */ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr, struct page **pages, unsigned long *num) { #ifdef pte_index const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1; if (addr < vma->vm_start || end_addr >= vma->vm_end) return -EFAULT; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vma->vm_flags |= VM_MIXEDMAP; } /* Defer page refcount checking till we're about to map that page. */ return insert_pages(vma, addr, pages, num, vma->vm_page_prot); #else unsigned long idx = 0, pgcount = *num; int err = -EINVAL; for (; idx < pgcount; ++idx) { err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]); if (err) break; } *num = pgcount - idx; return err; #endif /* ifdef pte_index */ } EXPORT_SYMBOL(vm_insert_pages); /** * vm_insert_page - insert single page into user vma * @vma: user vma to map to * @addr: target user address of this page * @page: source kernel page * * This allows drivers to insert individual pages they've allocated * into a user vma. * * The page has to be a nice clean _individual_ kernel allocation. * If you allocate a compound page, you need to have marked it as * such (__GFP_COMP), or manually just split the page up yourself * (see split_page()). * * NOTE! Traditionally this was done with "remap_pfn_range()" which * took an arbitrary page protection parameter. This doesn't allow * that. Your vma protection will have to be set up correctly, which * means that if you want a shared writable mapping, you'd better * ask for a shared writable mapping! * * The page does not need to be reserved. * * Usually this function is called from f_op->mmap() handler * under mm->mmap_lock write-lock, so it can change vma->vm_flags. * Caller must set VM_MIXEDMAP on vma if it wants to call this * function from other places, for example from page-fault handler. * * Return: %0 on success, negative error code otherwise. */ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { if (addr < vma->vm_start || addr >= vma->vm_end) return -EFAULT; if (!page_count(page)) return -EINVAL; if (!(vma->vm_flags & VM_MIXEDMAP)) { BUG_ON(mmap_read_trylock(vma->vm_mm)); BUG_ON(vma->vm_flags & VM_PFNMAP); vma->vm_flags |= VM_MIXEDMAP; } return insert_page(vma, addr, page, vma->vm_page_prot); } EXPORT_SYMBOL(vm_insert_page); /* * __vm_map_pages - maps range of kernel pages into user vma * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * @offset: user's requested vm_pgoff * * This allows drivers to map range of kernel pages into a user vma. * * Return: 0 on success and error code otherwise. */ static int __vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num, unsigned long offset) { unsigned long count = vma_pages(vma); unsigned long uaddr = vma->vm_start; int ret, i; /* Fail if the user requested offset is beyond the end of the object */ if (offset >= num) return -ENXIO; /* Fail if the user requested size exceeds available object size */ if (count > num - offset) return -ENXIO; for (i = 0; i < count; i++) { ret = vm_insert_page(vma, uaddr, pages[offset + i]); if (ret < 0) return ret; uaddr += PAGE_SIZE; } return 0; } /** * vm_map_pages - maps range of kernel pages starts with non zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Maps an object consisting of @num pages, catering for the user's * requested vm_pgoff * * If we fail to insert any page into the vma, the function will return * immediately leaving any previously inserted pages present. Callers * from the mmap handler may immediately return the error as their caller * will destroy the vma, removing any successfully inserted pages. Other * callers should make their own arrangements for calling unmap_region(). * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, vma->vm_pgoff); } EXPORT_SYMBOL(vm_map_pages); /** * vm_map_pages_zero - map range of kernel pages starts with zero offset * @vma: user vma to map to * @pages: pointer to array of source kernel pages * @num: number of pages in page array * * Similar to vm_map_pages(), except that it explicitly sets the offset * to 0. This function is intended for the drivers that did not consider * vm_pgoff. * * Context: Process context. Called by mmap handlers. * Return: 0 on success and error code otherwise. */ int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, unsigned long num) { return __vm_map_pages(vma, pages, num, 0); } EXPORT_SYMBOL(vm_map_pages_zero); static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t prot, bool mkwrite) { struct mm_struct *mm = vma->vm_mm; pte_t *pte, entry; spinlock_t *ptl; pte = get_locked_pte(mm, addr, &ptl); if (!pte) return VM_FAULT_OOM; if (!pte_none(*pte)) { if (mkwrite) { /* * For read faults on private mappings the PFN passed * in may not match the PFN we have mapped if the * mapped PFN is a writeable COW page. In the mkwrite * case we are creating a writable PTE for a shared * mapping and we expect the PFNs to match. If they * don't match, we are likely racing with block * allocation and mapping invalidation so just skip the * update. */ if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte))); goto out_unlock; } entry = pte_mkyoung(*pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, addr, pte, entry, 1)) update_mmu_cache(vma, addr, pte); } goto out_unlock; } /* Ok, finally just insert the thing.. */ if (pfn_t_devmap(pfn)) entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); else entry = pte_mkspecial(pfn_t_pte(pfn, prot)); if (mkwrite) { entry = pte_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); } set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ out_unlock: pte_unmap_unlock(pte, ptl); return VM_FAULT_NOPAGE; } /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_pfn(), except that it allows drivers * to override pgprot on a per-page basis. * * This only makes sense for IO mappings, and it makes no sense for * COW mappings. In general, using multiple vmas is preferable; * vmf_insert_pfn_prot should only be used if using multiple VMAs is * impractical. * * See vmf_insert_mixed_prot() for a discussion of the implication of using * a value of @pgprot different from that of @vma->vm_page_prot. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like * consistency in testing and feature parity among all, so we should * try to keep these invariants in place for everybody. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; if (!pfn_modify_allowed(pfn, pgprot)) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, false); } EXPORT_SYMBOL(vmf_insert_pfn_prot); /** * vmf_insert_pfn - insert single pfn into user vma * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * * Similar to vm_insert_page, this allows drivers to insert individual pages * they've allocated into a user vma. Same comments apply. * * This function should only be called from a vm_ops->fault handler, and * in that case the handler should return the result of this function. * * vma cannot be a COW mapping. * * As this is called only for pages that do not currently exist, we * do not need to flush old virtual caches or the TLB. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); } EXPORT_SYMBOL(vmf_insert_pfn); static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) { /* these checks mirror the abort conditions in vm_normal_page */ if (vma->vm_flags & VM_MIXEDMAP) return true; if (pfn_t_devmap(pfn)) return true; if (pfn_t_special(pfn)) return true; if (is_zero_pfn(pfn_t_to_pfn(pfn))) return true; return false; } static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot, bool mkwrite) { int err; BUG_ON(!vm_mixed_ok(vma, pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, pfn); if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot)) return VM_FAULT_SIGBUS; /* * If we don't have pte special, then we have to use the pfn_valid() * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* * refcount the page if pfn_valid is true (hence insert_page rather * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { struct page *page; /* * At this point we are committed to insert_page() * regardless of whether the caller specified flags that * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn_t_to_pfn(pfn)); err = insert_page(vma, addr, page, pgprot); } else { return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } if (err == -ENOMEM) return VM_FAULT_OOM; if (err < 0 && err != -EBUSY) return VM_FAULT_SIGBUS; return VM_FAULT_NOPAGE; } /** * vmf_insert_mixed_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to * @addr: target user address of this page * @pfn: source kernel pfn * @pgprot: pgprot flags for the inserted page * * This is exactly like vmf_insert_mixed(), except that it allows drivers * to override pgprot on a per-page basis. * * Typically this function should be used by drivers to set caching- and * encryption bits different than those of @vma->vm_page_prot, because * the caching- or encryption mode may not be known at mmap() time. * This is ok as long as @vma->vm_page_prot is not used by the core vm * to set caching and encryption bits for those vmas (except for COW pages). * This is ensured by core vm only modifying these page table entries using * functions that don't touch caching- or encryption bits, using pte_modify() * if needed. (See for example mprotect()). * Also when new page-table entries are created, this is only done using the * fault() callback, and never using the value of vma->vm_page_prot, * except for page-table entries that point to anonymous pages as the result * of COW. * * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t pgprot) { return __vm_insert_mixed(vma, addr, pfn, pgprot, false); } EXPORT_SYMBOL(vmf_insert_mixed_prot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, false); } EXPORT_SYMBOL(vmf_insert_mixed); /* * If the insertion of PTE failed because someone else already added a * different entry in the mean time, we treat that as success as we assume * the same entry was actually inserted. */ vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, true); } EXPORT_SYMBOL(vmf_insert_mixed_mkwrite); /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results * in null mappings (currently treated as "copy-on-access") */ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pte_t *pte, *mapped_pte; spinlock_t *ptl; int err = 0; mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); if (!pfn_modify_allowed(pfn, prot)) { err = -EACCES; break; } set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(mapped_pte, ptl); return err; } static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pmd_t *pmd; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pmd = pmd_alloc(mm, pud, addr); if (!pmd) return -ENOMEM; VM_BUG_ON(pmd_trans_huge(*pmd)); do { next = pmd_addr_end(addr, end); err = remap_pte_range(mm, pmd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pmd++, addr = next, addr != end); return 0; } static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { pud_t *pud; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; pud = pud_alloc(mm, p4d, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); err = remap_pmd_range(mm, pud, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pud++, addr = next, addr != end); return 0; } static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { p4d_t *p4d; unsigned long next; int err; pfn -= addr >> PAGE_SHIFT; p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); err = remap_pud_range(mm, p4d, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (p4d++, addr = next, addr != end); return 0; } static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { pgd_t *pgd; unsigned long next; unsigned long end = addr + PAGE_ALIGN(size); struct mm_struct *mm = vma->vm_mm; int err; if (WARN_ON_ONCE(!PAGE_ALIGNED(addr))) return -EINVAL; /* * Physically remapped pages are special. Tell the * rest of the world about it: * VM_IO tells people not to look at these pages * (accesses can have side effects). * VM_PFNMAP tells the core MM that the base pages are just * raw PFN mappings, and do not have a "struct page" associated * with them. * VM_DONTEXPAND * Disable vma merging and expanding with mremap(). * VM_DONTDUMP * Omit vma from core dump, even when VM_IO turned off. * * There's a horrible special case to handle copy-on-write * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". * See vm_normal_page() for details. */ if (is_cow_mapping(vma->vm_flags)) { if (addr != vma->vm_start || end != vma->vm_end) return -EINVAL; vma->vm_pgoff = pfn; } vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; pgd = pgd_offset(mm, addr); flush_cache_range(vma, addr, end); do { next = pgd_addr_end(addr, end); err = remap_p4d_range(mm, pgd, addr, next, pfn + (addr >> PAGE_SHIFT), prot); if (err) return err; } while (pgd++, addr = next, addr != end); return 0; } /* * Variant of remap_pfn_range that does not call track_pfn_remap. The caller * must have pre-validated the caching bits of the pgprot_t. */ int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { int error = remap_pfn_range_internal(vma, addr, pfn, size, prot); if (!error) return 0; /* * A partial pfn range mapping is dangerous: it does not * maintain page reference counts, and callers may free * pages due to the error. So zap it early. */ zap_page_range_single(vma, addr, size, NULL); return error; } /** * remap_pfn_range - remap kernel memory to userspace * @vma: user vma to map to * @addr: target page aligned user address to start at * @pfn: page frame number of kernel physical memory address * @size: size of mapping area * @prot: page protection flags for this mapping * * Note: this is only safe if the mm semaphore is held when called. * * Return: %0 on success, negative error code otherwise. */ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t prot) { int err; err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size)); if (err) return -EINVAL; err = remap_pfn_range_notrack(vma, addr, pfn, size, prot); if (err) untrack_pfn(vma, pfn, PAGE_ALIGN(size)); return err; } EXPORT_SYMBOL(remap_pfn_range); /** * vm_iomap_memory - remap memory to userspace * @vma: user vma to map to * @start: start of the physical memory to be mapped * @len: size of area * * This is a simplified io_remap_pfn_range() for common driver use. The * driver just needs to give us the physical memory range to be mapped, * we'll figure out the rest from the vma information. * * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get * whatever write-combining details or similar. * * Return: %0 on success, negative error code otherwise. */ int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) { unsigned long vm_len, pfn, pages; /* Check that the physical memory area passed in looks valid */ if (start + len < start) return -EINVAL; /* * You *really* shouldn't map things that aren't page-aligned, * but we've historically allowed it because IO memory might * just have smaller alignment. */ len += start & ~PAGE_MASK; pfn = start >> PAGE_SHIFT; pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; if (pfn + pages < pfn) return -EINVAL; /* We start the mapping 'vm_pgoff' pages into the area */ if (vma->vm_pgoff > pages) return -EINVAL; pfn += vma->vm_pgoff; pages -= vma->vm_pgoff; /* Can we fit all of the mapping? */ vm_len = vma->vm_end - vma->vm_start; if (vm_len >> PAGE_SHIFT > pages) return -EINVAL; /* Ok, let it rip */ return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); } EXPORT_SYMBOL(vm_iomap_memory); static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pte_t *pte; int err = 0; spinlock_t *ptl; if (create) { pte = (mm == &init_mm) ? pte_alloc_kernel_track(pmd, addr, mask) : pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; } else { pte = (mm == &init_mm) ? pte_offset_kernel(pmd, addr) : pte_offset_map_lock(mm, pmd, addr, &ptl); } BUG_ON(pmd_huge(*pmd)); arch_enter_lazy_mmu_mode(); if (fn) { do { if (create || !pte_none(*pte)) { err = fn(pte, addr, data); if (err) break; } } while (pte++, addr += PAGE_SIZE, addr != end); } *mask |= PGTBL_PTE_MODIFIED; arch_leave_lazy_mmu_mode(); if (mm != &init_mm) pte_unmap_unlock(pte-1, ptl); return err; } static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; int err = 0; BUG_ON(pud_huge(*pud)); if (create) { pmd = pmd_alloc_track(mm, pud, addr, mask); if (!pmd) return -ENOMEM; } else { pmd = pmd_offset(pud, addr); } do { next = pmd_addr_end(addr, end); if (create || !pmd_none_or_clear_bad(pmd)) { err = apply_to_pte_range(mm, pmd, addr, next, fn, data, create, mask); if (err) break; } } while (pmd++, addr = next, addr != end); return err; } static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; int err = 0; if (create) { pud = pud_alloc_track(mm, p4d, addr, mask); if (!pud) return -ENOMEM; } else { pud = pud_offset(p4d, addr); } do { next = pud_addr_end(addr, end); if (create || !pud_none_or_clear_bad(pud)) { err = apply_to_pmd_range(mm, pud, addr, next, fn, data, create, mask); if (err) break; } } while (pud++, addr = next, addr != end); return err; } static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data, bool create, pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; int err = 0; if (create) { p4d = p4d_alloc_track(mm, pgd, addr, mask); if (!p4d) return -ENOMEM; } else { p4d = p4d_offset(pgd, addr); } do { next = p4d_addr_end(addr, end); if (create || !p4d_none_or_clear_bad(p4d)) { err = apply_to_pud_range(mm, p4d, addr, next, fn, data, create, mask); if (err) break; } } while (p4d++, addr = next, addr != end); return err; } static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data, bool create) { pgd_t *pgd; unsigned long start = addr, next; unsigned long end = addr + size; pgtbl_mod_mask mask = 0; int err = 0; if (WARN_ON(addr >= end)) return -EINVAL; pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end); if (!create && pgd_none_or_clear_bad(pgd)) continue; err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask); if (err) break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, start + size); return err; } /* * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. */ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, true); } EXPORT_SYMBOL_GPL(apply_to_page_range); /* * Scan a region of virtual memory, calling a provided function on * each leaf page table where it exists. * * Unlike apply_to_page_range, this does _not_ fill in page tables * where they are absent. */ int apply_to_existing_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { return __apply_to_page_range(mm, addr, size, fn, data, false); } EXPORT_SYMBOL_GPL(apply_to_existing_page_range); /* * handle_pte_fault chooses page fault handler according to an entry which was * read non-atomically. Before making any commitment, on those architectures * or configurations (e.g. i386 with PAE) which might give a mix of unmatched * parts, do_swap_page must check under lock before unmapping the pte and * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, pte_t *page_table, pte_t orig_pte) { int same = 1; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPTION) if (sizeof(pte_t) > sizeof(unsigned long)) { spinlock_t *ptl = pte_lockptr(mm, pmd); spin_lock(ptl); same = pte_same(*page_table, orig_pte); spin_unlock(ptl); } #endif pte_unmap(page_table); return same; } static inline bool cow_user_page(struct page *dst, struct page *src, struct vm_fault *vmf) { bool ret; void *kaddr; void __user *uaddr; bool locked = false; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; unsigned long addr = vmf->address; if (likely(src)) { copy_user_highpage(dst, src, addr, vma); return true; } /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ kaddr = kmap_atomic(dst); uaddr = (void __user *)(addr & PAGE_MASK); /* * On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) { pte_t entry; vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* * Other thread has already handled the fault * and update local tlb only */ update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } entry = pte_mkyoung(vmf->orig_pte); if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) update_mmu_cache(vma, addr, vmf->pte); } /* * This really shouldn't fail, because the page is there * in the page tables. But it might just be unreadable, * in which case we just give up and fill the result with * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { if (locked) goto warn; /* Re-validate under PTL if the page is still mapped */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* The PTE changed under us, update local tlb */ update_mmu_tlb(vma, addr, vmf->pte); ret = false; goto pte_unlock; } /* * The same page can be mapped back since last copy attempt. * Try to copy again under PTL. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { /* * Give a warn in case there can be some obscure * use-case */ warn: WARN_ON_ONCE(1); clear_page(kaddr); } } ret = true; pte_unlock: if (locked) pte_unmap_unlock(vmf->pte, vmf->ptl); kunmap_atomic(kaddr); flush_dcache_page(dst); return ret; } static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) { struct file *vm_file = vma->vm_file; if (vm_file) return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO; /* * Special mappings (e.g. VDSO) do not have any file so fake * a default GFP_KERNEL for them. */ return GFP_KERNEL; } /* * Notify the address space that the page is about to become writable so that * it can prohibit this or wait for the page to get into an appropriate state. * * We do this without the lock held, so that it can sleep if it needs to. */ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf) { vm_fault_t ret; struct page *page = vmf->page; unsigned int old_flags = vmf->flags; vmf->flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; if (vmf->vma->vm_file && IS_SWAPFILE(vmf->vma->vm_file->f_mapping->host)) return VM_FAULT_SIGBUS; ret = vmf->vma->vm_ops->page_mkwrite(vmf); /* Restore original flags so that caller is not surprised */ vmf->flags = old_flags; if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) return ret; if (unlikely(!(ret & VM_FAULT_LOCKED))) { lock_page(page); if (!page->mapping) { unlock_page(page); return 0; /* retry */ } ret |= VM_FAULT_LOCKED; } else VM_BUG_ON_PAGE(!PageLocked(page), page); return ret; } /* * Handle dirtying of a page in shared file mapping on a write fault. * * The function expects the page to be locked and unlocks it. */ static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct address_space *mapping; struct page *page = vmf->page; bool dirtied; bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; dirtied = set_page_dirty(page); VM_BUG_ON_PAGE(PageAnon(page), page); /* * Take a local copy of the address_space - page.mapping may be zeroed * by truncate after unlock_page(). The address_space itself remains * pinned by vma->vm_file's reference. We rely on unlock_page()'s * release semantics to prevent the compiler from undoing this copying. */ mapping = page_rmapping(page); unlock_page(page); if (!page_mkwrite) file_update_time(vma->vm_file); /* * Throttle page dirtying rate down to writeback speed. * * mapping may be NULL here because some device drivers do not * set page.mapping but still dirty their pages * * Drop the mmap_lock before waiting on IO, if we can. The file * is pinning the mapping, as per above. */ if ((dirtied || page_mkwrite) && mapping) { struct file *fpin; fpin = maybe_unlock_mmap_for_io(vmf, NULL); balance_dirty_pages_ratelimited(mapping); if (fpin) { fput(fpin); return VM_FAULT_RETRY; } } return 0; } /* * Handle write page faults for pages that can be reused in the current vma * * This can happen either due to the mapping being with the VM_SHARED flag, * or due to us being the last reference standing to the page. In either * case, all we need to do here is to mark the page as writable and update * any related book-keeping. */ static inline void wp_page_reuse(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; struct page *page = vmf->page; pte_t entry; /* * Clear the pages cpupid information as the existing * information potentially belongs to a now completely * unrelated process. */ if (page) page_cpupid_xchg_last(page, (1 << LAST_CPUPID_SHIFT) - 1); flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = pte_mkyoung(vmf->orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); if (ptep_set_access_flags(vma, vmf->address, vmf->pte, entry, 1)) update_mmu_cache(vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); count_vm_event(PGREUSE); } /* * Handle the case of a page which we actually need to copy to a new page. * * Called with mmap_lock locked and the old page referenced, but * without the ptl held. * * High level logic flow: * * - Allocate a page, copy the content of the old page to the new one. * - Handle book keeping and accounting - cgroups, mmu-notifiers, etc. * - Take the PTL. If the pte changed, bail out and release the allocated page * - If the pte is still the way we remember it, update the page table and all * relevant references. This includes dropping the reference the page-table * held to the old page, as well as updating the rmap. * - In any case, unlock the PTL and drop the reference we took to the old page. */ static vm_fault_t wp_page_copy(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct page *old_page = vmf->page; struct page *new_page = NULL; pte_t entry; int page_copied = 0; struct mmu_notifier_range range; if (unlikely(anon_vma_prepare(vma))) goto oom; if (is_zero_pfn(pte_pfn(vmf->orig_pte))) { new_page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!new_page) goto oom; } else { new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!new_page) goto oom; if (!cow_user_page(new_page, old_page, vmf)) { /* * COW failed, if the fault was solved by other, * it's fine. If not, userspace would re-fault on * the same address and we will handle the fault * from the second attempt. */ put_page(new_page); if (old_page) put_page(old_page); return 0; } } if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) goto oom_free_new; cgroup_throttle_swaprate(new_page, GFP_KERNEL); __SetPageUptodate(new_page); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, vmf->address & PAGE_MASK, (vmf->address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(&range); /* * Re-check the pte - we dropped the lock */ vmf->pte = pte_offset_map_lock(mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) { if (old_page) { if (!PageAnon(old_page)) { dec_mm_counter_fast(mm, mm_counter_file(old_page)); inc_mm_counter_fast(mm, MM_ANONPAGES); } } else { inc_mm_counter_fast(mm, MM_ANONPAGES); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); entry = mk_pte(new_page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* * Clear the pte entry and flush it first, before updating the * pte with the new entry. This will avoid a race condition * seen in the presence of one thread doing SMC and another * thread doing COW. */ ptep_clear_flush_notify(vma, vmf->address, vmf->pte); page_add_new_anon_rmap(new_page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(new_page, vma); /* * We call the notify macro here because, when using secondary * mmu page tables (such as kvm shadow page tables), we want the * new page to be mapped directly into the secondary page table. */ set_pte_at_notify(mm, vmf->address, vmf->pte, entry); update_mmu_cache(vma, vmf->address, vmf->pte); if (old_page) { /* * Only after switching the pte to the new page may * we remove the mapcount here. Otherwise another * process may come and find the rmap count decremented * before the pte is switched to the new page, and * "reuse" the old page writing into it while our pte * here still points into it and can be read by other * threads. * * The critical issue is to order this * page_remove_rmap with the ptp_clear_flush above. * Those stores are ordered by (if nothing else,) * the barrier present in the atomic_add_negative * in page_remove_rmap. * * Then the TLB flush in ptep_clear_flush ensures that * no process can access the old page before the * decremented mapcount is visible. And the old page * cannot be reused until after the decremented * mapcount is visible. So transitively, TLBs to * old page will be flushed before it can be reused. */ page_remove_rmap(old_page, false); } /* Free the old page.. */ new_page = old_page; page_copied = 1; } else { update_mmu_tlb(vma, vmf->address, vmf->pte); } if (new_page) put_page(new_page); pte_unmap_unlock(vmf->pte, vmf->ptl); /* * No need to double call mmu_notifier->invalidate_range() callback as * the above ptep_clear_flush_notify() did already call it. */ mmu_notifier_invalidate_range_only_end(&range); if (old_page) { /* * Don't let another task, with possibly unlocked vma, * keep the mlocked page. */ if (page_copied && (vma->vm_flags & VM_LOCKED)) { lock_page(old_page); /* LRU manipulation */ if (PageMlocked(old_page)) munlock_vma_page(old_page); unlock_page(old_page); } put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; oom_free_new: put_page(new_page); oom: if (old_page) put_page(old_page); return VM_FAULT_OOM; } /** * finish_mkwrite_fault - finish page fault for a shared mapping, making PTE * writeable once the page is prepared * * @vmf: structure describing the fault * * This function handles all that is needed to finish a write page fault in a * shared mapping due to PTE being read-only once the mapped page is prepared. * It handles locking of PTE and modifying it. * * The function expects the page to be locked or other protection against * concurrent faults / writeback (such as DAX radix tree locks). * * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before * we acquired PTE lock. */ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) { WARN_ON_ONCE(!(vmf->vma->vm_flags & VM_SHARED)); vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); /* * We might have raced with another page fault while we released the * pte_offset_map_lock. */ if (!pte_same(*vmf->pte, vmf->orig_pte)) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return VM_FAULT_NOPAGE; } wp_page_reuse(vmf); return 0; } /* * Handle write page faults for VM_MIXEDMAP or VM_PFNMAP for a VM_SHARED * mapping */ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (vma->vm_ops && vma->vm_ops->pfn_mkwrite) { vm_fault_t ret; pte_unmap_unlock(vmf->pte, vmf->ptl); vmf->flags |= FAULT_FLAG_MKWRITE; ret = vma->vm_ops->pfn_mkwrite(vmf); if (ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)) return ret; return finish_mkwrite_fault(vmf); } wp_page_reuse(vmf); return VM_FAULT_WRITE; } static vm_fault_t wp_page_shared(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = VM_FAULT_WRITE; get_page(vmf->page); if (vma->vm_ops && vma->vm_ops->page_mkwrite) { vm_fault_t tmp; pte_unmap_unlock(vmf->pte, vmf->ptl); tmp = do_page_mkwrite(vmf); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { put_page(vmf->page); return tmp; } tmp = finish_mkwrite_fault(vmf); if (unlikely(tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) { unlock_page(vmf->page); put_page(vmf->page); return tmp; } } else { wp_page_reuse(vmf); lock_page(vmf->page); } ret |= fault_dirty_shared_page(vmf); put_page(vmf->page); return ret; } /* * This routine handles present pages, when users try to write * to a shared page. It is done by copying the page to a new address * and decrementing the shared-page counter for the old page. * * Note that this routine assumes that the protection checks have been * done by the caller (the low-level page fault routine in most cases). * Thus we can safely just mark it writable once we've done any necessary * COW. * * We also mark the page dirty at this point even though the page will * change only once the write actually happens. This avoids a few races, * and potentially makes it more efficient. * * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), with pte both mapped and locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_wp_page(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; if (userfaultfd_pte_wp(vma, *vmf->pte)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_WP); } /* * Userfaultfd write-protect can defer flushes. Ensure the TLB * is flushed in this case before copying. */ if (unlikely(userfaultfd_wp(vmf->vma) && mm_tlb_flush_pending(vmf->vma->vm_mm))) flush_tlb_page(vmf->vma, vmf->address); vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte); if (!vmf->page) { /* * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a * VM_PFNMAP VMA. * * We should not cow pages in a shared writeable mapping. * Just mark the pages writable and/or call ops->pfn_mkwrite. */ if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED)) return wp_pfn_shared(vmf); pte_unmap_unlock(vmf->pte, vmf->ptl); return wp_page_copy(vmf); } /* * Take out anonymous pages first, anonymous shared vmas are * not dirty accountable. */ if (PageAnon(vmf->page)) { struct page *page = vmf->page; /* PageKsm() doesn't necessarily raise the page refcount */ if (PageKsm(page) || page_count(page) != 1) goto copy; if (!trylock_page(page)) goto copy; if (PageKsm(page) || page_mapcount(page) != 1 || page_count(page) != 1) { unlock_page(page); goto copy; } /* * Ok, we've got the only map reference, and the only * page count reference, and the page is locked, * it's dark out, and we're wearing sunglasses. Hit it. */ unlock_page(page); wp_page_reuse(vmf); return VM_FAULT_WRITE; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); } copy: /* * Ok, we need to copy. Oh, well.. */ get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); return wp_page_copy(vmf); } static void unmap_mapping_range_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { zap_page_range_single(vma, start_addr, end_addr - start_addr, details); } static inline void unmap_mapping_range_tree(struct rb_root_cached *root, struct zap_details *details) { struct vm_area_struct *vma; pgoff_t vba, vea, zba, zea; vma_interval_tree_foreach(vma, root, details->first_index, details->last_index) { vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; zba = details->first_index; if (zba < vba) zba = vba; zea = details->last_index; if (zea > vea) zea = vea; unmap_mapping_range_vma(vma, ((zba - vba) << PAGE_SHIFT) + vma->vm_start, ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, details); } } /** * unmap_mapping_page() - Unmap single page from processes. * @page: The locked page to be unmapped. * * Unmap this page from any userspace process which still has it mmaped. * Typically, for efficiency, the range of nearby pages has already been * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once * truncation or invalidation holds the lock on a page, it may find that * the page has been remapped again: and then uses unmap_mapping_page() * to unmap it finally. */ void unmap_mapping_page(struct page *page) { struct address_space *mapping = page->mapping; struct zap_details details = { }; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageTail(page)); details.check_mapping = mapping; details.first_index = page->index; details.last_index = page->index + thp_nr_pages(page) - 1; details.single_page = page; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } /** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. * @start: Index of first page to be unmapped. * @nr: Number of pages to be unmapped. 0 to unmap to end of file. * @even_cows: Whether to unmap even private COWed pages. * * Unmap the pages in this address space from any userspace process which * has them mmaped. Generally, you want to remove COWed pages as well when * a file is being truncated, but not when invalidating pages from the page * cache. */ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { struct zap_details details = { }; details.check_mapping = even_cows ? NULL : mapping; details.first_index = start; details.last_index = start + nr - 1; if (details.last_index < details.first_index) details.last_index = ULONG_MAX; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) unmap_mapping_range_tree(&mapping->i_mmap, &details); i_mmap_unlock_write(mapping); } /** * unmap_mapping_range - unmap the portion of all mmaps in the specified * address_space corresponding to the specified byte range in the underlying * file. * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE * boundary. Note that this is different from truncate_pagecache(), which * must keep the partial page. In contrast, we must get rid of * partial pages. * @holelen: size of prospective hole in bytes. This will be rounded * up to a PAGE_SIZE boundary. A holelen of zero truncates to the * end of the file. * @even_cows: 1 when truncating a file, unmap even private COWed pages; * but 0 when invalidating pagecache, don't throw away private data. */ void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { long long holeend = (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; if (holeend & ~(long long)ULONG_MAX) hlen = ULONG_MAX - hba + 1; } unmap_mapping_pages(mapping, hba, hlen, even_cows); } EXPORT_SYMBOL(unmap_mapping_range); /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with pte unmapped and unlocked. * * We return with the mmap_lock locked or unlocked in the same cases * as does filemap_fault(). */ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; swp_entry_t entry; pte_t pte; int locked; int exclusive = 0; vm_fault_t ret = 0; void *shadow = NULL; if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) goto out; entry = pte_to_swp_entry(vmf->orig_pte); if (unlikely(non_swap_entry(entry))) { if (is_migration_entry(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); } else if (is_device_private_entry(entry)) { vmf->page = device_private_entry_to_page(entry); ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; } else { print_bad_pte(vma, vmf->address, vmf->orig_pte, NULL); ret = VM_FAULT_SIGBUS; } goto out; } delayacct_set_flag(DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry, vma, vmf->address); swapcache = page; if (!page) { struct swap_info_struct *si = swp_swap_info(entry); if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { /* skip swapcache */ page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (page) { int err; __SetPageLocked(page); __SetPageSwapBacked(page); set_page_private(page, entry.val); /* Tell memcg to use swap ownership records */ SetPageSwapCache(page); err = mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL); ClearPageSwapCache(page); if (err) { ret = VM_FAULT_OOM; goto out_page; } shadow = get_shadow_from_swap_cache(entry); if (shadow) workingset_refault(page, shadow); lru_cache_add(page); swap_readpage(page, true); } } else { page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vmf); swapcache = page; } if (!page) { /* * Back out if somebody else faulted in this pte * while we released the pte lock. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) ret = VM_FAULT_OOM; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto unlock; } /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(vma->vm_mm, PGMAJFAULT); } else if (PageHWPoison(page)) { /* * hwpoisoned dirty swapcache pages are kept for killing * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; delayacct_clear_flag(DELAYACCT_PF_SWAPIN); goto out_release; } locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags); delayacct_clear_flag(DELAYACCT_PF_SWAPIN); if (!locked) { ret |= VM_FAULT_RETRY; goto out_release; } /* * Make sure try_to_free_swap or reuse_swap_page or swapoff did not * release the swapcache from under us. The page pin, and pte_same * test below, are not enough to exclude that. Even if it is still * swapcache, we need to check that the page's swap has not changed. */ if (unlikely((!PageSwapCache(page) || page_private(page) != entry.val)) && swapcache) goto out_page; page = ksm_might_need_to_copy(page, vma, vmf->address); if (unlikely(!page)) { ret = VM_FAULT_OOM; page = swapcache; goto out_page; } cgroup_throttle_swaprate(page, GFP_KERNEL); /* * Back out if somebody else already faulted in this pte. */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) goto out_nomap; if (unlikely(!PageUptodate(page))) { ret = VM_FAULT_SIGBUS; goto out_nomap; } /* * The page isn't present yet, go ahead with the fault. * * Be careful about the sequence of operations here. * To get its accounting right, reuse_swap_page() must be called * while the page is counted on swap but not yet in mapcount i.e. * before page_add_anon_rmap() and swap_free(); try_to_free_swap() * must be called after the swap_free(), or it will never succeed. */ inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); vmf->flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; exclusive = RMAP_EXCLUSIVE; } flush_icache_page(vma, page); if (pte_swp_soft_dirty(vmf->orig_pte)) pte = pte_mksoft_dirty(pte); if (pte_swp_uffd_wp(vmf->orig_pte)) { pte = pte_mkuffd_wp(pte); pte = pte_wrprotect(pte); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte); arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte); vmf->orig_pte = pte; /* ksm created a completely new copy */ if (unlikely(page != swapcache && swapcache)) { page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { do_page_add_anon_rmap(page, vma, vmf->address, exclusive); } swap_free(entry); if (mem_cgroup_swap_full(page) || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) try_to_free_swap(page); unlock_page(page); if (page != swapcache && swapcache) { /* * Hold the lock to avoid the swap entry to be reused * until we take the PT lock for the pte_same() check * (to avoid false positives from pte_same). For * further safety release the lock after the swap_free * so that the swap count won't change under a * parallel locked swapcache. */ unlock_page(swapcache); put_page(swapcache); } if (vmf->flags & FAULT_FLAG_WRITE) { ret |= do_wp_page(vmf); if (ret & VM_FAULT_ERROR) ret &= VM_FAULT_ERROR; goto out; } /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); out: return ret; out_nomap: pte_unmap_unlock(vmf->pte, vmf->ptl); out_page: unlock_page(page); out_release: put_page(page); if (page != swapcache && swapcache) { unlock_page(swapcache); put_page(swapcache); } return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. * We return with mmap_lock still held, but pte unmapped and unlocked. */ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; vm_fault_t ret = 0; pte_t entry; /* File mapping without ->vm_ops ? */ if (vma->vm_flags & VM_SHARED) return VM_FAULT_SIGBUS; /* * Use pte_alloc() instead of pte_alloc_map(). We can't run * pte_offset_map() on pmds where a huge pmd might be created * from a different thread. * * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when * parallel threads are excluded by other means. * * Here we only have mmap_read_lock(mm). */ if (pte_alloc(vma->vm_mm, vmf->pmd)) return VM_FAULT_OOM; /* See the comment in pte_alloc_one_map() */ if (unlikely(pmd_trans_unstable(vmf->pmd))) return 0; /* Use the zero-page for reads */ if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm)) { entry = pte_mkspecial(pfn_pte(my_zero_pfn(vmf->address), vma->vm_page_prot)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { update_mmu_tlb(vma, vmf->address, vmf->pte); goto unlock; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return handle_userfault(vmf, VM_UFFD_MISSING); } goto setpte; } /* Allocate our own private page. */ if (unlikely(anon_vma_prepare(vma))) goto oom; page = alloc_zeroed_user_highpage_movable(vma, vmf->address); if (!page) goto oom; if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); /* * The memory barrier inside __SetPageUptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); entry = mk_pte(page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (vma->vm_flags & VM_WRITE) entry = pte_mkwrite(pte_mkdirty(entry)); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) { update_mmu_cache(vma, vmf->address, vmf->pte); goto release; } ret = check_stable_address_space(vma->vm_mm); if (ret) goto release; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); put_page(page); return handle_userfault(vmf, VM_UFFD_MISSING); } inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); setpte: set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; release: put_page(page); goto unlock; oom_free_page: put_page(page); oom: return VM_FAULT_OOM; } /* * The mmap_lock must have been held on entry, and may have been * released depending on flags and vma->vm_ops->fault() return value. * See filemap_fault() and __lock_page_retry(). */ static vm_fault_t __do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; /* * Preallocate pte before we take page_lock because this might lead to * deadlocks for memcg reclaim which waits for pages under writeback: * lock_page(A) * SetPageWriteback(A) * unlock_page(A) * lock_page(B) * lock_page(B) * pte_alloc_one * shrink_page_list * wait_on_page_writeback(A) * SetPageWriteback(B) * unlock_page(B) * # flush A, B to clear the writeback */ if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } ret = vma->vm_ops->fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | VM_FAULT_DONE_COW))) return ret; if (unlikely(PageHWPoison(vmf->page))) { struct page *page = vmf->page; vm_fault_t poisonret = VM_FAULT_HWPOISON; if (ret & VM_FAULT_LOCKED) { if (page_mapped(page)) unmap_mapping_pages(page_mapping(page), page->index, 1, false); /* Retry if a clean page was removed from the cache. */ if (invalidate_inode_page(page)) poisonret = VM_FAULT_NOPAGE; unlock_page(page); } put_page(page); vmf->page = NULL; return poisonret; } if (unlikely(!(ret & VM_FAULT_LOCKED))) lock_page(vmf->page); else VM_BUG_ON_PAGE(!PageLocked(vmf->page), vmf->page); return ret; } /* * The ordering of these checks is important for pmds with _PAGE_DEVMAP set. * If we check pmd_trans_unstable() first we will trip the bad_pmd() check * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. */ static int pmd_devmap_trans_unstable(pmd_t *pmd) { return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); } static vm_fault_t pte_alloc_one_map(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; if (!pmd_none(*vmf->pmd)) goto map_pte; if (vmf->prealloc_pte) { vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { spin_unlock(vmf->ptl); goto map_pte; } mm_inc_nr_ptes(vma->vm_mm); pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); spin_unlock(vmf->ptl); vmf->prealloc_pte = NULL; } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) { return VM_FAULT_OOM; } map_pte: /* * If a huge pmd materialized under us just retry later. Use * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge * under us and then back to pmd_none, as a result of MADV_DONTNEED * running immediately after a huge pmd fault in a different thread of * this mm, in turn leading to a misleading pmd_trans_huge() retval. * All we have to ensure is that it is a regular pmd that we can walk * with pte_offset_map() and we can do that through an atomic read in * C, which is what pmd_trans_unstable() provides. */ if (pmd_devmap_trans_unstable(vmf->pmd)) return VM_FAULT_NOPAGE; /* * At this point we know that our vmf->pmd points to a page of ptes * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge() * for the duration of the fault. If a racing MADV_DONTNEED runs and * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still * be valid and we will re-check to make sure the vmf->pte isn't * pte_none() under vmf->ptl protection when we return to * alloc_set_pte(). */ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); return 0; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void deposit_prealloc_pte(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, vmf->prealloc_pte); /* * We are going to consume the prealloc table, * count that as nr_ptes. */ mm_inc_nr_ptes(vma->vm_mm); vmf->prealloc_pte = NULL; } static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t entry; int i; vm_fault_t ret = VM_FAULT_FALLBACK; if (!transhuge_vma_suitable(vma, haddr)) return ret; page = compound_head(page); if (compound_order(page) != HPAGE_PMD_ORDER) return ret; /* * Archs like ppc64 need additonal space to store information * related to pte entry. Use the preallocated table for that. */ if (arch_needs_pgtable_deposit() && !vmf->prealloc_pte) { vmf->prealloc_pte = pte_alloc_one(vma->vm_mm); if (!vmf->prealloc_pte) return VM_FAULT_OOM; smp_wmb(); /* See comment in __pte_alloc() */ } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) goto out; for (i = 0; i < HPAGE_PMD_NR; i++) flush_icache_page(vma, page + i); entry = mk_huge_pmd(page, vma->vm_page_prot); if (write) entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); add_mm_counter(vma->vm_mm, mm_counter_file(page), HPAGE_PMD_NR); page_add_file_rmap(page, true); /* * deposit and withdraw with pmd lock held */ if (arch_needs_pgtable_deposit()) deposit_prealloc_pte(vmf); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, haddr, vmf->pmd); /* fault is handled */ ret = 0; count_vm_event(THP_FILE_MAPPED); out: spin_unlock(vmf->ptl); return ret; } #else static vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page) { BUILD_BUG(); return 0; } #endif /** * alloc_set_pte - setup new PTE entry for given page and add reverse page * mapping. If needed, the function allocates page table or use pre-allocated. * * @vmf: fault environment * @page: page to map * * Caller must take care of unlocking vmf->ptl, if vmf->pte is non-NULL on * return. * * Target users are page handler itself and implementations of * vm_ops->map_pages. * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct page *page) { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; pte_t entry; vm_fault_t ret; if (pmd_none(*vmf->pmd) && PageTransCompound(page)) { ret = do_set_pmd(vmf, page); if (ret != VM_FAULT_FALLBACK) return ret; } if (!vmf->pte) { ret = pte_alloc_one_map(vmf); if (ret) return ret; } /* Re-check under ptl */ if (unlikely(!pte_none(*vmf->pte))) { update_mmu_tlb(vma, vmf->address, vmf->pte); return VM_FAULT_NOPAGE; } flush_icache_page(vma, page); entry = mk_pte(page, vma->vm_page_prot); entry = pte_sw_mkyoung(entry); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); /* copy-on-write page */ if (write && !(vma->vm_flags & VM_SHARED)) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, vmf->address, false); lru_cache_add_inactive_or_unevictable(page, vma); } else { inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page)); page_add_file_rmap(page, false); } set_pte_at(vma->vm_mm, vmf->address, vmf->pte, entry); /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache(vma, vmf->address, vmf->pte); return 0; } /** * finish_fault - finish page fault once we have prepared the page to fault * * @vmf: structure describing the fault * * This function handles all that is needed to finish a page fault once the * page to fault in is prepared. It handles locking of PTEs, inserts PTE for * given page, adds reverse page mapping, handles memcg charges and LRU * addition. * * The function expects the page to be locked and on success it consumes a * reference of a page being mapped (for the PTE which maps it). * * Return: %0 on success, %VM_FAULT_ code in case of error. */ vm_fault_t finish_fault(struct vm_fault *vmf) { struct page *page; vm_fault_t ret = 0; /* Did we COW the page? */ if ((vmf->flags & FAULT_FLAG_WRITE) && !(vmf->vma->vm_flags & VM_SHARED)) page = vmf->cow_page; else page = vmf->page; /* * check even for read faults because we might have lost our CoWed * page */ if (!(vmf->vma->vm_flags & VM_SHARED)) ret = check_stable_address_space(vmf->vma->vm_mm); if (!ret) ret = alloc_set_pte(vmf, page); if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; } static unsigned long fault_around_bytes __read_mostly = rounddown_pow_of_two(65536); #ifdef CONFIG_DEBUG_FS static int fault_around_bytes_get(void *data, u64 *val) { *val = fault_around_bytes; return 0; } /* * fault_around_bytes must be rounded down to the nearest page order as it's * what do_fault_around() expects to see. */ static int fault_around_bytes_set(void *data, u64 val) { if (val / PAGE_SIZE > PTRS_PER_PTE) return -EINVAL; if (val > PAGE_SIZE) fault_around_bytes = rounddown_pow_of_two(val); else fault_around_bytes = PAGE_SIZE; /* rounddown_pow_of_two(0) is undefined */ return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fault_around_bytes_fops, fault_around_bytes_get, fault_around_bytes_set, "%llu\n"); static int __init fault_around_debugfs(void) { debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL, &fault_around_bytes_fops); return 0; } late_initcall(fault_around_debugfs); #endif /* * do_fault_around() tries to map few pages around the fault address. The hope * is that the pages will be needed soon and this will lower the number of * faults to handle. * * It uses vm_ops->map_pages() to map the pages, which skips the page if it's * not ready to be mapped: not up-to-date, locked, etc. * * This function is called with the page table lock taken. In the split ptlock * case the page table lock only protects only those entries which belong to * the page table corresponding to the fault address. * * This function doesn't cross the VMA boundaries, in order to call map_pages() * only once. * * fault_around_bytes defines how many bytes we'll try to map. * do_fault_around() expects it to be set to a power of two less than or equal * to PTRS_PER_PTE. * * The virtual address of the area that we map is naturally aligned to * fault_around_bytes rounded down to the machine page size * (and therefore to page order). This way it's easier to guarantee * that we don't cross page table boundaries. */ static vm_fault_t do_fault_around(struct vm_fault *vmf) { unsigned long address = vmf->address, nr_pages, mask; pgoff_t start_pgoff = vmf->pgoff; pgoff_t end_pgoff; int off; vm_fault_t ret = 0; nr_pages = READ_ONCE(fault_around_bytes) >> PAGE_SHIFT; mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK; vmf->address = max(address & mask, vmf->vma->vm_start); off = ((address - vmf->address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); start_pgoff -= off; /* * end_pgoff is either the end of the page table, the end of * the vma or nr_pages from start_pgoff, depending what is nearest. */ end_pgoff = start_pgoff - ((vmf->address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) + PTRS_PER_PTE - 1; end_pgoff = min3(end_pgoff, vma_pages(vmf->vma) + vmf->vma->vm_pgoff - 1, start_pgoff + nr_pages - 1); if (pmd_none(*vmf->pmd)) { vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); if (!vmf->prealloc_pte) goto out; smp_wmb(); /* See comment in __pte_alloc() */ } vmf->vma->vm_ops->map_pages(vmf, start_pgoff, end_pgoff); /* Huge page is mapped? Page fault is solved */ if (pmd_trans_huge(*vmf->pmd)) { ret = VM_FAULT_NOPAGE; goto out; } /* ->map_pages() haven't done anything useful. Cold page cache? */ if (!vmf->pte) goto out; /* check if the page fault is solved */ vmf->pte -= (vmf->address >> PAGE_SHIFT) - (address >> PAGE_SHIFT); if (!pte_none(*vmf->pte)) ret = VM_FAULT_NOPAGE; pte_unmap_unlock(vmf->pte, vmf->ptl); out: vmf->address = address; vmf->pte = NULL; return ret; } static vm_fault_t do_read_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; /* * Let's call ->map_pages() first and use ->fault() as fallback * if page by the offset is not ready to be mapped (cold cache or * something). */ if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { ret = do_fault_around(vmf); if (ret) return ret; } ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; ret |= finish_fault(vmf); unlock_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) put_page(vmf->page); return ret; } static vm_fault_t do_cow_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; if (unlikely(anon_vma_prepare(vma))) return VM_FAULT_OOM; vmf->cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!vmf->cow_page) return VM_FAULT_OOM; if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } cgroup_throttle_swaprate(vmf->cow_page, GFP_KERNEL); ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; if (ret & VM_FAULT_DONE_COW) return ret; copy_user_highpage(vmf->cow_page, vmf->page, vmf->address, vma); __SetPageUptodate(vmf->cow_page); ret |= finish_fault(vmf); unlock_page(vmf->page); put_page(vmf->page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; return ret; uncharge_out: put_page(vmf->cow_page); return ret; } static vm_fault_t do_shared_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret, tmp; ret = __do_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; /* * Check if the backing address space wants to know that the page is * about to become writable */ if (vma->vm_ops->page_mkwrite) { unlock_page(vmf->page); tmp = do_page_mkwrite(vmf); if (unlikely(!tmp || (tmp & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))) { put_page(vmf->page); return tmp; } } ret |= finish_fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) { unlock_page(vmf->page); put_page(vmf->page); return ret; } ret |= fault_dirty_shared_page(vmf); return ret; } /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults). * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). * If mmap_lock is released, vma may become invalid (for example * by other thread calling munmap()). */ static vm_fault_t do_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *vm_mm = vma->vm_mm; vm_fault_t ret; /* * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ if (!vma->vm_ops->fault) { /* * If we find a migration pmd entry or a none pmd entry, which * should never happen, return SIGBUS */ if (unlikely(!pmd_present(*vmf->pmd))) ret = VM_FAULT_SIGBUS; else { vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); /* * Make sure this is not a temporary clearing of pte * by holding ptl and checking again. A R/M/W update * of pte involves: take ptl, clearing the pte so that * we don't have concurrent modification by hardware * followed by an update. */ if (unlikely(pte_none(*vmf->pte))) ret = VM_FAULT_SIGBUS; else ret = VM_FAULT_NOPAGE; pte_unmap_unlock(vmf->pte, vmf->ptl); } } else if (!(vmf->flags & FAULT_FLAG_WRITE)) ret = do_read_fault(vmf); else if (!(vma->vm_flags & VM_SHARED)) ret = do_cow_fault(vmf); else ret = do_shared_fault(vmf); /* preallocated pagetable is unused: free it */ if (vmf->prealloc_pte) { pte_free(vm_mm, vmf->prealloc_pte); vmf->prealloc_pte = NULL; } return ret; } static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags) { get_page(page); count_vm_numa_event(NUMA_HINT_FAULTS); if (page_nid == numa_node_id()) { count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); *flags |= TNF_FAULT_LOCAL; } return mpol_misplaced(page, vma, addr); } static vm_fault_t do_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL; int page_nid = NUMA_NO_NODE; int last_cpupid; int target_nid; bool migrated = false; pte_t pte, old_pte; bool was_writable = pte_savedwrite(vmf->orig_pte); int flags = 0; /* * The "pte" at this point cannot be used safely without * validation through pte_unmap_same(). It's of NUMA type but * the pfn may be screwed if the read is non atomic. */ vmf->ptl = pte_lockptr(vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); if (unlikely(!pte_same(*vmf->pte, vmf->orig_pte))) { pte_unmap_unlock(vmf->pte, vmf->ptl); goto out; } /* * Make it present again, Depending on how arch implementes non * accessible ptes, some can allow access by kernel mode. */ old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte); pte = pte_modify(old_pte, vma->vm_page_prot); pte = pte_mkyoung(pte); if (was_writable) pte = pte_mkwrite(pte); ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte); update_mmu_cache(vma, vmf->address, vmf->pte); page = vm_normal_page(vma, vmf->address, pte); if (!page) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* TODO: handle PTE-mapped THP */ if (PageCompound(page)) { pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* * Avoid grouping on RO pages in general. RO pages shouldn't hurt as * much anyway since they can be in shared cache state. This misses * the case where a mapping is writable but the process never writes * to it but pte_write gets cleared during protection updates and * pte_dirty has unpredictable behaviour between PTE scan updates, * background writeback, dirty balancing and application behaviour. */ if (!pte_write(pte)) flags |= TNF_NO_GROUP; /* * Flag if the page is shared between multiple address spaces. This * is later used when determining whether to group tasks together */ if (page_mapcount(page) > 1 && (vma->vm_flags & VM_SHARED)) flags |= TNF_SHARED; last_cpupid = page_cpupid_last(page); page_nid = page_to_nid(page); target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid, &flags); pte_unmap_unlock(vmf->pte, vmf->ptl); if (target_nid == NUMA_NO_NODE) { put_page(page); goto out; } /* Migrate to the requested node */ migrated = migrate_misplaced_page(page, vma, target_nid); if (migrated) { page_nid = target_nid; flags |= TNF_MIGRATED; } else flags |= TNF_MIGRATE_FAIL; out: if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, 1, flags); return 0; } static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) return do_huge_pmd_anonymous_page(vmf); if (vmf->vma->vm_ops->huge_fault) return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); return VM_FAULT_FALLBACK; } /* `inline' is required to avoid gcc 4.1.2 build error */ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) { if (vma_is_anonymous(vmf->vma)) { if (userfaultfd_huge_pmd_wp(vmf->vma, orig_pmd)) return handle_userfault(vmf, VM_UFFD_WP); return do_huge_pmd_wp_page(vmf, orig_pmd); } if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); if (!(ret & VM_FAULT_FALLBACK)) return ret; } /* COW or write-notify handled on pte level: split pmd. */ __split_huge_pmd(vmf->vma, vmf->pmd, vmf->address, false, NULL); return VM_FAULT_FALLBACK; } static vm_fault_t create_huge_pud(struct vm_fault *vmf) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) return VM_FAULT_FALLBACK; if (vmf->vma->vm_ops->huge_fault) return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ return VM_FAULT_FALLBACK; } static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) /* No support for anonymous transparent PUD pages yet */ if (vma_is_anonymous(vmf->vma)) goto split; if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD); if (!(ret & VM_FAULT_FALLBACK)) return ret; } split: /* COW or write-notify not handled on PUD level: split pud.*/ __split_huge_pud(vmf->vma, vmf->pud, vmf->address); #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ return VM_FAULT_FALLBACK; } /* * These routines also need to handle stuff like marking pages dirty * and/or accessed for architectures that don't do it in hardware (most * RISC architectures). The early dirtying is also good on the i386. * * There is also a hook called "update_mmu_cache()" that architectures * with external mmu caches can use to update those (ie the Sparc or * PowerPC hashed page tables that act as extended TLBs). * * We enter with non-exclusive mmap_lock (to exclude vma changes, but allow * concurrent faults). * * The mmap_lock may have been released depending on flags and our return value. * See filemap_fault() and __lock_page_or_retry(). */ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) { pte_t entry; if (unlikely(pmd_none(*vmf->pmd))) { /* * Leave __pte_alloc() until later: because vm_ops->fault may * want to allocate huge page, and if we expose page table * for an instant, it will be difficult to retract from * concurrent faults and from rmap lookups. */ vmf->pte = NULL; } else { /* See comment in pte_alloc_one_map() */ if (pmd_devmap_trans_unstable(vmf->pmd)) return 0; /* * A regular pmd is established and it can't morph into a huge * pmd from under us anymore at this point because we hold the * mmap_lock read mode and khugepaged takes it in write mode. * So now it's safe to run pte_offset_map(). */ vmf->pte = pte_offset_map(vmf->pmd, vmf->address); vmf->orig_pte = *vmf->pte; /* * some architectures can have larger ptes than wordsize, * e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and * CONFIG_32BIT=y, so READ_ONCE cannot guarantee atomic * accesses. The code below just needs a consistent view * for the ifs and we later double check anyway with the * ptl lock held. So here a barrier will do. */ barrier(); if (pte_none(vmf->orig_pte)) { pte_unmap(vmf->pte); vmf->pte = NULL; } } if (!vmf->pte) { if (vma_is_anonymous(vmf->vma)) return do_anonymous_page(vmf); else return do_fault(vmf); } if (!pte_present(vmf->orig_pte)) return do_swap_page(vmf); if (pte_protnone(vmf->orig_pte) && vma_is_accessible(vmf->vma)) return do_numa_page(vmf); vmf->ptl = pte_lockptr(vmf->vma->vm_mm, vmf->pmd); spin_lock(vmf->ptl); entry = vmf->orig_pte; if (unlikely(!pte_same(*vmf->pte, entry))) { update_mmu_tlb(vmf->vma, vmf->address, vmf->pte); goto unlock; } if (vmf->flags & FAULT_FLAG_WRITE) { if (!pte_write(entry)) return do_wp_page(vmf); entry = pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry, vmf->flags & FAULT_FLAG_WRITE)) { update_mmu_cache(vmf->vma, vmf->address, vmf->pte); } else { /* Skip spurious TLB flush for retried page fault */ if (vmf->flags & FAULT_FLAG_TRIED) goto unlock; /* * This is needed only for protection faults but the arch code * is not yet telling us if this is a protection fault or not. * This still avoids useless tlb flushes for .text page faults * with threads. */ if (vmf->flags & FAULT_FLAG_WRITE) flush_tlb_fix_spurious_fault(vmf->vma, vmf->address); } unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; } /* * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) { struct vm_fault vmf = { .vma = vma, .address = address & PAGE_MASK, .flags = flags, .pgoff = linear_page_index(vma, address), .gfp_mask = __get_fault_gfp_mask(vma), }; unsigned int dirty = flags & FAULT_FLAG_WRITE; struct mm_struct *mm = vma->vm_mm; pgd_t *pgd; p4d_t *p4d; vm_fault_t ret; pgd = pgd_offset(mm, address); p4d = p4d_alloc(mm, pgd, address); if (!p4d) return VM_FAULT_OOM; vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud) return VM_FAULT_OOM; retry_pud: if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pud_t orig_pud = *vmf.pud; barrier(); if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) { /* NUMA case for anonymous PUDs would go here */ if (dirty && !pud_write(orig_pud)) { ret = wp_huge_pud(&vmf, orig_pud); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pud_set_accessed(&vmf, orig_pud); return 0; } } } vmf.pmd = pmd_alloc(mm, vmf.pud, address); if (!vmf.pmd) return VM_FAULT_OOM; /* Huge pud page fault raced with pmd_alloc? */ if (pud_trans_unstable(vmf.pud)) goto retry_pud; if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { pmd_t orig_pmd = *vmf.pmd; barrier(); if (unlikely(is_swap_pmd(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(orig_pmd)); if (is_pmd_migration_entry(orig_pmd)) pmd_migration_entry_wait(mm, vmf.pmd); return 0; } if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) return do_huge_pmd_numa_page(&vmf, orig_pmd); if (dirty && !pmd_write(orig_pmd)) { ret = wp_huge_pmd(&vmf, orig_pmd); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { huge_pmd_set_accessed(&vmf, orig_pmd); return 0; } } } return handle_pte_fault(&vmf); } /** * mm_account_fault - Do page fault accountings * * @regs: the pt_regs struct pointer. When set to NULL, will skip accounting * of perf event counters, but we'll still do the per-task accounting to * the task who triggered this page fault. * @address: the faulted address. * @flags: the fault flags. * @ret: the fault retcode. * * This will take care of most of the page fault accountings. Meanwhile, it * will also include the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf counter * updates. However note that the handling of PERF_COUNT_SW_PAGE_FAULTS should * still be in per-arch page fault handlers at the entry of page fault. */ static inline void mm_account_fault(struct pt_regs *regs, unsigned long address, unsigned int flags, vm_fault_t ret) { bool major; /* * We don't do accounting for some specific faults: * * - Unsuccessful faults (e.g. when the address wasn't valid). That * includes arch_vma_access_permitted() failing before reaching here. * So this is not a "this many hardware page faults" counter. We * should use the hw profiling for that. * * - Incomplete faults (VM_FAULT_RETRY). They will only be counted * once they're completed. */ if (ret & (VM_FAULT_ERROR | VM_FAULT_RETRY)) return; /* * We define the fault as a major fault when the final successful fault * is VM_FAULT_MAJOR, or if it retried (which implies that we couldn't * handle it immediately previously). */ major = (ret & VM_FAULT_MAJOR) || (flags & FAULT_FLAG_TRIED); if (major) current->maj_flt++; else current->min_flt++; /* * If the fault is done for GUP, regs will be NULL. We only do the * accounting for the per thread fault counters who triggered the * fault, and we skip the perf event updates. */ if (!regs) return; if (major) perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); else perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } /* * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) { vm_fault_t ret; __set_current_state(TASK_RUNNING); count_vm_event(PGFAULT); count_memcg_event_mm(vma->vm_mm, PGFAULT); /* do counter updates before entering really critical section. */ check_sync_rss_stat(current); if (!arch_vma_access_permitted(vma, flags & FAULT_FLAG_WRITE, flags & FAULT_FLAG_INSTRUCTION, flags & FAULT_FLAG_REMOTE)) return VM_FAULT_SIGSEGV; /* * Enable the memcg OOM handling for faults triggered in user * space. Kernel faults are handled more gracefully. */ if (flags & FAULT_FLAG_USER) mem_cgroup_enter_user_fault(); if (unlikely(is_vm_hugetlb_page(vma))) ret = hugetlb_fault(vma->vm_mm, vma, address, flags); else ret = __handle_mm_fault(vma, address, flags); if (flags & FAULT_FLAG_USER) { mem_cgroup_exit_user_fault(); /* * The task may have entered a memcg OOM situation but * if the allocation error was handled gracefully (no * VM_FAULT_OOM), there is no need to kill anything. * Just clean up the OOM state peacefully. */ if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)) mem_cgroup_oom_synchronize(false); } mm_account_fault(regs, address, flags, ret); return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); #ifndef __PAGETABLE_P4D_FOLDED /* * Allocate p4d page table. * We've already handled the fast-path in-line. */ int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) { p4d_t *new = p4d_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); if (pgd_present(*pgd)) /* Another has populated it */ p4d_free(mm, new); else pgd_populate(mm, pgd, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_P4D_FOLDED */ #ifndef __PAGETABLE_PUD_FOLDED /* * Allocate page upper directory. * We've already handled the fast-path in-line. */ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address) { pud_t *new = pud_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ spin_lock(&mm->page_table_lock); if (!p4d_present(*p4d)) { mm_inc_nr_puds(mm); p4d_populate(mm, p4d, new); } else /* Another has populated it */ pud_free(mm, new); spin_unlock(&mm->page_table_lock); return 0; } #endif /* __PAGETABLE_PUD_FOLDED */ #ifndef __PAGETABLE_PMD_FOLDED /* * Allocate page middle directory. * We've already handled the fast-path in-line. */ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) { spinlock_t *ptl; pmd_t *new = pmd_alloc_one(mm, address); if (!new) return -ENOMEM; smp_wmb(); /* See comment in __pte_alloc */ ptl = pud_lock(mm, pud); if (!pud_present(*pud)) { mm_inc_nr_pmds(mm); pud_populate(mm, pud, new); } else /* Another has populated it */ pmd_free(mm, new); spin_unlock(ptl); return 0; } #endif /* __PAGETABLE_PMD_FOLDED */ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *ptep; pgd = pgd_offset(mm, address); if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) goto out; p4d = p4d_offset(pgd, address); if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d))) goto out; pud = pud_offset(p4d, address); if (pud_none(*pud) || unlikely(pud_bad(*pud))) goto out; pmd = pmd_offset(pud, address); VM_BUG_ON(pmd_trans_huge(*pmd)); if (pmd_huge(*pmd)) { if (!pmdpp) goto out; if (range) { mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address & PMD_MASK, (address & PMD_MASK) + PMD_SIZE); mmu_notifier_invalidate_range_start(range); } *ptlp = pmd_lock(mm, pmd); if (pmd_huge(*pmd)) { *pmdpp = pmd; return 0; } spin_unlock(*ptlp); if (range) mmu_notifier_invalidate_range_end(range); } if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) goto out; if (range) { mmu_notifier_range_init(range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address & PAGE_MASK, (address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(range); } ptep = pte_offset_map_lock(mm, pmd, address, ptlp); if (!pte_present(*ptep)) goto unlock; *ptepp = ptep; return 0; unlock: pte_unmap_unlock(ptep, *ptlp); if (range) mmu_notifier_invalidate_range_end(range); out: return -EINVAL; } /** * follow_pte - look up PTE at a user virtual address * @mm: the mm_struct of the target address space * @address: user virtual address * @ptepp: location to store found PTE * @ptlp: location to store the lock for the PTE * * On a successful return, the pointer to the PTE is stored in @ptepp; * the corresponding lock is taken and its location is stored in @ptlp. * The contents of the PTE are only stable until @ptlp is released; * any further use, if any, must be protected against invalidation * with MMU notifiers. * * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore * should be taken for read. * * KVM uses this function. While it is arguably less bad than ``follow_pfn``, * it is not a good general-purpose API. * * Return: zero on success, -ve otherwise. */ int follow_pte(struct mm_struct *mm, unsigned long address, pte_t **ptepp, spinlock_t **ptlp) { return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp); } EXPORT_SYMBOL_GPL(follow_pte); /** * follow_pfn - look up PFN at a user virtual address * @vma: memory mapping * @address: user virtual address * @pfn: location to store found PFN * * Only IO mappings and raw PFN mappings are allowed. * * This function does not allow the caller to read the permissions * of the PTE. Do not use it. * * Return: zero and the pfn at @pfn on success, -ve otherwise. */ int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn) { int ret = -EINVAL; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) return ret; ret = follow_pte(vma->vm_mm, address, &ptep, &ptl); if (ret) return ret; *pfn = pte_pfn(*ptep); pte_unmap_unlock(ptep, ptl); return 0; } EXPORT_SYMBOL(follow_pfn); #ifdef CONFIG_HAVE_IOREMAP_PROT int follow_phys(struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned long *prot, resource_size_t *phys) { int ret = -EINVAL; pte_t *ptep, pte; spinlock_t *ptl; if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) goto out; if (follow_pte(vma->vm_mm, address, &ptep, &ptl)) goto out; pte = *ptep; /* Never return PFNs of anon folios in COW mappings. */ if (vm_normal_page(vma, address, pte)) goto unlock; if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; *prot = pgprot_val(pte_pgprot(pte)); *phys = (resource_size_t)pte_pfn(pte) << PAGE_SHIFT; ret = 0; unlock: pte_unmap_unlock(ptep, ptl); out: return ret; } int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { resource_size_t phys_addr; unsigned long prot = 0; void __iomem *maddr; int offset = addr & (PAGE_SIZE-1); if (follow_phys(vma, addr, write, &prot, &phys_addr)) return -EINVAL; maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (!maddr) return -ENOMEM; if (write) memcpy_toio(maddr + offset, buf, len); else memcpy_fromio(buf, maddr + offset, len); iounmap(maddr); return len; } EXPORT_SYMBOL_GPL(generic_access_phys); #endif /* * Access another process' address space as given in mm. If non-NULL, use the * given task for page fault accounting. */ int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct vm_area_struct *vma; void *old_buf = buf; int write = gup_flags & FOLL_WRITE; if (mmap_read_lock_killable(mm)) return 0; /* ignore errors, just check how much was successfully transferred */ while (len) { int bytes, ret, offset; void *maddr; struct page *page = NULL; ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page, &vma, NULL); if (ret <= 0) { #ifndef CONFIG_HAVE_IOREMAP_PROT break; #else /* * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. */ vma = find_vma(mm, addr); if (!vma || vma->vm_start > addr) break; if (vma->vm_ops && vma->vm_ops->access) ret = vma->vm_ops->access(vma, addr, buf, len, write); if (ret <= 0) break; bytes = ret; #endif } else { bytes = len; offset = addr & (PAGE_SIZE-1); if (bytes > PAGE_SIZE-offset) bytes = PAGE_SIZE-offset; maddr = kmap(page); if (write) { copy_to_user_page(vma, page, addr, maddr + offset, buf, bytes); set_page_dirty_lock(page); } else { copy_from_user_page(vma, page, addr, buf, maddr + offset, bytes); } kunmap(page); put_page(page); } len -= bytes; buf += bytes; addr += bytes; } mmap_read_unlock(mm); return buf - old_buf; } /** * access_remote_vm - access another process' address space * @mm: the mm_struct of the target address space * @addr: start address to access * @buf: source or destination buffer * @len: number of bytes to transfer * @gup_flags: flags modifying lookup behaviour * * The caller must hold a reference on @mm. * * Return: number of bytes copied from source to destination. */ int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags) { return __access_remote_vm(NULL, mm, addr, buf, len, gup_flags); } /* * Access another process' address space. * Source/target buffer must be kernel space, * Do not walk the page table directly, use get_user_pages */ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags) { struct mm_struct *mm; int ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags); mmput(mm); return ret; } EXPORT_SYMBOL_GPL(access_process_vm); /* * Print the name of a VMA. */ void print_vma_addr(char *prefix, unsigned long ip) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; /* * we might be running from an atomic context so we cannot sleep */ if (!mmap_read_trylock(mm)) return; vma = find_vma(mm, ip); if (vma && vma->vm_file) { struct file *f = vma->vm_file; char *buf = (char *)__get_free_page(GFP_NOWAIT); if (buf) { char *p; p = file_path(f, buf, PAGE_SIZE); if (IS_ERR(p)) p = "?"; printk("%s%s[%lx+%lx]", prefix, kbasename(p), vma->vm_start, vma->vm_end - vma->vm_start); free_page((unsigned long)buf); } } mmap_read_unlock(mm); } #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) void __might_fault(const char *file, int line) { /* * Some code (nfs/sunrpc) uses socket ops on kernel memory while * holding the mmap_lock, this is safe because kernel memory doesn't * get paged out, therefore we'll never actually fault, and the * below annotations will generate false positives. */ if (uaccess_kernel()) return; if (pagefault_disabled()) return; __might_sleep(file, line, 0); #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) if (current->mm) might_lock_read(¤t->mm->mmap_lock); #endif } EXPORT_SYMBOL(__might_fault); #endif #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) /* * Process all subpages of the specified huge page with the specified * operation. The target subpage will be processed last to keep its * cache lines hot. */ static inline void process_huge_page( unsigned long addr_hint, unsigned int pages_per_huge_page, void (*process_subpage)(unsigned long addr, int idx, void *arg), void *arg) { int i, n, base, l; unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); /* Process target subpage last to keep its cache lines hot */ might_sleep(); n = (addr_hint - addr) / PAGE_SIZE; if (2 * n <= pages_per_huge_page) { /* If target subpage in first half of huge page */ base = 0; l = n; /* Process subpages at the end of huge page */ for (i = pages_per_huge_page - 1; i >= 2 * n; i--) { cond_resched(); process_subpage(addr + i * PAGE_SIZE, i, arg); } } else { /* If target subpage in second half of huge page */ base = pages_per_huge_page - 2 * (pages_per_huge_page - n); l = pages_per_huge_page - n; /* Process subpages at the begin of huge page */ for (i = 0; i < base; i++) { cond_resched(); process_subpage(addr + i * PAGE_SIZE, i, arg); } } /* * Process remaining subpages in left-right-left-right pattern * towards the target subpage */ for (i = 0; i < l; i++) { int left_idx = base + i; int right_idx = base + 2 * l - 1 - i; cond_resched(); process_subpage(addr + left_idx * PAGE_SIZE, left_idx, arg); cond_resched(); process_subpage(addr + right_idx * PAGE_SIZE, right_idx, arg); } } static void clear_gigantic_page(struct page *page, unsigned long addr, unsigned int pages_per_huge_page) { int i; struct page *p = page; might_sleep(); for (i = 0; i < pages_per_huge_page; i++, p = mem_map_next(p, page, i)) { cond_resched(); clear_user_highpage(p, addr + i * PAGE_SIZE); } } static void clear_subpage(unsigned long addr, int idx, void *arg) { struct page *page = arg; clear_user_highpage(page + idx, addr); } void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page) { unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { clear_gigantic_page(page, addr, pages_per_huge_page); return; } process_huge_page(addr_hint, pages_per_huge_page, clear_subpage, page); } static void copy_user_gigantic_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma, unsigned int pages_per_huge_page) { int i; struct page *dst_base = dst; struct page *src_base = src; for (i = 0; i < pages_per_huge_page; ) { cond_resched(); copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); i++; dst = mem_map_next(dst, dst_base, i); src = mem_map_next(src, src_base, i); } } struct copy_subpage_arg { struct page *dst; struct page *src; struct vm_area_struct *vma; }; static void copy_subpage(unsigned long addr, int idx, void *arg) { struct copy_subpage_arg *copy_arg = arg; copy_user_highpage(copy_arg->dst + idx, copy_arg->src + idx, addr, copy_arg->vma); } void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr_hint, struct vm_area_struct *vma, unsigned int pages_per_huge_page) { unsigned long addr = addr_hint & ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); struct copy_subpage_arg arg = { .dst = dst, .src = src, .vma = vma, }; if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { copy_user_gigantic_page(dst, src, addr, vma, pages_per_huge_page); return; } process_huge_page(addr_hint, pages_per_huge_page, copy_subpage, &arg); } long copy_huge_page_from_user(struct page *dst_page, const void __user *usr_src, unsigned int pages_per_huge_page, bool allow_pagefault) { void *src = (void *)usr_src; void *page_kaddr; unsigned long i, rc = 0; unsigned long ret_val = pages_per_huge_page * PAGE_SIZE; struct page *subpage = dst_page; for (i = 0; i < pages_per_huge_page; i++, subpage = mem_map_next(subpage, dst_page, i)) { if (allow_pagefault) page_kaddr = kmap(subpage); else page_kaddr = kmap_atomic(subpage); rc = copy_from_user(page_kaddr, (const void __user *)(src + i * PAGE_SIZE), PAGE_SIZE); if (allow_pagefault) kunmap(subpage); else kunmap_atomic(page_kaddr); ret_val -= (PAGE_SIZE - rc); if (rc) break; flush_dcache_page(subpage); cond_resched(); } return ret_val; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ #if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS static struct kmem_cache *page_ptl_cachep; void __init ptlock_cache_init(void) { page_ptl_cachep = kmem_cache_create("page->ptl", sizeof(spinlock_t), 0, SLAB_PANIC, NULL); } bool ptlock_alloc(struct page *page) { spinlock_t *ptl; ptl = kmem_cache_alloc(page_ptl_cachep, GFP_KERNEL); if (!ptl) return false; page->ptl = ptl; return true; } void ptlock_free(struct page *page) { kmem_cache_free(page_ptl_cachep, page->ptl); } #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/open.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/string.h> #include <linux/mm.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fsnotify.h> #include <linux/module.h> #include <linux/tty.h> #include <linux/namei.h> #include <linux/backing-dev.h> #include <linux/capability.h> #include <linux/securebits.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/rcupdate.h> #include <linux/audit.h> #include <linux/falloc.h> #include <linux/fs_struct.h> #include <linux/ima.h> #include <linux/dnotify.h> #include <linux/compat.h> #include "internal.h" int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, struct file *filp) { int ret; struct iattr newattrs; /* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */ if (length < 0) return -EINVAL; newattrs.ia_size = length; newattrs.ia_valid = ATTR_SIZE | time_attrs; if (filp) { newattrs.ia_file = filp; newattrs.ia_valid |= ATTR_FILE; } /* Remove suid, sgid, and file capabilities on truncate too */ ret = dentry_needs_remove_privs(dentry); if (ret < 0) return ret; if (ret) newattrs.ia_valid |= ret | ATTR_FORCE; inode_lock(dentry->d_inode); /* Note any delegations or leases have already been broken: */ ret = notify_change(dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); return ret; } long vfs_truncate(const struct path *path, loff_t length) { struct inode *inode; long error; inode = path->dentry->d_inode; /* For directories it's -EISDIR, for other non-regulars - -EINVAL */ if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode)) return -EINVAL; error = mnt_want_write(path->mnt); if (error) goto out; error = inode_permission(inode, MAY_WRITE); if (error) goto mnt_drop_write_and_out; error = -EPERM; if (IS_APPEND(inode)) goto mnt_drop_write_and_out; error = get_write_access(inode); if (error) goto mnt_drop_write_and_out; /* * Make sure that there are no leases. get_write_access() protects * against the truncate racing with a lease-granting setlease(). */ error = break_lease(inode, O_WRONLY); if (error) goto put_write_and_out; error = locks_verify_truncate(inode, NULL, length); if (!error) error = security_path_truncate(path); if (!error) error = do_truncate(path->dentry, length, 0, NULL); put_write_and_out: put_write_access(inode); mnt_drop_write_and_out: mnt_drop_write(path->mnt); out: return error; } EXPORT_SYMBOL_GPL(vfs_truncate); long do_sys_truncate(const char __user *pathname, loff_t length) { unsigned int lookup_flags = LOOKUP_FOLLOW; struct path path; int error; if (length < 0) /* sorry, but loff_t says... */ return -EINVAL; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (!error) { error = vfs_truncate(&path, length); path_put(&path); } if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE2(truncate, const char __user *, path, long, length) { return do_sys_truncate(path, length); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length) { return do_sys_truncate(path, length); } #endif long do_sys_ftruncate(unsigned int fd, loff_t length, int small) { struct inode *inode; struct dentry *dentry; struct fd f; int error; error = -EINVAL; if (length < 0) goto out; error = -EBADF; f = fdget(fd); if (!f.file) goto out; /* explicitly opened as large or we are on 64-bit box */ if (f.file->f_flags & O_LARGEFILE) small = 0; dentry = f.file->f_path.dentry; inode = dentry->d_inode; error = -EINVAL; if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE)) goto out_putf; error = -EINVAL; /* Cannot ftruncate over 2^31 bytes without large file support */ if (small && length > MAX_NON_LFS) goto out_putf; error = -EPERM; /* Check IS_APPEND on real upper inode */ if (IS_APPEND(file_inode(f.file))) goto out_putf; sb_start_write(inode->i_sb); error = locks_verify_truncate(inode, f.file, length); if (!error) error = security_path_truncate(&f.file->f_path); if (!error) error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file); sb_end_write(inode->i_sb); out_putf: fdput(f); out: return error; } SYSCALL_DEFINE2(ftruncate, unsigned int, fd, off_t, length) { return do_sys_ftruncate(fd, length, 1); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_off_t, length) { return do_sys_ftruncate(fd, length, 1); } #endif /* LFS versions of truncate are only needed on 32 bit machines */ #if BITS_PER_LONG == 32 SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length) { return do_sys_truncate(path, length); } SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length) { return do_sys_ftruncate(fd, length, 0); } #endif /* BITS_PER_LONG == 32 */ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); long ret; if (offset < 0 || len <= 0) return -EINVAL; /* Return error if mode is not supported */ if (mode & ~FALLOC_FL_SUPPORTED_MASK) return -EOPNOTSUPP; /* Punch hole and zero range are mutually exclusive */ if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) == (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) return -EOPNOTSUPP; /* Punch hole must have keep size set */ if ((mode & FALLOC_FL_PUNCH_HOLE) && !(mode & FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; /* Collapse range should only be used exclusively. */ if ((mode & FALLOC_FL_COLLAPSE_RANGE) && (mode & ~FALLOC_FL_COLLAPSE_RANGE)) return -EINVAL; /* Insert range should only be used exclusively. */ if ((mode & FALLOC_FL_INSERT_RANGE) && (mode & ~FALLOC_FL_INSERT_RANGE)) return -EINVAL; /* Unshare range should only be used with allocate mode. */ if ((mode & FALLOC_FL_UNSHARE_RANGE) && (mode & ~(FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE))) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; /* * We can only allow pure fallocate on append only files */ if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode)) return -EPERM; if (IS_IMMUTABLE(inode)) return -EPERM; /* * We cannot allow any fallocate operation on an active swapfile */ if (IS_SWAPFILE(inode)) return -ETXTBSY; /* * Revalidate the write permissions, in case security policy has * changed since the files were opened. */ ret = security_file_permission(file, MAY_WRITE); if (ret) return ret; if (S_ISFIFO(inode->i_mode)) return -ESPIPE; if (S_ISDIR(inode->i_mode)) return -EISDIR; if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -ENODEV; /* Check for wrap through zero too */ if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0)) return -EFBIG; if (!file->f_op->fallocate) return -EOPNOTSUPP; file_start_write(file); ret = file->f_op->fallocate(file, mode, offset, len); /* * Create inotify and fanotify events. * * To keep the logic simple always create events if fallocate succeeds. * This implies that events are even created if the file size remains * unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE. */ if (ret == 0) fsnotify_modify(file); file_end_write(file); return ret; } EXPORT_SYMBOL_GPL(vfs_fallocate); int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len) { struct fd f = fdget(fd); int error = -EBADF; if (f.file) { error = vfs_fallocate(f.file, mode, offset, len); fdput(f); } return error; } SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) { return ksys_fallocate(fd, mode, offset, len); } /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and * switching the fsuid/fsgid around to the real ones. */ static const struct cred *access_override_creds(void) { const struct cred *old_cred; struct cred *override_cred; override_cred = prepare_creds(); if (!override_cred) return NULL; override_cred->fsuid = override_cred->uid; override_cred->fsgid = override_cred->gid; if (!issecure(SECURE_NO_SETUID_FIXUP)) { /* Clear the capabilities if we switch to a non-root user */ kuid_t root_uid = make_kuid(override_cred->user_ns, 0); if (!uid_eq(override_cred->uid, root_uid)) cap_clear(override_cred->cap_effective); else override_cred->cap_effective = override_cred->cap_permitted; } /* * The new set of credentials can *only* be used in * task-synchronous circumstances, and does not need * RCU freeing, unless somebody then takes a separate * reference to it. * * NOTE! This is _only_ true because this credential * is used purely for override_creds() that installs * it as the subjective cred. Other threads will be * accessing ->real_cred, not the subjective cred. * * If somebody _does_ make a copy of this (using the * 'get_current_cred()' function), that will clear the * non_rcu field, because now that other user may be * expecting RCU freeing. But normal thread-synchronous * cred accesses will keep things non-RCY. */ override_cred->non_rcu = 1; old_cred = override_creds(override_cred); /* override_cred() gets its own ref */ put_cred(override_cred); return old_cred; } static long do_faccessat(int dfd, const char __user *filename, int mode, int flags) { struct path path; struct inode *inode; int res; unsigned int lookup_flags = LOOKUP_FOLLOW; const struct cred *old_cred = NULL; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ return -EINVAL; if (flags & ~(AT_EACCESS | AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) return -EINVAL; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (!(flags & AT_EACCESS)) { old_cred = access_override_creds(); if (!old_cred) return -ENOMEM; } retry: res = user_path_at(dfd, filename, lookup_flags, &path); if (res) goto out; inode = d_backing_inode(path.dentry); if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) { /* * MAY_EXEC on regular files is denied if the fs is mounted * with the "noexec" flag. */ res = -EACCES; if (path_noexec(&path)) goto out_path_release; } res = inode_permission(inode, mode | MAY_ACCESS); /* SuS v2 requires we report a read only fs too */ if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) goto out_path_release; /* * This is a rare case where using __mnt_is_readonly() * is OK without a mnt_want/drop_write() pair. Since * no actual write to the fs is performed here, we do * not need to telegraph to that to anyone. * * By doing this, we accept that this access is * inherently racy and know that the fs may change * state before we even see this result. */ if (__mnt_is_readonly(path.mnt)) res = -EROFS; out_path_release: path_put(&path); if (retry_estale(res, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: if (old_cred) revert_creds(old_cred); return res; } SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) { return do_faccessat(dfd, filename, mode, 0); } SYSCALL_DEFINE4(faccessat2, int, dfd, const char __user *, filename, int, mode, int, flags) { return do_faccessat(dfd, filename, mode, flags); } SYSCALL_DEFINE2(access, const char __user *, filename, int, mode) { return do_faccessat(AT_FDCWD, filename, mode, 0); } SYSCALL_DEFINE1(chdir, const char __user *, filename) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; retry: error = user_path_at(AT_FDCWD, filename, lookup_flags, &path); if (error) goto out; error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; set_fs_pwd(current->fs, &path); dput_and_out: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct fd f = fdget_raw(fd); int error; error = -EBADF; if (!f.file) goto out; error = -ENOTDIR; if (!d_can_lookup(f.file->f_path.dentry)) goto out_putf; error = file_permission(f.file, MAY_EXEC | MAY_CHDIR); if (!error) set_fs_pwd(current->fs, &f.file->f_path); out_putf: fdput(f); out: return error; } SYSCALL_DEFINE1(chroot, const char __user *, filename) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; retry: error = user_path_at(AT_FDCWD, filename, lookup_flags, &path); if (error) goto out; error = path_permission(&path, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; error = -EPERM; if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT)) goto dput_and_out; error = security_path_chroot(&path); if (error) goto dput_and_out; set_fs_root(current->fs, &path); error = 0; dput_and_out: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } int chmod_common(const struct path *path, umode_t mode) { struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; struct iattr newattrs; int error; error = mnt_want_write(path->mnt); if (error) return error; retry_deleg: inode_lock(inode); error = security_path_chmod(path, mode); if (error) goto out_unlock; newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; error = notify_change(path->dentry, &newattrs, &delegated_inode); out_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(path->mnt); return error; } int vfs_fchmod(struct file *file, umode_t mode) { audit_file(file); return chmod_common(&file->f_path, mode); } SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) { struct fd f = fdget(fd); int err = -EBADF; if (f.file) { err = vfs_fchmod(f.file, mode); fdput(f); } return err; } static int do_fchmodat(int dfd, const char __user *filename, umode_t mode) { struct path path; int error; unsigned int lookup_flags = LOOKUP_FOLLOW; retry: error = user_path_at(dfd, filename, lookup_flags, &path); if (!error) { error = chmod_common(&path, mode); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } } return error; } SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode) { return do_fchmodat(dfd, filename, mode); } SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode) { return do_fchmodat(AT_FDCWD, filename, mode); } int chown_common(const struct path *path, uid_t user, gid_t group) { struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; int error; struct iattr newattrs; kuid_t uid; kgid_t gid; uid = make_kuid(current_user_ns(), user); gid = make_kgid(current_user_ns(), group); retry_deleg: newattrs.ia_valid = ATTR_CTIME; if (user != (uid_t) -1) { if (!uid_valid(uid)) return -EINVAL; newattrs.ia_valid |= ATTR_UID; newattrs.ia_uid = uid; } if (group != (gid_t) -1) { if (!gid_valid(gid)) return -EINVAL; newattrs.ia_valid |= ATTR_GID; newattrs.ia_gid = gid; } inode_lock(inode); if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV | setattr_should_drop_sgid(inode); error = security_path_chown(path, uid, gid); if (!error) error = notify_change(path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag) { struct path path; int error = -EINVAL; int lookup_flags; if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) goto out; lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; if (flag & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; retry: error = user_path_at(dfd, filename, lookup_flags, &path); if (error) goto out; error = mnt_want_write(path.mnt); if (error) goto out_release; error = chown_common(&path, user, group); mnt_drop_write(path.mnt); out_release: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out: return error; } SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag) { return do_fchownat(dfd, filename, user, group, flag); } SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) { return do_fchownat(AT_FDCWD, filename, user, group, 0); } SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) { return do_fchownat(AT_FDCWD, filename, user, group, AT_SYMLINK_NOFOLLOW); } int vfs_fchown(struct file *file, uid_t user, gid_t group) { int error; error = mnt_want_write_file(file); if (error) return error; audit_file(file); error = chown_common(&file->f_path, user, group); mnt_drop_write_file(file); return error; } int ksys_fchown(unsigned int fd, uid_t user, gid_t group) { struct fd f = fdget(fd); int error = -EBADF; if (f.file) { error = vfs_fchown(f.file, user, group); fdput(f); } return error; } SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) { return ksys_fchown(fd, user, group); } static int do_dentry_open(struct file *f, struct inode *inode, int (*open)(struct inode *, struct file *)) { static const struct file_operations empty_fops = {}; int error; path_get(&f->f_path); f->f_inode = inode; f->f_mapping = inode->i_mapping; f->f_wb_err = filemap_sample_wb_err(f->f_mapping); f->f_sb_err = file_sample_sb_err(f); if (unlikely(f->f_flags & O_PATH)) { f->f_mode = FMODE_PATH | FMODE_OPENED; f->f_op = &empty_fops; return 0; } if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = get_write_access(inode); if (unlikely(error)) goto cleanup_file; error = __mnt_want_write(f->f_path.mnt); if (unlikely(error)) { put_write_access(inode); goto cleanup_file; } f->f_mode |= FMODE_WRITER; } /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */ if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)) f->f_mode |= FMODE_ATOMIC_POS; f->f_op = fops_get(inode->i_fop); if (WARN_ON(!f->f_op)) { error = -ENODEV; goto cleanup_all; } error = security_file_open(f); if (error) goto cleanup_all; error = break_lease(locks_inode(f), f->f_flags); if (error) goto cleanup_all; /* normally all 3 are set; ->open() can clear them if needed */ f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; if (!open) open = f->f_op->open; if (open) { error = open(inode, f); if (error) goto cleanup_all; } f->f_mode |= FMODE_OPENED; if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(inode); if ((f->f_mode & FMODE_READ) && likely(f->f_op->read || f->f_op->read_iter)) f->f_mode |= FMODE_CAN_READ; if ((f->f_mode & FMODE_WRITE) && likely(f->f_op->write || f->f_op->write_iter)) f->f_mode |= FMODE_CAN_WRITE; f->f_write_hint = WRITE_LIFE_NOT_SET; f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); /* NB: we're sure to have correct a_ops only after f_op->open */ if (f->f_flags & O_DIRECT) { if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO) return -EINVAL; } /* * XXX: Huge page cache doesn't support writing yet. Drop all page * cache for this file before processing writes. */ if ((f->f_mode & FMODE_WRITE) && filemap_nr_thps(inode->i_mapping)) truncate_pagecache(inode, 0); return 0; cleanup_all: if (WARN_ON_ONCE(error > 0)) error = -EINVAL; fops_put(f->f_op); if (f->f_mode & FMODE_WRITER) { put_write_access(inode); __mnt_drop_write(f->f_path.mnt); } cleanup_file: path_put(&f->f_path); f->f_path.mnt = NULL; f->f_path.dentry = NULL; f->f_inode = NULL; return error; } /** * finish_open - finish opening a file * @file: file pointer * @dentry: pointer to dentry * @open: open callback * @opened: state of open * * This can be used to finish opening a file passed to i_op->atomic_open(). * * If the open callback is set to NULL, then the standard f_op->open() * filesystem callback is substituted. * * NB: the dentry reference is _not_ consumed. If, for example, the dentry is * the return value of d_splice_alias(), then the caller needs to perform dput() * on it after finish_open(). * * Returns zero on success or -errno if the open failed. */ int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)) { BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */ file->f_path.dentry = dentry; return do_dentry_open(file, d_backing_inode(dentry), open); } EXPORT_SYMBOL(finish_open); /** * finish_no_open - finish ->atomic_open() without opening the file * * @file: file pointer * @dentry: dentry or NULL (as returned from ->lookup()) * * This can be used to set the result of a successful lookup in ->atomic_open(). * * NB: unlike finish_open() this function does consume the dentry reference and * the caller need not dput() it. * * Returns "0" which must be the return value of ->atomic_open() after having * called this function. */ int finish_no_open(struct file *file, struct dentry *dentry) { file->f_path.dentry = dentry; return 0; } EXPORT_SYMBOL(finish_no_open); char *file_path(struct file *filp, char *buf, int buflen) { return d_path(&filp->f_path, buf, buflen); } EXPORT_SYMBOL(file_path); /** * vfs_open - open the file at the given path * @path: path to open * @file: newly allocated file with f_flag initialized * @cred: credentials to use */ int vfs_open(const struct path *path, struct file *file) { file->f_path = *path; return do_dentry_open(file, d_backing_inode(path->dentry), NULL); } struct file *dentry_open(const struct path *path, int flags, const struct cred *cred) { int error; struct file *f; validate_creds(cred); /* We must always pass in a valid mount pointer. */ BUG_ON(!path->mnt); f = alloc_empty_file(flags, cred); if (!IS_ERR(f)) { error = vfs_open(path, f); if (error) { fput(f); f = ERR_PTR(error); } } return f; } EXPORT_SYMBOL(dentry_open); /** * dentry_create - Create and open a file * @path: path to create * @flags: O_ flags * @mode: mode bits for new file * @cred: credentials to use * * Caller must hold the parent directory's lock, and have prepared * a negative dentry, placed in @path->dentry, for the new file. * * Caller sets @path->mnt to the vfsmount of the filesystem where * the new file is to be created. The parent directory and the * negative dentry must reside on the same filesystem instance. * * On success, returns a "struct file *". Otherwise a ERR_PTR * is returned. */ struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred) { struct file *f; int error; validate_creds(cred); f = alloc_empty_file(flags, cred); if (IS_ERR(f)) return f; error = vfs_create(d_inode(path->dentry->d_parent), path->dentry, mode, true); if (!error) error = vfs_open(path, f); if (unlikely(error)) { fput(f); return ERR_PTR(error); } return f; } EXPORT_SYMBOL(dentry_create); struct file *open_with_fake_path(const struct path *path, int flags, struct inode *inode, const struct cred *cred) { struct file *f = alloc_empty_file_noaccount(flags, cred); if (!IS_ERR(f)) { int error; f->f_path = *path; error = do_dentry_open(f, inode, NULL); if (error) { fput(f); f = ERR_PTR(error); } } return f; } EXPORT_SYMBOL(open_with_fake_path); #define WILL_CREATE(flags) (flags & (O_CREAT | __O_TMPFILE)) #define O_PATH_FLAGS (O_DIRECTORY | O_NOFOLLOW | O_PATH | O_CLOEXEC) inline struct open_how build_open_how(int flags, umode_t mode) { struct open_how how = { .flags = flags & VALID_OPEN_FLAGS, .mode = mode & S_IALLUGO, }; /* O_PATH beats everything else. */ if (how.flags & O_PATH) how.flags &= O_PATH_FLAGS; /* Modes should only be set for create-like flags. */ if (!WILL_CREATE(how.flags)) how.mode = 0; return how; } inline int build_open_flags(const struct open_how *how, struct open_flags *op) { u64 flags = how->flags; u64 strip = FMODE_NONOTIFY | O_CLOEXEC; int lookup_flags = 0; int acc_mode = ACC_MODE(flags); BUILD_BUG_ON_MSG(upper_32_bits(VALID_OPEN_FLAGS), "struct open_flags doesn't yet handle flags > 32 bits"); /* * Strip flags that either shouldn't be set by userspace like * FMODE_NONOTIFY or that aren't relevant in determining struct * open_flags like O_CLOEXEC. */ flags &= ~strip; /* * Older syscalls implicitly clear all of the invalid flags or argument * values before calling build_open_flags(), but openat2(2) checks all * of its arguments. */ if (flags & ~VALID_OPEN_FLAGS) return -EINVAL; if (how->resolve & ~VALID_RESOLVE_FLAGS) return -EINVAL; /* Scoping flags are mutually exclusive. */ if ((how->resolve & RESOLVE_BENEATH) && (how->resolve & RESOLVE_IN_ROOT)) return -EINVAL; /* Deal with the mode. */ if (WILL_CREATE(flags)) { if (how->mode & ~S_IALLUGO) return -EINVAL; op->mode = how->mode | S_IFREG; } else { if (how->mode != 0) return -EINVAL; op->mode = 0; } /* * In order to ensure programs get explicit errors when trying to use * O_TMPFILE on old kernels, O_TMPFILE is implemented such that it * looks like (O_DIRECTORY|O_RDWR & ~O_CREAT) to old kernels. But we * have to require userspace to explicitly set it. */ if (flags & __O_TMPFILE) { if ((flags & O_TMPFILE_MASK) != O_TMPFILE) return -EINVAL; if (!(acc_mode & MAY_WRITE)) return -EINVAL; } if (flags & O_PATH) { /* O_PATH only permits certain other flags to be set. */ if (flags & ~O_PATH_FLAGS) return -EINVAL; acc_mode = 0; } /* * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only * check for O_DSYNC if the need any syncing at all we enforce it's * always set instead of having to deal with possibly weird behaviour * for malicious applications setting only __O_SYNC. */ if (flags & __O_SYNC) flags |= O_DSYNC; op->open_flag = flags; /* O_TRUNC implies we need access checks for write permissions */ if (flags & O_TRUNC) acc_mode |= MAY_WRITE; /* Allow the LSM permission hook to distinguish append access from general write access. */ if (flags & O_APPEND) acc_mode |= MAY_APPEND; op->acc_mode = acc_mode; op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN; if (flags & O_CREAT) { op->intent |= LOOKUP_CREATE; if (flags & O_EXCL) { op->intent |= LOOKUP_EXCL; flags |= O_NOFOLLOW; } } if (flags & O_DIRECTORY) lookup_flags |= LOOKUP_DIRECTORY; if (!(flags & O_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (how->resolve & RESOLVE_NO_XDEV) lookup_flags |= LOOKUP_NO_XDEV; if (how->resolve & RESOLVE_NO_MAGICLINKS) lookup_flags |= LOOKUP_NO_MAGICLINKS; if (how->resolve & RESOLVE_NO_SYMLINKS) lookup_flags |= LOOKUP_NO_SYMLINKS; if (how->resolve & RESOLVE_BENEATH) lookup_flags |= LOOKUP_BENEATH; if (how->resolve & RESOLVE_IN_ROOT) lookup_flags |= LOOKUP_IN_ROOT; if (how->resolve & RESOLVE_CACHED) { /* Don't bother even trying for create/truncate/tmpfile open */ if (flags & (O_TRUNC | O_CREAT | __O_TMPFILE)) return -EAGAIN; lookup_flags |= LOOKUP_CACHED; } op->lookup_flags = lookup_flags; return 0; } /** * file_open_name - open file and return file pointer * * @name: struct filename containing path to open * @flags: open flags as per the open(2) second argument * @mode: mode for the new file if O_CREAT is set, else ignored * * This is the helper to open a file from kernelspace if you really * have to. But in generally you should not do this, so please move * along, nothing to see here.. */ struct file *file_open_name(struct filename *name, int flags, umode_t mode) { struct open_flags op; struct open_how how = build_open_how(flags, mode); int err = build_open_flags(&how, &op); if (err) return ERR_PTR(err); return do_filp_open(AT_FDCWD, name, &op); } /** * filp_open - open file and return file pointer * * @filename: path to open * @flags: open flags as per the open(2) second argument * @mode: mode for the new file if O_CREAT is set, else ignored * * This is the helper to open a file from kernelspace if you really * have to. But in generally you should not do this, so please move * along, nothing to see here.. */ struct file *filp_open(const char *filename, int flags, umode_t mode) { struct filename *name = getname_kernel(filename); struct file *file = ERR_CAST(name); if (!IS_ERR(name)) { file = file_open_name(name, flags, mode); putname(name); } return file; } EXPORT_SYMBOL(filp_open); struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt, const char *filename, int flags, umode_t mode) { struct open_flags op; struct open_how how = build_open_how(flags, mode); int err = build_open_flags(&how, &op); if (err) return ERR_PTR(err); return do_file_open_root(dentry, mnt, filename, &op); } EXPORT_SYMBOL(file_open_root); static long do_sys_openat2(int dfd, const char __user *filename, struct open_how *how) { struct open_flags op; int fd = build_open_flags(how, &op); struct filename *tmp; if (fd) return fd; tmp = getname(filename); if (IS_ERR(tmp)) return PTR_ERR(tmp); fd = get_unused_fd_flags(how->flags); if (fd >= 0) { struct file *f = do_filp_open(dfd, tmp, &op); if (IS_ERR(f)) { put_unused_fd(fd); fd = PTR_ERR(f); } else { fsnotify_open(f); fd_install(fd, f); } } putname(tmp); return fd; } long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode) { struct open_how how = build_open_how(flags, mode); return do_sys_openat2(dfd, filename, &how); } SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(AT_FDCWD, filename, flags, mode); } SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(dfd, filename, flags, mode); } SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename, struct open_how __user *, how, size_t, usize) { int err; struct open_how tmp; BUILD_BUG_ON(sizeof(struct open_how) < OPEN_HOW_SIZE_VER0); BUILD_BUG_ON(sizeof(struct open_how) != OPEN_HOW_SIZE_LATEST); if (unlikely(usize < OPEN_HOW_SIZE_VER0)) return -EINVAL; if (unlikely(usize > PAGE_SIZE)) return -E2BIG; err = copy_struct_from_user(&tmp, sizeof(tmp), how, usize); if (err) return err; /* O_LARGEFILE is only allowed for non-O_PATH. */ if (!(tmp.flags & O_PATH) && force_o_largefile()) tmp.flags |= O_LARGEFILE; return do_sys_openat2(dfd, filename, &tmp); } #ifdef CONFIG_COMPAT /* * Exactly like sys_open(), except that it doesn't set the * O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { return do_sys_open(AT_FDCWD, filename, flags, mode); } /* * Exactly like sys_openat(), except that it doesn't set the * O_LARGEFILE flag. */ COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { return do_sys_open(dfd, filename, flags, mode); } #endif #ifndef __alpha__ /* * For backward compatibility? Maybe this should be moved * into arch/i386 instead? */ SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode) { int flags = O_CREAT | O_WRONLY | O_TRUNC; if (force_o_largefile()) flags |= O_LARGEFILE; return do_sys_open(AT_FDCWD, pathname, flags, mode); } #endif /* * "id" is the POSIX thread ID. We use the * files pointer for this.. */ int filp_close(struct file *filp, fl_owner_t id) { int retval = 0; if (!file_count(filp)) { printk(KERN_ERR "VFS: Close: file count is 0\n"); return 0; } if (filp->f_op->flush) retval = filp->f_op->flush(filp, id); if (likely(!(filp->f_mode & FMODE_PATH))) { dnotify_flush(filp, id); locks_remove_posix(filp, id); } fput(filp); return retval; } EXPORT_SYMBOL(filp_close); /* * Careful here! We test whether the file pointer is NULL before * releasing the fd. This ensures that one clone task can't release * an fd while another clone is opening it. */ SYSCALL_DEFINE1(close, unsigned int, fd) { int retval = close_fd(fd); /* can't restart close syscall because file table entry was cleared */ if (unlikely(retval == -ERESTARTSYS || retval == -ERESTARTNOINTR || retval == -ERESTARTNOHAND || retval == -ERESTART_RESTARTBLOCK)) retval = -EINTR; return retval; } /** * close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: reserved for future extensions * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. * Currently, errors to close a given file descriptor are ignored. */ SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd, unsigned int, flags) { return __close_range(fd, max_fd, flags); } /* * This routine simulates a hangup on the tty, to arrange that users * are given clean terminals at login time. */ SYSCALL_DEFINE0(vhangup) { if (capable(CAP_SYS_TTY_CONFIG)) { tty_vhangup_self(); return 0; } return -EPERM; } /* * Called when an inode is about to be open. * We use this to disallow opening large files on 32bit systems if * the caller didn't specify O_LARGEFILE. On 64bit systems we force * on this flag in sys_open. */ int generic_file_open(struct inode * inode, struct file * filp) { if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS) return -EOVERFLOW; return 0; } EXPORT_SYMBOL(generic_file_open); /* * This is used by subsystems that don't want seekable * file descriptors. The function is not supposed to ever fail, the only * reason it returns an 'int' and not 'void' is so that it can be plugged * directly into file_operations structure. */ int nonseekable_open(struct inode *inode, struct file *filp) { filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE); return 0; } EXPORT_SYMBOL(nonseekable_open); /* * stream_open is used by subsystems that want stream-like file descriptors. * Such file descriptors are not seekable and don't have notion of position * (file.f_pos is always 0 and ppos passed to .read()/.write() is always NULL). * Contrary to file descriptors of other regular files, .read() and .write() * can run simultaneously. * * stream_open never fails and is marked to return int so that it could be * directly used as file_operations.open . */ int stream_open(struct inode *inode, struct file *filp) { filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); filp->f_mode |= FMODE_STREAM; return 0; } EXPORT_SYMBOL(stream_open); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 | /* * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H #include <uapi/linux/perf_event.h> #include <uapi/linux/bpf_perf_event.h> /* * Kernel-internal data types and definitions: */ #ifdef CONFIG_PERF_EVENTS # include <asm/perf_event.h> # include <asm/local64.h> #endif struct perf_guest_info_callbacks { int (*is_in_guest)(void); int (*is_user_mode)(void); unsigned long (*get_guest_ip)(void); void (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT #include <asm/hw_breakpoint.h> #endif #include <linux/list.h> #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/fs.h> #include <linux/pid_namespace.h> #include <linux/workqueue.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/irq_work.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/atomic.h> #include <linux/sysfs.h> #include <linux/perf_regs.h> #include <linux/cgroup.h> #include <linux/refcount.h> #include <linux/security.h> #include <asm/local.h> struct perf_callchain_entry { __u64 nr; __u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { struct perf_callchain_entry *entry; u32 max_stack; u32 nr; short contexts; bool contexts_maxed; }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, unsigned long off, unsigned long len); struct perf_raw_frag { union { struct perf_raw_frag *next; unsigned long pad; }; perf_copy_f copy; void *data; u32 size; } __packed; struct perf_raw_record { struct perf_raw_frag frag; u32 size; }; /* * branch stack layout: * nr: number of taken branches stored in entries[] * hw_idx: The low level index of raw branch records * for the most recent branch. * -1ULL means invalid/unknown. * * Note that nr can vary from sample to sample * branches (to, from) are stored from most recent * to least recent, i.e., entries[0] contains the most * recent branch. * The entries[] is an abstraction of raw branch records, * which may not be stored in age order in HW, e.g. Intel LBR. * The hw_idx is to expose the low level index of raw * branch record for the most recent branch aka entries[0]. * The hw_idx index is between -1 (unknown) and max depth, * which can be retrieved in /sys/devices/cpu/caps/branches. * For the architectures whose raw branch records are * already stored in age order, the hw_idx should be 0. */ struct perf_branch_stack { __u64 nr; __u64 hw_idx; struct perf_branch_entry entries[]; }; struct task_struct; /* * extra PMU register associated with an event */ struct hw_perf_event_extra { u64 config; /* register value */ unsigned int reg; /* register address or index */ int alloc; /* extra register already allocated */ int idx; /* index in shared_regs->regs[] */ }; /** * struct hw_perf_event - performance event hardware details: */ struct hw_perf_event { #ifdef CONFIG_PERF_EVENTS union { struct { /* hardware */ u64 config; u64 last_tag; unsigned long config_base; unsigned long event_base; int event_base_rdpmc; int idx; int last_cpu; int flags; struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; struct { /* software */ struct hrtimer hrtimer; }; struct { /* tracepoint */ /* for tp_event->class */ struct list_head tp_list; }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ /* * Crufty hack to avoid the chicken and egg * problem hw_breakpoint has with context * creation and event initalization. */ struct arch_hw_breakpoint info; struct list_head bp_list; }; #endif struct { /* amd_iommu */ u8 iommu_bank; u8 iommu_cntr; u16 padding; u64 conf; u64 conf1; }; }; /* * If the event is a per task event, this will point to the task in * question. See the comment in perf_event_alloc(). */ struct task_struct *target; /* * PMU would store hardware filter configuration * here. */ void *addr_filters; /* Last sync'ed generation of filters */ unsigned long addr_filters_gen; /* * hw_perf_event::state flags; used to track the PERF_EF_* state. */ #define PERF_HES_STOPPED 0x01 /* the counter is stopped */ #define PERF_HES_UPTODATE 0x02 /* event->count up-to-date */ #define PERF_HES_ARCH 0x04 int state; /* * The last observed hardware counter value, updated with a * local64_cmpxchg() such that pmu::read() can be called nested. */ local64_t prev_count; /* * The period to start the next sample with. */ u64 sample_period; union { struct { /* Sampling */ /* * The period we started this sample with. */ u64 last_period; /* * However much is left of the current period; * note that this is a full 64bit value and * allows for generation of periods longer * than hardware might allow. */ local64_t period_left; }; struct { /* Topdown events counting for context switch */ u64 saved_metric; u64 saved_slots; }; }; /* * State for throttling the event, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 interrupts_seq; u64 interrupts; /* * State for freq target events, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 freq_time_stamp; u64 freq_count_stamp; #endif }; struct perf_event; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ #define PERF_PMU_TXN_ADD 0x1 /* txn to add/schedule event on PMU */ #define PERF_PMU_TXN_READ 0x2 /* txn to read event group from PMU */ /** * pmu::capabilities flags */ #define PERF_PMU_CAP_NO_INTERRUPT 0x01 #define PERF_PMU_CAP_NO_NMI 0x02 #define PERF_PMU_CAP_AUX_NO_SG 0x04 #define PERF_PMU_CAP_EXTENDED_REGS 0x08 #define PERF_PMU_CAP_EXCLUSIVE 0x10 #define PERF_PMU_CAP_ITRACE 0x20 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40 #define PERF_PMU_CAP_NO_EXCLUDE 0x80 #define PERF_PMU_CAP_AUX_OUTPUT 0x100 struct perf_output_handle; /** * struct pmu - generic performance monitoring unit */ struct pmu { struct list_head entry; struct module *module; struct device *dev; const struct attribute_group **attr_groups; const struct attribute_group **attr_update; const char *name; int type; /* * various common per-pmu feature flags */ int capabilities; int __percpu *pmu_disable_count; struct perf_cpu_context __percpu *pmu_cpu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; /* number of address filters this PMU can do */ unsigned int nr_addr_filters; /* * Fully disable/enable this PMU, can be used to protect from the PMI * as well as for lazy/batch writing of the MSRs. */ void (*pmu_enable) (struct pmu *pmu); /* optional */ void (*pmu_disable) (struct pmu *pmu); /* optional */ /* * Try and initialize the event for this PMU. * * Returns: * -ENOENT -- @event is not for this PMU * * -ENODEV -- @event is for this PMU but PMU not present * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * * Other error return values are allowed. */ int (*event_init) (struct perf_event *event); /* * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are * matching hw_perf_event::state flags. */ #define PERF_EF_START 0x01 /* start the counter when adding */ #define PERF_EF_RELOAD 0x02 /* reload the counter when starting */ #define PERF_EF_UPDATE 0x04 /* update the counter when stopping */ /* * Adds/Removes a counter to/from the PMU, can be done inside a * transaction, see the ->*_txn() methods. * * The add/del callbacks will reserve all hardware resources required * to service the event, this includes any counter constraint * scheduling etc. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on. * * ->add() called without PERF_EF_START should result in the same state * as ->add() followed by ->stop(). * * ->del() must always PERF_EF_UPDATE stop an event. If it calls * ->stop() that must deal with already being stopped without * PERF_EF_UPDATE. */ int (*add) (struct perf_event *event, int flags); void (*del) (struct perf_event *event, int flags); /* * Starts/Stops a counter present on the PMU. * * The PMI handler should stop the counter when perf_event_overflow() * returns !0. ->start() will be used to continue. * * Also used to change the sample period. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on -- will be called from NMI context with the PMU generates * NMIs. * * ->stop() with PERF_EF_UPDATE will read the counter and update * period/count values like ->read() would. * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); /* * Updates the counter value of the event. * * For sampling capable PMUs this will also update the software period * hw_perf_event::period_left field. */ void (*read) (struct perf_event *event); /* * Group events scheduling is treated as a transaction, add * group events as a whole and perform one schedulability test. * If the test fails, roll back the whole group * * Start the transaction, after this ->add() doesn't need to * do schedulability tests. * * Optional. */ void (*start_txn) (struct pmu *pmu, unsigned int txn_flags); /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. * * Optional. */ int (*commit_txn) (struct pmu *pmu); /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. * * Optional. */ void (*cancel_txn) (struct pmu *pmu); /* * Will return the value for perf_event_mmap_page::index for this event, * if no implementation is provided it will default to: event->hw.idx + 1. */ int (*event_idx) (struct perf_event *event); /*optional */ /* * context-switches callback */ void (*sched_task) (struct perf_event_context *ctx, bool sched_in); /* * Kmem cache of PMU specific data */ struct kmem_cache *task_ctx_cache; /* * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data) * can be synchronized using this function. See Intel LBR callstack support * implementation and Perf core context switch handling callbacks for usage * examples. */ void (*swap_task_ctx) (struct perf_event_context *prev, struct perf_event_context *next); /* optional */ /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, int nr_pages, bool overwrite); /* optional */ /* * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */ /* * Take a snapshot of the AUX buffer without touching the event * state, so that preempting ->start()/->stop() callbacks does * not interfere with their logic. Called in PMI context. * * Returns the size of AUX data copied to the output handle. * * Optional. */ long (*snapshot_aux) (struct perf_event *event, struct perf_output_handle *handle, unsigned long size); /* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the * supplied filters are valid, -errno otherwise. * * Runs in the context of the ioctl()ing process and is not serialized * with the rest of the PMU callbacks. */ int (*addr_filters_validate) (struct list_head *filters); /* optional */ /* * Synchronize address range filter configuration: * translate hw-agnostic filters into hardware configuration in * event::hw::addr_filters. * * Runs as a part of filter sync sequence that is done in ->start() * callback by calling perf_event_addr_filters_sync(). * * May (and should) traverse event::addr_filters::list, for which its * caller provides necessary serialization. */ void (*addr_filters_sync) (struct perf_event *event); /* optional */ /* * Check if event can be used for aux_output purposes for * events of this PMU. * * Runs from perf_event_open(). Should return 0 for "no match" * or non-zero for "match". */ int (*aux_output_match) (struct perf_event *event); /* optional */ /* * Filter events for PMU-specific reasons. */ int (*filter_match) (struct perf_event *event); /* optional */ /* * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { PERF_ADDR_FILTER_ACTION_STOP = 0, PERF_ADDR_FILTER_ACTION_START, PERF_ADDR_FILTER_ACTION_FILTER, }; /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop * * This is a hardware-agnostic filter configuration as specified by the user. */ struct perf_addr_filter { struct list_head entry; struct path path; unsigned long offset; unsigned long size; enum perf_addr_filter_action_t action; }; /** * struct perf_addr_filters_head - container for address range filters * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). */ struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; unsigned int nr_file_filters; }; struct perf_addr_filter_range { unsigned long start; unsigned long size; }; /** * enum perf_event_state - the states of an event: */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -4, PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, }; struct file; struct perf_sample_data; typedef void (*perf_overflow_handler_t)(struct perf_event *, struct perf_sample_data *, struct pt_regs *regs); /* * Event capabilities. For event_caps and groups caps. * * PERF_EV_CAP_SOFTWARE: Is a software event. * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read * from any CPU in the package where it is active. * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) struct swevent_hlist { struct hlist_head heads[SWEVENT_HLIST_SIZE]; struct rcu_head rcu_head; }; #define PERF_ATTACH_CONTEXT 0x01 #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 #define PERF_ATTACH_TASK_DATA 0x08 #define PERF_ATTACH_ITRACE 0x10 #define PERF_ATTACH_SCHED_CB 0x20 struct perf_cgroup; struct perf_buffer; struct pmu_event_list { raw_spinlock_t lock; struct list_head list; }; #define for_each_sibling_event(sibling, event) \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) /** * struct perf_event - performance event kernel representation: */ struct perf_event { #ifdef CONFIG_PERF_EVENTS /* * entry onto perf_event_context::event_list; * modifications require ctx->lock * RCU safe iterations. */ struct list_head event_entry; /* * Locked for modification by both ctx->mutex and ctx->lock; holding * either sufficies for read. */ struct list_head sibling_list; struct list_head active_list; /* * Node on the pinned or flexible tree located at the event context; */ struct rb_node group_node; u64 group_index; /* * We need storage to track the entries in perf_pmu_migrate_context; we * cannot use the event_entry because of RCU and we want to keep the * group in tact which avoids us using the other two entries. */ struct list_head migrate_entry; struct hlist_node hlist_entry; struct list_head active_entry; int nr_siblings; /* Not serialized. Only written during event initialization. */ int event_caps; /* The cumulative AND of all event_caps for events in this group. */ int group_caps; unsigned int group_generation; struct perf_event *group_leader; struct pmu *pmu; void *pmu_private; enum perf_event_state state; unsigned int attach_state; local64_t count; atomic64_t child_count; /* * These are the total time in nanoseconds that the event * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. */ u64 total_time_enabled; u64 total_time_running; u64 tstamp; struct perf_event_attr attr; u16 header_size; u16 id_header_size; u16 read_size; struct hw_perf_event hw; struct perf_event_context *ctx; atomic_long_t refcount; /* * These accumulate total time (in nanoseconds) that children * events have been enabled and running, respectively. */ atomic64_t child_total_time_enabled; atomic64_t child_total_time_running; /* * Protect attach/detach and child_list: */ struct mutex child_mutex; struct list_head child_list; struct perf_event *parent; int oncpu; int cpu; struct list_head owner_entry; struct task_struct *owner; /* mmap bits */ struct mutex mmap_mutex; atomic_t mmap_count; struct perf_buffer *rb; struct list_head rb_entry; unsigned long rcu_batches; int rcu_pending; /* poll related */ wait_queue_head_t waitq; struct fasync_struct *fasync; /* delayed work for NMIs and such */ int pending_wakeup; int pending_kill; int pending_disable; struct irq_work pending; atomic_t event_limit; /* address range filters */ struct perf_addr_filters_head addr_filters; /* vma address array for file-based filders */ struct perf_addr_filter_range *addr_filter_ranges; unsigned long addr_filters_gen; /* for aux_output events */ struct perf_event *aux_event; void (*destroy)(struct perf_event *); struct rcu_head rcu_head; struct pid_namespace *ns; u64 id; atomic64_t lost_samples; u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; #ifdef CONFIG_BPF_SYSCALL perf_overflow_handler_t orig_overflow_handler; struct bpf_prog *prog; #endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; struct event_filter *filter; #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; #endif #endif #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; /* cgroup event is attach to */ #endif #ifdef CONFIG_SECURITY void *security; #endif struct list_head sb_list; #endif /* CONFIG_PERF_EVENTS */ }; struct perf_event_groups { struct rb_root tree; u64 index; }; /** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */ struct perf_event_context { struct pmu *pmu; /* * Protect the states of the events in the list, * nr_active, and the list: */ raw_spinlock_t lock; /* * Protect the list of events. Locking either mutex or lock * is sufficient to ensure the list doesn't change; to change * the list you need to lock both the mutex and the spinlock. */ struct mutex mutex; struct list_head active_ctx_list; struct perf_event_groups pinned_groups; struct perf_event_groups flexible_groups; struct list_head event_list; struct list_head pinned_active; struct list_head flexible_active; int nr_events; int nr_active; int is_active; int nr_stat; int nr_freq; int rotate_disable; /* * Set when nr_events != nr_active, except tolerant to events not * necessary to be active due to scheduling constraints, such as cgroups. */ int rotate_necessary; refcount_t refcount; struct task_struct *task; /* * Context clock, runs when context enabled. */ u64 time; u64 timestamp; u64 timeoffset; /* * These fields let us detect when two contexts have both * been cloned (inherited) from a common ancestor. */ struct perf_event_context *parent_ctx; u64 parent_gen; u64 generation; int pin_count; #ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ #endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; }; /* * Number of contexts where an event can trigger: * task, softirq, hardirq, nmi. */ #define PERF_NR_CONTEXTS 4 /** * struct perf_event_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int active_oncpu; int exclusive; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; unsigned int hrtimer_active; #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; struct list_head cgrp_cpuctx_entry; #endif struct list_head sched_cb_entry; int sched_cb_usage; int online; /* * Per-CPU storage for iterators used in visit_groups_merge. The default * storage is of size 2 to hold the CPU and any CPU event iterators. */ int heap_size; struct perf_event **heap; struct perf_event *heap_default[2]; }; struct perf_output_handle { struct perf_event *event; struct perf_buffer *rb; unsigned long wakeup; unsigned long size; u64 aux_flags; union { void *addr; unsigned long head; }; int page; }; struct bpf_perf_event_data_kern { bpf_user_pt_regs_t *regs; struct perf_sample_data *data; struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF /* * perf_cgroup_info keeps track of time_enabled for a cgroup. * This is a per-cpu dynamically allocated data structure. */ struct perf_cgroup_info { u64 time; u64 timestamp; u64 timeoffset; int active; }; struct perf_cgroup { struct cgroup_subsys_state css; struct perf_cgroup_info __percpu *info; }; /* * Must ensure cgroup is pinned (css_get) before calling * this function. In other words, we cannot call this function * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { return container_of(task_css_check(task, perf_event_cgrp_id, ctx ? lockdep_is_held(&ctx->lock) : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ #ifdef CONFIG_PERF_EVENTS extern void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event); extern void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size); extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); extern int perf_num_counters(void); extern const char *perf_pmu_name(void); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next); extern int perf_event_init_task(struct task_struct *child); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); extern struct file *perf_event_get(unsigned int fd); extern const struct perf_event *perf_get_event(struct file *file); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern void perf_pmu_resched(struct pmu *pmu); extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, perf_overflow_handler_t callback, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); struct perf_sample_data { /* * Fields set by perf_sample_data_init(), group so as to * minimize the cachelines touched. */ u64 addr; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 period; u64 weight; u64 txn; union perf_mem_data_src data_src; /* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ u64 type; u64 ip; struct { u32 pid; u32 tid; } tid_entry; u64 time; u64 id; u64 stream_id; struct { u32 cpu; u32 reserved; } cpu_entry; struct perf_callchain_entry *callchain; u64 aux_size; struct perf_regs regs_user; struct perf_regs regs_intr; u64 stack_user_size; u64 phys_addr; u64 cgroup; } ____cacheline_aligned; /* default value for data source */ #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA)) static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period) { /* remaining struct members initialized in perf_prepare_sample() */ data->addr = addr; data->raw = NULL; data->br_stack = NULL; data->period = period; data->weight = 0; data->data_src.val = PERF_MEM_NA; data->txn = 0; } extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_prepare_sample(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_forward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_backward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern int perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); static inline bool __is_default_overflow_handler(perf_overflow_handler_t overflow_handler) { if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) return true; return false; } #define is_default_overflow_handler(event) \ __is_default_overflow_handler((event)->overflow_handler) #ifdef CONFIG_BPF_SYSCALL static inline bool uses_default_overflow_handler(struct perf_event *event) { if (likely(is_default_overflow_handler(event))) return true; return __is_default_overflow_handler(event->orig_overflow_handler); } #else #define uses_default_overflow_handler(event) \ is_default_overflow_handler(event) #endif extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_event__output_id_sample(struct perf_event *event, struct perf_output_handle *handle, struct perf_sample_data *sample); extern void perf_log_lost_samples(struct perf_event *event, u64 lost); static inline bool event_has_any_exclude_flag(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; return attr->exclude_idle || attr->exclude_user || attr->exclude_kernel || attr->exclude_hv || attr->exclude_guest || attr->exclude_host; } static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; } /* * Return 1 for a software event, 0 for a hardware event */ static inline int is_software_event(struct perf_event *event) { return event->event_caps & PERF_EV_CAP_SOFTWARE; } /* * Return 1 for event in sw context, 0 for event in hw context */ static inline int in_software_context(struct perf_event *event) { return event->ctx->pmu->task_ctx_nr == perf_sw_context; } static inline int is_exclusive_pmu(struct pmu *pmu) { return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE; } extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } #endif /* * When generating a perf sample in-line, instead of from an interrupt / * exception, we lack a pt_regs. This is typically used from software events * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. * * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests * - sp for PERF_SAMPLE_CALLCHAIN * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) * * NOTE: assumes @regs is otherwise already 0 filled; this is important for * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, regs, addr); } DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); /* * 'Special' version for the scheduler, it hard assumes no recursion, * which is guaranteed by us not actually scheduling inside other swevents * because those disable preemption. */ static __always_inline void perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(event_id, nr, regs, addr); } } extern struct static_key_false perf_sched_events; static __always_inline bool perf_sw_migrate_enabled(void) { if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS])) return true; return false; } static inline void perf_event_task_migrate(struct task_struct *task) { if (perf_sw_migrate_enabled()) task->sched_migrated = 1; } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (perf_sw_migrate_enabled() && task->sched_migrated) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0); task->sched_migrated = 0; } } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym); extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; static inline struct perf_guest_info_callbacks *perf_get_guest_cbs(void) { /* * Callbacks are RCU-protected and must be READ_ONCE to avoid reloading * the callbacks between a !NULL check and dereferences, to ensure * pending stores/changes to the callback pointers are visible before a * non-NULL perf_guest_cbs is visible to readers, and to prevent a * module from unloading callbacks while readers are active. */ return rcu_dereference(perf_guest_cbs); } extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); extern void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len); /* Callchains */ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); extern void put_callchain_entry(int rctx); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->contexts; return 0; } else { ctx->contexts_maxed = true; return -1; /* no more room, stop walking the stack */ } } static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->nr; return 0; } else { return -1; /* no more room, stop walking the stack */ } } extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_mlock; extern int sysctl_perf_event_sample_rate; extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); int perf_proc_update_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int perf_event_max_stack_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 /* Finer grained perf_event_open(2) access control. */ #define PERF_SECURITY_CPU 1 #define PERF_SECURITY_KERNEL 2 #define PERF_SECURITY_TRACEPOINT 3 static inline int perf_is_paranoid(void) { return sysctl_perf_event_paranoid > -1; } static inline int perf_allow_kernel(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_KERNEL); } static inline int perf_allow_cpu(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; return security_perf_event_open(attr, PERF_SECURITY_CPU); } static inline int perf_allow_tracepoint(struct perf_event_attr *attr) { if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT); } extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags # define perf_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) # define perf_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif static inline bool has_branch_stack(struct perf_event *event) { return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; } static inline bool needs_branch_stack(struct perf_event *event) { return event->attr.branch_sample_type != 0; } static inline bool has_aux(struct perf_event *event) { return event->pmu->setup_aux; } static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; } static inline bool has_addr_filter(struct perf_event *event) { return event->pmu->nr_addr_filters; } /* * An inherited event uses parent's filters */ static inline struct perf_addr_filters_head * perf_event_addr_filters(struct perf_event *event) { struct perf_addr_filters_head *ifh = &event->addr_filters; if (event->parent) ifh = &event->parent->addr_filters; return ifh; } extern void perf_event_addr_filters_sync(struct perf_event *event); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, struct perf_output_handle *handle, unsigned long from, unsigned long to); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); extern int perf_event_period(struct perf_event *event, u64 value); extern u64 perf_event_pause(struct perf_event *event, bool reset); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; } static inline void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) { } static inline int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) { return -EINVAL; } static inline void * perf_get_aux(struct perf_output_handle *handle) { return NULL; } static inline void perf_event_task_migrate(struct task_struct *task) { } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } static inline const struct perf_event *perf_get_event(struct file *file) { return ERR_PTR(-EINVAL); } static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); } static inline int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } static inline int perf_event_refresh(struct perf_event *event, int refresh) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline int perf_register_guest_info_callbacks (struct perf_guest_info_callbacks *callbacks) { return 0; } static inline int perf_unregister_guest_info_callbacks (struct perf_guest_info_callbacks *callbacks) { return 0; } static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { } static inline void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } static inline void perf_swevent_put_recursion_context(int rctx) { } static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; } static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } static inline int perf_event_period(struct perf_event *event, u64 value) { return -EINVAL; } static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); #else static inline void perf_restore_debug_store(void) { } #endif static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag) { return frag->pad < sizeof(u64); } #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) struct perf_pmu_events_attr { struct device_attribute attr; u64 id; const char *event_str; }; struct perf_pmu_events_ht_attr { struct device_attribute attr; u64 id; const char *event_str_ht; const char *event_str_noht; }; ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, \ }; #define PMU_EVENT_ATTR_STRING(_name, _var, _str) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = _str, \ }; #define PMU_FORMAT_ATTR(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ \ static struct device_attribute format_attr_##_name = __ATTR_RO(_name) /* Performance counter hotplug functions */ #ifdef CONFIG_PERF_EVENTS int perf_event_init_cpu(unsigned int cpu); int perf_event_exit_cpu(unsigned int cpu); #else #define perf_event_init_cpu NULL #define perf_event_exit_cpu NULL #endif extern void __weak arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now); #endif /* _LINUX_PERF_EVENT_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_PREEMPT_H #define __ASM_PREEMPT_H #include <asm/rmwcc.h> #include <asm/percpu.h> #include <linux/thread_info.h> DECLARE_PER_CPU(int, __preempt_count); /* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 /* * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such * that a decrement hitting 0 means we can and should reschedule. */ #define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED) /* * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users * that think a non-zero value indicates we cannot preempt. */ static __always_inline int preempt_count(void) { return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED; } static __always_inline void preempt_count_set(int pc) { int old, new; do { old = raw_cpu_read_4(__preempt_count); new = (old & PREEMPT_NEED_RESCHED) | (pc & ~PREEMPT_NEED_RESCHED); } while (raw_cpu_cmpxchg_4(__preempt_count, old, new) != old); } /* * must be macros to avoid header recursion hell */ #define init_task_preempt_count(p) do { } while (0) #define init_idle_preempt_count(p, cpu) do { \ per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \ } while (0) /* * We fold the NEED_RESCHED bit into the preempt count such that * preempt_enable() can decrement and test for needing to reschedule with a * single instruction. * * We invert the actual bit, so that when the decrement hits 0 we know we both * need to resched (the bit is cleared) and can resched (no preempt count). */ static __always_inline void set_preempt_need_resched(void) { raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED); } static __always_inline void clear_preempt_need_resched(void) { raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED); } static __always_inline bool test_preempt_need_resched(void) { return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED); } /* * The various preempt_count add/sub methods */ static __always_inline void __preempt_count_add(int val) { raw_cpu_add_4(__preempt_count, val); } static __always_inline void __preempt_count_sub(int val) { raw_cpu_add_4(__preempt_count, -val); } /* * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule * a decrement which hits zero means we have no preempt_count and should * reschedule. */ static __always_inline bool __preempt_count_dec_and_test(void) { return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var])); } /* * Returns true when we need to resched and can (barring IRQ state). */ static __always_inline bool should_resched(int preempt_offset) { return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); } #ifdef CONFIG_PREEMPTION extern asmlinkage void preempt_schedule_thunk(void); # define __preempt_schedule() \ asm volatile ("call preempt_schedule_thunk" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule(void); extern asmlinkage void preempt_schedule_notrace_thunk(void); # define __preempt_schedule_notrace() \ asm volatile ("call preempt_schedule_notrace_thunk" : ASM_CALL_CONSTRAINT) extern asmlinkage void preempt_schedule_notrace(void); #endif #endif /* __ASM_PREEMPT_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_IVERSION_H #define _LINUX_IVERSION_H #include <linux/fs.h> /* * The inode->i_version field: * --------------------------- * The change attribute (i_version) is mandated by NFSv4 and is mostly for * knfsd, but is also used for other purposes (e.g. IMA). The i_version must * appear different to observers if there was a change to the inode's data or * metadata since it was last queried. * * Observers see the i_version as a 64-bit number that never decreases. If it * remains the same since it was last checked, then nothing has changed in the * inode. If it's different then something has changed. Observers cannot infer * anything about the nature or magnitude of the changes from the value, only * that the inode has changed in some fashion. * * Not all filesystems properly implement the i_version counter. Subsystems that * want to use i_version field on an inode should first check whether the * filesystem sets the SB_I_VERSION flag (usually via the IS_I_VERSION macro). * * Those that set SB_I_VERSION will automatically have their i_version counter * incremented on writes to normal files. If the SB_I_VERSION is not set, then * the VFS will not touch it on writes, and the filesystem can use it how it * wishes. Note that the filesystem is always responsible for updating the * i_version on namespace changes in directories (mkdir, rmdir, unlink, etc.). * We consider these sorts of filesystems to have a kernel-managed i_version. * * It may be impractical for filesystems to keep i_version updates atomic with * respect to the changes that cause them. They should, however, guarantee * that i_version updates are never visible before the changes that caused * them. Also, i_version updates should never be delayed longer than it takes * the original change to reach disk. * * This implementation uses the low bit in the i_version field as a flag to * track when the value has been queried. If it has not been queried since it * was last incremented, we can skip the increment in most cases. * * In the event that we're updating the ctime, we will usually go ahead and * bump the i_version anyway. Since that has to go to stable storage in some * fashion, we might as well increment it as well. * * With this implementation, the value should always appear to observers to * increase over time if the file has changed. It's recommended to use * inode_eq_iversion() helper to compare values. * * Note that some filesystems (e.g. NFS and AFS) just use the field to store * a server-provided value (for the most part). For that reason, those * filesystems do not set SB_I_VERSION. These filesystems are considered to * have a self-managed i_version. * * Persistently storing the i_version * ---------------------------------- * Queries of the i_version field are not gated on them hitting the backing * store. It's always possible that the host could crash after allowing * a query of the value but before it has made it to disk. * * To mitigate this problem, filesystems should always use * inode_set_iversion_queried when loading an existing inode from disk. This * ensures that the next attempted inode increment will result in the value * changing. * * Storing the value to disk therefore does not count as a query, so those * filesystems should use inode_peek_iversion to grab the value to be stored. * There is no need to flag the value as having been queried in that case. */ /* * We borrow the lowest bit in the i_version to use as a flag to tell whether * it has been queried since we last incremented it. If it has, then we must * increment it on the next change. After that, we can clear the flag and * avoid incrementing it again until it has again been queried. */ #define I_VERSION_QUERIED_SHIFT (1) #define I_VERSION_QUERIED (1ULL << (I_VERSION_QUERIED_SHIFT - 1)) #define I_VERSION_INCREMENT (1ULL << I_VERSION_QUERIED_SHIFT) /** * inode_set_iversion_raw - set i_version to the specified raw value * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val. This function is for use by * filesystems that self-manage the i_version. * * For example, the NFS client stores its NFSv4 change attribute in this way, * and the AFS client stores the data_version from the server here. */ static inline void inode_set_iversion_raw(struct inode *inode, u64 val) { atomic64_set(&inode->i_version, val); } /** * inode_peek_iversion_raw - grab a "raw" iversion value * @inode: inode from which i_version should be read * * Grab a "raw" inode->i_version value and return it. The i_version is not * flagged or converted in any way. This is mostly used to access a self-managed * i_version. * * With those filesystems, we want to treat the i_version as an entirely * opaque value. */ static inline u64 inode_peek_iversion_raw(const struct inode *inode) { return atomic64_read(&inode->i_version); } /** * inode_set_max_iversion_raw - update i_version new value is larger * @inode: inode to set * @val: new i_version to set * * Some self-managed filesystems (e.g Ceph) will only update the i_version * value if the new value is larger than the one we already have. */ static inline void inode_set_max_iversion_raw(struct inode *inode, u64 val) { u64 cur, old; cur = inode_peek_iversion_raw(inode); for (;;) { if (cur > val) break; old = atomic64_cmpxchg(&inode->i_version, cur, val); if (likely(old == cur)) break; cur = old; } } /** * inode_set_iversion - set i_version to a particular value * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val. This function is for filesystems with * a kernel-managed i_version, for initializing a newly-created inode from * scratch. * * In this case, we do not set the QUERIED flag since we know that this value * has never been queried. */ static inline void inode_set_iversion(struct inode *inode, u64 val) { inode_set_iversion_raw(inode, val << I_VERSION_QUERIED_SHIFT); } /** * inode_set_iversion_queried - set i_version to a particular value as quereied * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val, and flag it for increment on the next * change. * * Filesystems that persistently store the i_version on disk should use this * when loading an existing inode from disk. * * When loading in an i_version value from a backing store, we can't be certain * that it wasn't previously viewed before being stored. Thus, we must assume * that it was, to ensure that we don't end up handing out the same value for * different versions of the same inode. */ static inline void inode_set_iversion_queried(struct inode *inode, u64 val) { inode_set_iversion_raw(inode, (val << I_VERSION_QUERIED_SHIFT) | I_VERSION_QUERIED); } /** * inode_maybe_inc_iversion - increments i_version * @inode: inode with the i_version that should be updated * @force: increment the counter even if it's not necessary? * * Every time the inode is modified, the i_version field must be seen to have * changed by any observer. * * If "force" is set or the QUERIED flag is set, then ensure that we increment * the value, and clear the queried flag. * * In the common case where neither is set, then we can return "false" without * updating i_version. * * If this function returns false, and no other metadata has changed, then we * can avoid logging the metadata. */ static inline bool inode_maybe_inc_iversion(struct inode *inode, bool force) { u64 cur, old, new; /* * The i_version field is not strictly ordered with any other inode * information, but the legacy inode_inc_iversion code used a spinlock * to serialize increments. * * Here, we add full memory barriers to ensure that any de-facto * ordering with other info is preserved. * * This barrier pairs with the barrier in inode_query_iversion() */ smp_mb(); cur = inode_peek_iversion_raw(inode); for (;;) { /* If flag is clear then we needn't do anything */ if (!force && !(cur & I_VERSION_QUERIED)) return false; /* Since lowest bit is flag, add 2 to avoid it */ new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; old = atomic64_cmpxchg(&inode->i_version, cur, new); if (likely(old == cur)) break; cur = old; } return true; } /** * inode_inc_iversion - forcibly increment i_version * @inode: inode that needs to be updated * * Forcbily increment the i_version field. This always results in a change to * the observable value. */ static inline void inode_inc_iversion(struct inode *inode) { inode_maybe_inc_iversion(inode, true); } /** * inode_iversion_need_inc - is the i_version in need of being incremented? * @inode: inode to check * * Returns whether the inode->i_version counter needs incrementing on the next * change. Just fetch the value and check the QUERIED flag. */ static inline bool inode_iversion_need_inc(struct inode *inode) { return inode_peek_iversion_raw(inode) & I_VERSION_QUERIED; } /** * inode_inc_iversion_raw - forcibly increment raw i_version * @inode: inode that needs to be updated * * Forcbily increment the raw i_version field. This always results in a change * to the raw value. * * NFS will use the i_version field to store the value from the server. It * mostly treats it as opaque, but in the case where it holds a write * delegation, it must increment the value itself. This function does that. */ static inline void inode_inc_iversion_raw(struct inode *inode) { atomic64_inc(&inode->i_version); } /** * inode_peek_iversion - read i_version without flagging it to be incremented * @inode: inode from which i_version should be read * * Read the inode i_version counter for an inode without registering it as a * query. * * This is typically used by local filesystems that need to store an i_version * on disk. In that situation, it's not necessary to flag it as having been * viewed, as the result won't be used to gauge changes from that point. */ static inline u64 inode_peek_iversion(const struct inode *inode) { return inode_peek_iversion_raw(inode) >> I_VERSION_QUERIED_SHIFT; } /** * inode_query_iversion - read i_version for later use * @inode: inode from which i_version should be read * * Read the inode i_version counter. This should be used by callers that wish * to store the returned i_version for later comparison. This will guarantee * that a later query of the i_version will result in a different value if * anything has changed. * * In this implementation, we fetch the current value, set the QUERIED flag and * then try to swap it into place with a cmpxchg, if it wasn't already set. If * that fails, we try again with the newly fetched value from the cmpxchg. */ static inline u64 inode_query_iversion(struct inode *inode) { u64 cur, old, new; cur = inode_peek_iversion_raw(inode); for (;;) { /* If flag is already set, then no need to swap */ if (cur & I_VERSION_QUERIED) { /* * This barrier (and the implicit barrier in the * cmpxchg below) pairs with the barrier in * inode_maybe_inc_iversion(). */ smp_mb(); break; } new = cur | I_VERSION_QUERIED; old = atomic64_cmpxchg(&inode->i_version, cur, new); if (likely(old == cur)) break; cur = old; } return cur >> I_VERSION_QUERIED_SHIFT; } /* * For filesystems without any sort of change attribute, the best we can * do is fake one up from the ctime: */ static inline u64 time_to_chattr(struct timespec64 *t) { u64 chattr = t->tv_sec; chattr <<= 32; chattr += t->tv_nsec; return chattr; } /** * inode_eq_iversion_raw - check whether the raw i_version counter has changed * @inode: inode to check * @old: old value to check against its i_version * * Compare the current raw i_version counter with a previous one. Returns true * if they are the same or false if they are different. */ static inline bool inode_eq_iversion_raw(const struct inode *inode, u64 old) { return inode_peek_iversion_raw(inode) == old; } /** * inode_eq_iversion - check whether the i_version counter has changed * @inode: inode to check * @old: old value to check against its i_version * * Compare an i_version counter with a previous one. Returns true if they are * the same, and false if they are different. * * Note that we don't need to set the QUERIED flag in this case, as the value * in the inode is not being recorded for later use. */ static inline bool inode_eq_iversion(const struct inode *inode, u64 old) { return inode_peek_iversion(inode) == old; } #endif |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 | // SPDX-License-Identifier: GPL-2.0 // Generated by scripts/atomic/gen-atomic-fallback.sh // DO NOT MODIFY THIS FILE DIRECTLY #ifndef _LINUX_ATOMIC_FALLBACK_H #define _LINUX_ATOMIC_FALLBACK_H #include <linux/compiler.h> #ifndef arch_xchg_relaxed #define arch_xchg_relaxed arch_xchg #define arch_xchg_acquire arch_xchg #define arch_xchg_release arch_xchg #else /* arch_xchg_relaxed */ #ifndef arch_xchg_acquire #define arch_xchg_acquire(...) \ __atomic_op_acquire(arch_xchg, __VA_ARGS__) #endif #ifndef arch_xchg_release #define arch_xchg_release(...) \ __atomic_op_release(arch_xchg, __VA_ARGS__) #endif #ifndef arch_xchg #define arch_xchg(...) \ __atomic_op_fence(arch_xchg, __VA_ARGS__) #endif #endif /* arch_xchg_relaxed */ #ifndef arch_cmpxchg_relaxed #define arch_cmpxchg_relaxed arch_cmpxchg #define arch_cmpxchg_acquire arch_cmpxchg #define arch_cmpxchg_release arch_cmpxchg #else /* arch_cmpxchg_relaxed */ #ifndef arch_cmpxchg_acquire #define arch_cmpxchg_acquire(...) \ __atomic_op_acquire(arch_cmpxchg, __VA_ARGS__) #endif #ifndef arch_cmpxchg_release #define arch_cmpxchg_release(...) \ __atomic_op_release(arch_cmpxchg, __VA_ARGS__) #endif #ifndef arch_cmpxchg #define arch_cmpxchg(...) \ __atomic_op_fence(arch_cmpxchg, __VA_ARGS__) #endif #endif /* arch_cmpxchg_relaxed */ #ifndef arch_cmpxchg64_relaxed #define arch_cmpxchg64_relaxed arch_cmpxchg64 #define arch_cmpxchg64_acquire arch_cmpxchg64 #define arch_cmpxchg64_release arch_cmpxchg64 #else /* arch_cmpxchg64_relaxed */ #ifndef arch_cmpxchg64_acquire #define arch_cmpxchg64_acquire(...) \ __atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__) #endif #ifndef arch_cmpxchg64_release #define arch_cmpxchg64_release(...) \ __atomic_op_release(arch_cmpxchg64, __VA_ARGS__) #endif #ifndef arch_cmpxchg64 #define arch_cmpxchg64(...) \ __atomic_op_fence(arch_cmpxchg64, __VA_ARGS__) #endif #endif /* arch_cmpxchg64_relaxed */ #ifndef arch_atomic_read_acquire static __always_inline int arch_atomic_read_acquire(const atomic_t *v) { return smp_load_acquire(&(v)->counter); } #define arch_atomic_read_acquire arch_atomic_read_acquire #endif #ifndef arch_atomic_set_release static __always_inline void arch_atomic_set_release(atomic_t *v, int i) { smp_store_release(&(v)->counter, i); } #define arch_atomic_set_release arch_atomic_set_release #endif #ifndef arch_atomic_add_return_relaxed #define arch_atomic_add_return_acquire arch_atomic_add_return #define arch_atomic_add_return_release arch_atomic_add_return #define arch_atomic_add_return_relaxed arch_atomic_add_return #else /* arch_atomic_add_return_relaxed */ #ifndef arch_atomic_add_return_acquire static __always_inline int arch_atomic_add_return_acquire(int i, atomic_t *v) { int ret = arch_atomic_add_return_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_add_return_acquire arch_atomic_add_return_acquire #endif #ifndef arch_atomic_add_return_release static __always_inline int arch_atomic_add_return_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_add_return_relaxed(i, v); } #define arch_atomic_add_return_release arch_atomic_add_return_release #endif #ifndef arch_atomic_add_return static __always_inline int arch_atomic_add_return(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_add_return_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_add_return arch_atomic_add_return #endif #endif /* arch_atomic_add_return_relaxed */ #ifndef arch_atomic_fetch_add_relaxed #define arch_atomic_fetch_add_acquire arch_atomic_fetch_add #define arch_atomic_fetch_add_release arch_atomic_fetch_add #define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add #else /* arch_atomic_fetch_add_relaxed */ #ifndef arch_atomic_fetch_add_acquire static __always_inline int arch_atomic_fetch_add_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_add_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_add_acquire arch_atomic_fetch_add_acquire #endif #ifndef arch_atomic_fetch_add_release static __always_inline int arch_atomic_fetch_add_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_add_relaxed(i, v); } #define arch_atomic_fetch_add_release arch_atomic_fetch_add_release #endif #ifndef arch_atomic_fetch_add static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_add_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_add arch_atomic_fetch_add #endif #endif /* arch_atomic_fetch_add_relaxed */ #ifndef arch_atomic_sub_return_relaxed #define arch_atomic_sub_return_acquire arch_atomic_sub_return #define arch_atomic_sub_return_release arch_atomic_sub_return #define arch_atomic_sub_return_relaxed arch_atomic_sub_return #else /* arch_atomic_sub_return_relaxed */ #ifndef arch_atomic_sub_return_acquire static __always_inline int arch_atomic_sub_return_acquire(int i, atomic_t *v) { int ret = arch_atomic_sub_return_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_sub_return_acquire arch_atomic_sub_return_acquire #endif #ifndef arch_atomic_sub_return_release static __always_inline int arch_atomic_sub_return_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_sub_return_relaxed(i, v); } #define arch_atomic_sub_return_release arch_atomic_sub_return_release #endif #ifndef arch_atomic_sub_return static __always_inline int arch_atomic_sub_return(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_sub_return_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_sub_return arch_atomic_sub_return #endif #endif /* arch_atomic_sub_return_relaxed */ #ifndef arch_atomic_fetch_sub_relaxed #define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub #define arch_atomic_fetch_sub_release arch_atomic_fetch_sub #define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub #else /* arch_atomic_fetch_sub_relaxed */ #ifndef arch_atomic_fetch_sub_acquire static __always_inline int arch_atomic_fetch_sub_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_sub_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub_acquire #endif #ifndef arch_atomic_fetch_sub_release static __always_inline int arch_atomic_fetch_sub_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_sub_relaxed(i, v); } #define arch_atomic_fetch_sub_release arch_atomic_fetch_sub_release #endif #ifndef arch_atomic_fetch_sub static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_sub_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_sub arch_atomic_fetch_sub #endif #endif /* arch_atomic_fetch_sub_relaxed */ #ifndef arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { arch_atomic_add(1, v); } #define arch_atomic_inc arch_atomic_inc #endif #ifndef arch_atomic_inc_return_relaxed #ifdef arch_atomic_inc_return #define arch_atomic_inc_return_acquire arch_atomic_inc_return #define arch_atomic_inc_return_release arch_atomic_inc_return #define arch_atomic_inc_return_relaxed arch_atomic_inc_return #endif /* arch_atomic_inc_return */ #ifndef arch_atomic_inc_return static __always_inline int arch_atomic_inc_return(atomic_t *v) { return arch_atomic_add_return(1, v); } #define arch_atomic_inc_return arch_atomic_inc_return #endif #ifndef arch_atomic_inc_return_acquire static __always_inline int arch_atomic_inc_return_acquire(atomic_t *v) { return arch_atomic_add_return_acquire(1, v); } #define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire #endif #ifndef arch_atomic_inc_return_release static __always_inline int arch_atomic_inc_return_release(atomic_t *v) { return arch_atomic_add_return_release(1, v); } #define arch_atomic_inc_return_release arch_atomic_inc_return_release #endif #ifndef arch_atomic_inc_return_relaxed static __always_inline int arch_atomic_inc_return_relaxed(atomic_t *v) { return arch_atomic_add_return_relaxed(1, v); } #define arch_atomic_inc_return_relaxed arch_atomic_inc_return_relaxed #endif #else /* arch_atomic_inc_return_relaxed */ #ifndef arch_atomic_inc_return_acquire static __always_inline int arch_atomic_inc_return_acquire(atomic_t *v) { int ret = arch_atomic_inc_return_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire #endif #ifndef arch_atomic_inc_return_release static __always_inline int arch_atomic_inc_return_release(atomic_t *v) { __atomic_release_fence(); return arch_atomic_inc_return_relaxed(v); } #define arch_atomic_inc_return_release arch_atomic_inc_return_release #endif #ifndef arch_atomic_inc_return static __always_inline int arch_atomic_inc_return(atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_inc_return_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic_inc_return arch_atomic_inc_return #endif #endif /* arch_atomic_inc_return_relaxed */ #ifndef arch_atomic_fetch_inc_relaxed #ifdef arch_atomic_fetch_inc #define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc #define arch_atomic_fetch_inc_release arch_atomic_fetch_inc #define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc #endif /* arch_atomic_fetch_inc */ #ifndef arch_atomic_fetch_inc static __always_inline int arch_atomic_fetch_inc(atomic_t *v) { return arch_atomic_fetch_add(1, v); } #define arch_atomic_fetch_inc arch_atomic_fetch_inc #endif #ifndef arch_atomic_fetch_inc_acquire static __always_inline int arch_atomic_fetch_inc_acquire(atomic_t *v) { return arch_atomic_fetch_add_acquire(1, v); } #define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire #endif #ifndef arch_atomic_fetch_inc_release static __always_inline int arch_atomic_fetch_inc_release(atomic_t *v) { return arch_atomic_fetch_add_release(1, v); } #define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release #endif #ifndef arch_atomic_fetch_inc_relaxed static __always_inline int arch_atomic_fetch_inc_relaxed(atomic_t *v) { return arch_atomic_fetch_add_relaxed(1, v); } #define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc_relaxed #endif #else /* arch_atomic_fetch_inc_relaxed */ #ifndef arch_atomic_fetch_inc_acquire static __always_inline int arch_atomic_fetch_inc_acquire(atomic_t *v) { int ret = arch_atomic_fetch_inc_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire #endif #ifndef arch_atomic_fetch_inc_release static __always_inline int arch_atomic_fetch_inc_release(atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_inc_relaxed(v); } #define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release #endif #ifndef arch_atomic_fetch_inc static __always_inline int arch_atomic_fetch_inc(atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_inc_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_inc arch_atomic_fetch_inc #endif #endif /* arch_atomic_fetch_inc_relaxed */ #ifndef arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { arch_atomic_sub(1, v); } #define arch_atomic_dec arch_atomic_dec #endif #ifndef arch_atomic_dec_return_relaxed #ifdef arch_atomic_dec_return #define arch_atomic_dec_return_acquire arch_atomic_dec_return #define arch_atomic_dec_return_release arch_atomic_dec_return #define arch_atomic_dec_return_relaxed arch_atomic_dec_return #endif /* arch_atomic_dec_return */ #ifndef arch_atomic_dec_return static __always_inline int arch_atomic_dec_return(atomic_t *v) { return arch_atomic_sub_return(1, v); } #define arch_atomic_dec_return arch_atomic_dec_return #endif #ifndef arch_atomic_dec_return_acquire static __always_inline int arch_atomic_dec_return_acquire(atomic_t *v) { return arch_atomic_sub_return_acquire(1, v); } #define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire #endif #ifndef arch_atomic_dec_return_release static __always_inline int arch_atomic_dec_return_release(atomic_t *v) { return arch_atomic_sub_return_release(1, v); } #define arch_atomic_dec_return_release arch_atomic_dec_return_release #endif #ifndef arch_atomic_dec_return_relaxed static __always_inline int arch_atomic_dec_return_relaxed(atomic_t *v) { return arch_atomic_sub_return_relaxed(1, v); } #define arch_atomic_dec_return_relaxed arch_atomic_dec_return_relaxed #endif #else /* arch_atomic_dec_return_relaxed */ #ifndef arch_atomic_dec_return_acquire static __always_inline int arch_atomic_dec_return_acquire(atomic_t *v) { int ret = arch_atomic_dec_return_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire #endif #ifndef arch_atomic_dec_return_release static __always_inline int arch_atomic_dec_return_release(atomic_t *v) { __atomic_release_fence(); return arch_atomic_dec_return_relaxed(v); } #define arch_atomic_dec_return_release arch_atomic_dec_return_release #endif #ifndef arch_atomic_dec_return static __always_inline int arch_atomic_dec_return(atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_dec_return_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic_dec_return arch_atomic_dec_return #endif #endif /* arch_atomic_dec_return_relaxed */ #ifndef arch_atomic_fetch_dec_relaxed #ifdef arch_atomic_fetch_dec #define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec #define arch_atomic_fetch_dec_release arch_atomic_fetch_dec #define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec #endif /* arch_atomic_fetch_dec */ #ifndef arch_atomic_fetch_dec static __always_inline int arch_atomic_fetch_dec(atomic_t *v) { return arch_atomic_fetch_sub(1, v); } #define arch_atomic_fetch_dec arch_atomic_fetch_dec #endif #ifndef arch_atomic_fetch_dec_acquire static __always_inline int arch_atomic_fetch_dec_acquire(atomic_t *v) { return arch_atomic_fetch_sub_acquire(1, v); } #define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire #endif #ifndef arch_atomic_fetch_dec_release static __always_inline int arch_atomic_fetch_dec_release(atomic_t *v) { return arch_atomic_fetch_sub_release(1, v); } #define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release #endif #ifndef arch_atomic_fetch_dec_relaxed static __always_inline int arch_atomic_fetch_dec_relaxed(atomic_t *v) { return arch_atomic_fetch_sub_relaxed(1, v); } #define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec_relaxed #endif #else /* arch_atomic_fetch_dec_relaxed */ #ifndef arch_atomic_fetch_dec_acquire static __always_inline int arch_atomic_fetch_dec_acquire(atomic_t *v) { int ret = arch_atomic_fetch_dec_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire #endif #ifndef arch_atomic_fetch_dec_release static __always_inline int arch_atomic_fetch_dec_release(atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_dec_relaxed(v); } #define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release #endif #ifndef arch_atomic_fetch_dec static __always_inline int arch_atomic_fetch_dec(atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_dec_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_dec arch_atomic_fetch_dec #endif #endif /* arch_atomic_fetch_dec_relaxed */ #ifndef arch_atomic_fetch_and_relaxed #define arch_atomic_fetch_and_acquire arch_atomic_fetch_and #define arch_atomic_fetch_and_release arch_atomic_fetch_and #define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and #else /* arch_atomic_fetch_and_relaxed */ #ifndef arch_atomic_fetch_and_acquire static __always_inline int arch_atomic_fetch_and_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_and_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_and_acquire arch_atomic_fetch_and_acquire #endif #ifndef arch_atomic_fetch_and_release static __always_inline int arch_atomic_fetch_and_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_and_relaxed(i, v); } #define arch_atomic_fetch_and_release arch_atomic_fetch_and_release #endif #ifndef arch_atomic_fetch_and static __always_inline int arch_atomic_fetch_and(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_and_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_and arch_atomic_fetch_and #endif #endif /* arch_atomic_fetch_and_relaxed */ #ifndef arch_atomic_andnot static __always_inline void arch_atomic_andnot(int i, atomic_t *v) { arch_atomic_and(~i, v); } #define arch_atomic_andnot arch_atomic_andnot #endif #ifndef arch_atomic_fetch_andnot_relaxed #ifdef arch_atomic_fetch_andnot #define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot #define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot #define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot #endif /* arch_atomic_fetch_andnot */ #ifndef arch_atomic_fetch_andnot static __always_inline int arch_atomic_fetch_andnot(int i, atomic_t *v) { return arch_atomic_fetch_and(~i, v); } #define arch_atomic_fetch_andnot arch_atomic_fetch_andnot #endif #ifndef arch_atomic_fetch_andnot_acquire static __always_inline int arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) { return arch_atomic_fetch_and_acquire(~i, v); } #define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire #endif #ifndef arch_atomic_fetch_andnot_release static __always_inline int arch_atomic_fetch_andnot_release(int i, atomic_t *v) { return arch_atomic_fetch_and_release(~i, v); } #define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release #endif #ifndef arch_atomic_fetch_andnot_relaxed static __always_inline int arch_atomic_fetch_andnot_relaxed(int i, atomic_t *v) { return arch_atomic_fetch_and_relaxed(~i, v); } #define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed #endif #else /* arch_atomic_fetch_andnot_relaxed */ #ifndef arch_atomic_fetch_andnot_acquire static __always_inline int arch_atomic_fetch_andnot_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_andnot_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire #endif #ifndef arch_atomic_fetch_andnot_release static __always_inline int arch_atomic_fetch_andnot_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_andnot_relaxed(i, v); } #define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release #endif #ifndef arch_atomic_fetch_andnot static __always_inline int arch_atomic_fetch_andnot(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_andnot_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_andnot arch_atomic_fetch_andnot #endif #endif /* arch_atomic_fetch_andnot_relaxed */ #ifndef arch_atomic_fetch_or_relaxed #define arch_atomic_fetch_or_acquire arch_atomic_fetch_or #define arch_atomic_fetch_or_release arch_atomic_fetch_or #define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or #else /* arch_atomic_fetch_or_relaxed */ #ifndef arch_atomic_fetch_or_acquire static __always_inline int arch_atomic_fetch_or_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_or_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_or_acquire arch_atomic_fetch_or_acquire #endif #ifndef arch_atomic_fetch_or_release static __always_inline int arch_atomic_fetch_or_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_or_relaxed(i, v); } #define arch_atomic_fetch_or_release arch_atomic_fetch_or_release #endif #ifndef arch_atomic_fetch_or static __always_inline int arch_atomic_fetch_or(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_or_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_or arch_atomic_fetch_or #endif #endif /* arch_atomic_fetch_or_relaxed */ #ifndef arch_atomic_fetch_xor_relaxed #define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor #define arch_atomic_fetch_xor_release arch_atomic_fetch_xor #define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor #else /* arch_atomic_fetch_xor_relaxed */ #ifndef arch_atomic_fetch_xor_acquire static __always_inline int arch_atomic_fetch_xor_acquire(int i, atomic_t *v) { int ret = arch_atomic_fetch_xor_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor_acquire #endif #ifndef arch_atomic_fetch_xor_release static __always_inline int arch_atomic_fetch_xor_release(int i, atomic_t *v) { __atomic_release_fence(); return arch_atomic_fetch_xor_relaxed(i, v); } #define arch_atomic_fetch_xor_release arch_atomic_fetch_xor_release #endif #ifndef arch_atomic_fetch_xor static __always_inline int arch_atomic_fetch_xor(int i, atomic_t *v) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_fetch_xor_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic_fetch_xor arch_atomic_fetch_xor #endif #endif /* arch_atomic_fetch_xor_relaxed */ #ifndef arch_atomic_xchg_relaxed #define arch_atomic_xchg_acquire arch_atomic_xchg #define arch_atomic_xchg_release arch_atomic_xchg #define arch_atomic_xchg_relaxed arch_atomic_xchg #else /* arch_atomic_xchg_relaxed */ #ifndef arch_atomic_xchg_acquire static __always_inline int arch_atomic_xchg_acquire(atomic_t *v, int i) { int ret = arch_atomic_xchg_relaxed(v, i); __atomic_acquire_fence(); return ret; } #define arch_atomic_xchg_acquire arch_atomic_xchg_acquire #endif #ifndef arch_atomic_xchg_release static __always_inline int arch_atomic_xchg_release(atomic_t *v, int i) { __atomic_release_fence(); return arch_atomic_xchg_relaxed(v, i); } #define arch_atomic_xchg_release arch_atomic_xchg_release #endif #ifndef arch_atomic_xchg static __always_inline int arch_atomic_xchg(atomic_t *v, int i) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_xchg_relaxed(v, i); __atomic_post_full_fence(); return ret; } #define arch_atomic_xchg arch_atomic_xchg #endif #endif /* arch_atomic_xchg_relaxed */ #ifndef arch_atomic_cmpxchg_relaxed #define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg #define arch_atomic_cmpxchg_release arch_atomic_cmpxchg #define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg #else /* arch_atomic_cmpxchg_relaxed */ #ifndef arch_atomic_cmpxchg_acquire static __always_inline int arch_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) { int ret = arch_atomic_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; } #define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire #endif #ifndef arch_atomic_cmpxchg_release static __always_inline int arch_atomic_cmpxchg_release(atomic_t *v, int old, int new) { __atomic_release_fence(); return arch_atomic_cmpxchg_relaxed(v, old, new); } #define arch_atomic_cmpxchg_release arch_atomic_cmpxchg_release #endif #ifndef arch_atomic_cmpxchg static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) { int ret; __atomic_pre_full_fence(); ret = arch_atomic_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; } #define arch_atomic_cmpxchg arch_atomic_cmpxchg #endif #endif /* arch_atomic_cmpxchg_relaxed */ #ifndef arch_atomic_try_cmpxchg_relaxed #ifdef arch_atomic_try_cmpxchg #define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg #define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg #define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg #endif /* arch_atomic_try_cmpxchg */ #ifndef arch_atomic_try_cmpxchg static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { int r, o = *old; r = arch_atomic_cmpxchg(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg #endif #ifndef arch_atomic_try_cmpxchg_acquire static __always_inline bool arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { int r, o = *old; r = arch_atomic_cmpxchg_acquire(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire #endif #ifndef arch_atomic_try_cmpxchg_release static __always_inline bool arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { int r, o = *old; r = arch_atomic_cmpxchg_release(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release #endif #ifndef arch_atomic_try_cmpxchg_relaxed static __always_inline bool arch_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { int r, o = *old; r = arch_atomic_cmpxchg_relaxed(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg_relaxed #endif #else /* arch_atomic_try_cmpxchg_relaxed */ #ifndef arch_atomic_try_cmpxchg_acquire static __always_inline bool arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; } #define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire #endif #ifndef arch_atomic_try_cmpxchg_release static __always_inline bool arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { __atomic_release_fence(); return arch_atomic_try_cmpxchg_relaxed(v, old, new); } #define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release #endif #ifndef arch_atomic_try_cmpxchg static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) { bool ret; __atomic_pre_full_fence(); ret = arch_atomic_try_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; } #define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg #endif #endif /* arch_atomic_try_cmpxchg_relaxed */ #ifndef arch_atomic_sub_and_test /** * arch_atomic_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @v: pointer of type atomic_t * * Atomically subtracts @i from @v and returns * true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { return arch_atomic_sub_return(i, v) == 0; } #define arch_atomic_sub_and_test arch_atomic_sub_and_test #endif #ifndef arch_atomic_dec_and_test /** * arch_atomic_dec_and_test - decrement and test * @v: pointer of type atomic_t * * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { return arch_atomic_dec_return(v) == 0; } #define arch_atomic_dec_and_test arch_atomic_dec_and_test #endif #ifndef arch_atomic_inc_and_test /** * arch_atomic_inc_and_test - increment and test * @v: pointer of type atomic_t * * Atomically increments @v by 1 * and returns true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { return arch_atomic_inc_return(v) == 0; } #define arch_atomic_inc_and_test arch_atomic_inc_and_test #endif #ifndef arch_atomic_add_negative /** * arch_atomic_add_negative - add and test if negative * @i: integer value to add * @v: pointer of type atomic_t * * Atomically adds @i to @v and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { return arch_atomic_add_return(i, v) < 0; } #define arch_atomic_add_negative arch_atomic_add_negative #endif #ifndef arch_atomic_fetch_add_unless /** * arch_atomic_fetch_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, so long as @v was not already @u. * Returns original value of @v */ static __always_inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) { int c = arch_atomic_read(v); do { if (unlikely(c == u)) break; } while (!arch_atomic_try_cmpxchg(v, &c, c + a)); return c; } #define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless #endif #ifndef arch_atomic_add_unless /** * arch_atomic_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ static __always_inline bool arch_atomic_add_unless(atomic_t *v, int a, int u) { return arch_atomic_fetch_add_unless(v, a, u) != u; } #define arch_atomic_add_unless arch_atomic_add_unless #endif #ifndef arch_atomic_inc_not_zero /** * arch_atomic_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic_t * * Atomically increments @v by 1, if @v is non-zero. * Returns true if the increment was done. */ static __always_inline bool arch_atomic_inc_not_zero(atomic_t *v) { return arch_atomic_add_unless(v, 1, 0); } #define arch_atomic_inc_not_zero arch_atomic_inc_not_zero #endif #ifndef arch_atomic_inc_unless_negative static __always_inline bool arch_atomic_inc_unless_negative(atomic_t *v) { int c = arch_atomic_read(v); do { if (unlikely(c < 0)) return false; } while (!arch_atomic_try_cmpxchg(v, &c, c + 1)); return true; } #define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative #endif #ifndef arch_atomic_dec_unless_positive static __always_inline bool arch_atomic_dec_unless_positive(atomic_t *v) { int c = arch_atomic_read(v); do { if (unlikely(c > 0)) return false; } while (!arch_atomic_try_cmpxchg(v, &c, c - 1)); return true; } #define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive #endif #ifndef arch_atomic_dec_if_positive static __always_inline int arch_atomic_dec_if_positive(atomic_t *v) { int dec, c = arch_atomic_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; } while (!arch_atomic_try_cmpxchg(v, &c, dec)); return dec; } #define arch_atomic_dec_if_positive arch_atomic_dec_if_positive #endif #ifdef CONFIG_GENERIC_ATOMIC64 #include <asm-generic/atomic64.h> #endif #ifndef arch_atomic64_read_acquire static __always_inline s64 arch_atomic64_read_acquire(const atomic64_t *v) { return smp_load_acquire(&(v)->counter); } #define arch_atomic64_read_acquire arch_atomic64_read_acquire #endif #ifndef arch_atomic64_set_release static __always_inline void arch_atomic64_set_release(atomic64_t *v, s64 i) { smp_store_release(&(v)->counter, i); } #define arch_atomic64_set_release arch_atomic64_set_release #endif #ifndef arch_atomic64_add_return_relaxed #define arch_atomic64_add_return_acquire arch_atomic64_add_return #define arch_atomic64_add_return_release arch_atomic64_add_return #define arch_atomic64_add_return_relaxed arch_atomic64_add_return #else /* arch_atomic64_add_return_relaxed */ #ifndef arch_atomic64_add_return_acquire static __always_inline s64 arch_atomic64_add_return_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_add_return_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_add_return_acquire arch_atomic64_add_return_acquire #endif #ifndef arch_atomic64_add_return_release static __always_inline s64 arch_atomic64_add_return_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_add_return_relaxed(i, v); } #define arch_atomic64_add_return_release arch_atomic64_add_return_release #endif #ifndef arch_atomic64_add_return static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_add_return_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_add_return arch_atomic64_add_return #endif #endif /* arch_atomic64_add_return_relaxed */ #ifndef arch_atomic64_fetch_add_relaxed #define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add #define arch_atomic64_fetch_add_release arch_atomic64_fetch_add #define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add #else /* arch_atomic64_fetch_add_relaxed */ #ifndef arch_atomic64_fetch_add_acquire static __always_inline s64 arch_atomic64_fetch_add_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_add_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add_acquire #endif #ifndef arch_atomic64_fetch_add_release static __always_inline s64 arch_atomic64_fetch_add_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_add_relaxed(i, v); } #define arch_atomic64_fetch_add_release arch_atomic64_fetch_add_release #endif #ifndef arch_atomic64_fetch_add static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_add_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_add arch_atomic64_fetch_add #endif #endif /* arch_atomic64_fetch_add_relaxed */ #ifndef arch_atomic64_sub_return_relaxed #define arch_atomic64_sub_return_acquire arch_atomic64_sub_return #define arch_atomic64_sub_return_release arch_atomic64_sub_return #define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return #else /* arch_atomic64_sub_return_relaxed */ #ifndef arch_atomic64_sub_return_acquire static __always_inline s64 arch_atomic64_sub_return_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_sub_return_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_sub_return_acquire arch_atomic64_sub_return_acquire #endif #ifndef arch_atomic64_sub_return_release static __always_inline s64 arch_atomic64_sub_return_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_sub_return_relaxed(i, v); } #define arch_atomic64_sub_return_release arch_atomic64_sub_return_release #endif #ifndef arch_atomic64_sub_return static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_sub_return_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_sub_return arch_atomic64_sub_return #endif #endif /* arch_atomic64_sub_return_relaxed */ #ifndef arch_atomic64_fetch_sub_relaxed #define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub #define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub #define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub #else /* arch_atomic64_fetch_sub_relaxed */ #ifndef arch_atomic64_fetch_sub_acquire static __always_inline s64 arch_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_sub_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub_acquire #endif #ifndef arch_atomic64_fetch_sub_release static __always_inline s64 arch_atomic64_fetch_sub_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_sub_relaxed(i, v); } #define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub_release #endif #ifndef arch_atomic64_fetch_sub static __always_inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_sub_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_sub arch_atomic64_fetch_sub #endif #endif /* arch_atomic64_fetch_sub_relaxed */ #ifndef arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { arch_atomic64_add(1, v); } #define arch_atomic64_inc arch_atomic64_inc #endif #ifndef arch_atomic64_inc_return_relaxed #ifdef arch_atomic64_inc_return #define arch_atomic64_inc_return_acquire arch_atomic64_inc_return #define arch_atomic64_inc_return_release arch_atomic64_inc_return #define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return #endif /* arch_atomic64_inc_return */ #ifndef arch_atomic64_inc_return static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v) { return arch_atomic64_add_return(1, v); } #define arch_atomic64_inc_return arch_atomic64_inc_return #endif #ifndef arch_atomic64_inc_return_acquire static __always_inline s64 arch_atomic64_inc_return_acquire(atomic64_t *v) { return arch_atomic64_add_return_acquire(1, v); } #define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire #endif #ifndef arch_atomic64_inc_return_release static __always_inline s64 arch_atomic64_inc_return_release(atomic64_t *v) { return arch_atomic64_add_return_release(1, v); } #define arch_atomic64_inc_return_release arch_atomic64_inc_return_release #endif #ifndef arch_atomic64_inc_return_relaxed static __always_inline s64 arch_atomic64_inc_return_relaxed(atomic64_t *v) { return arch_atomic64_add_return_relaxed(1, v); } #define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed #endif #else /* arch_atomic64_inc_return_relaxed */ #ifndef arch_atomic64_inc_return_acquire static __always_inline s64 arch_atomic64_inc_return_acquire(atomic64_t *v) { s64 ret = arch_atomic64_inc_return_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire #endif #ifndef arch_atomic64_inc_return_release static __always_inline s64 arch_atomic64_inc_return_release(atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_inc_return_relaxed(v); } #define arch_atomic64_inc_return_release arch_atomic64_inc_return_release #endif #ifndef arch_atomic64_inc_return static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_inc_return_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_inc_return arch_atomic64_inc_return #endif #endif /* arch_atomic64_inc_return_relaxed */ #ifndef arch_atomic64_fetch_inc_relaxed #ifdef arch_atomic64_fetch_inc #define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc #define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc #define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc #endif /* arch_atomic64_fetch_inc */ #ifndef arch_atomic64_fetch_inc static __always_inline s64 arch_atomic64_fetch_inc(atomic64_t *v) { return arch_atomic64_fetch_add(1, v); } #define arch_atomic64_fetch_inc arch_atomic64_fetch_inc #endif #ifndef arch_atomic64_fetch_inc_acquire static __always_inline s64 arch_atomic64_fetch_inc_acquire(atomic64_t *v) { return arch_atomic64_fetch_add_acquire(1, v); } #define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire #endif #ifndef arch_atomic64_fetch_inc_release static __always_inline s64 arch_atomic64_fetch_inc_release(atomic64_t *v) { return arch_atomic64_fetch_add_release(1, v); } #define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release #endif #ifndef arch_atomic64_fetch_inc_relaxed static __always_inline s64 arch_atomic64_fetch_inc_relaxed(atomic64_t *v) { return arch_atomic64_fetch_add_relaxed(1, v); } #define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc_relaxed #endif #else /* arch_atomic64_fetch_inc_relaxed */ #ifndef arch_atomic64_fetch_inc_acquire static __always_inline s64 arch_atomic64_fetch_inc_acquire(atomic64_t *v) { s64 ret = arch_atomic64_fetch_inc_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire #endif #ifndef arch_atomic64_fetch_inc_release static __always_inline s64 arch_atomic64_fetch_inc_release(atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_inc_relaxed(v); } #define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release #endif #ifndef arch_atomic64_fetch_inc static __always_inline s64 arch_atomic64_fetch_inc(atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_inc_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_inc arch_atomic64_fetch_inc #endif #endif /* arch_atomic64_fetch_inc_relaxed */ #ifndef arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { arch_atomic64_sub(1, v); } #define arch_atomic64_dec arch_atomic64_dec #endif #ifndef arch_atomic64_dec_return_relaxed #ifdef arch_atomic64_dec_return #define arch_atomic64_dec_return_acquire arch_atomic64_dec_return #define arch_atomic64_dec_return_release arch_atomic64_dec_return #define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return #endif /* arch_atomic64_dec_return */ #ifndef arch_atomic64_dec_return static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v) { return arch_atomic64_sub_return(1, v); } #define arch_atomic64_dec_return arch_atomic64_dec_return #endif #ifndef arch_atomic64_dec_return_acquire static __always_inline s64 arch_atomic64_dec_return_acquire(atomic64_t *v) { return arch_atomic64_sub_return_acquire(1, v); } #define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire #endif #ifndef arch_atomic64_dec_return_release static __always_inline s64 arch_atomic64_dec_return_release(atomic64_t *v) { return arch_atomic64_sub_return_release(1, v); } #define arch_atomic64_dec_return_release arch_atomic64_dec_return_release #endif #ifndef arch_atomic64_dec_return_relaxed static __always_inline s64 arch_atomic64_dec_return_relaxed(atomic64_t *v) { return arch_atomic64_sub_return_relaxed(1, v); } #define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed #endif #else /* arch_atomic64_dec_return_relaxed */ #ifndef arch_atomic64_dec_return_acquire static __always_inline s64 arch_atomic64_dec_return_acquire(atomic64_t *v) { s64 ret = arch_atomic64_dec_return_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire #endif #ifndef arch_atomic64_dec_return_release static __always_inline s64 arch_atomic64_dec_return_release(atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_dec_return_relaxed(v); } #define arch_atomic64_dec_return_release arch_atomic64_dec_return_release #endif #ifndef arch_atomic64_dec_return static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_dec_return_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_dec_return arch_atomic64_dec_return #endif #endif /* arch_atomic64_dec_return_relaxed */ #ifndef arch_atomic64_fetch_dec_relaxed #ifdef arch_atomic64_fetch_dec #define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec #define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec #define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec #endif /* arch_atomic64_fetch_dec */ #ifndef arch_atomic64_fetch_dec static __always_inline s64 arch_atomic64_fetch_dec(atomic64_t *v) { return arch_atomic64_fetch_sub(1, v); } #define arch_atomic64_fetch_dec arch_atomic64_fetch_dec #endif #ifndef arch_atomic64_fetch_dec_acquire static __always_inline s64 arch_atomic64_fetch_dec_acquire(atomic64_t *v) { return arch_atomic64_fetch_sub_acquire(1, v); } #define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire #endif #ifndef arch_atomic64_fetch_dec_release static __always_inline s64 arch_atomic64_fetch_dec_release(atomic64_t *v) { return arch_atomic64_fetch_sub_release(1, v); } #define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release #endif #ifndef arch_atomic64_fetch_dec_relaxed static __always_inline s64 arch_atomic64_fetch_dec_relaxed(atomic64_t *v) { return arch_atomic64_fetch_sub_relaxed(1, v); } #define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec_relaxed #endif #else /* arch_atomic64_fetch_dec_relaxed */ #ifndef arch_atomic64_fetch_dec_acquire static __always_inline s64 arch_atomic64_fetch_dec_acquire(atomic64_t *v) { s64 ret = arch_atomic64_fetch_dec_relaxed(v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire #endif #ifndef arch_atomic64_fetch_dec_release static __always_inline s64 arch_atomic64_fetch_dec_release(atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_dec_relaxed(v); } #define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release #endif #ifndef arch_atomic64_fetch_dec static __always_inline s64 arch_atomic64_fetch_dec(atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_dec_relaxed(v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_dec arch_atomic64_fetch_dec #endif #endif /* arch_atomic64_fetch_dec_relaxed */ #ifndef arch_atomic64_fetch_and_relaxed #define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and #define arch_atomic64_fetch_and_release arch_atomic64_fetch_and #define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and #else /* arch_atomic64_fetch_and_relaxed */ #ifndef arch_atomic64_fetch_and_acquire static __always_inline s64 arch_atomic64_fetch_and_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_and_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and_acquire #endif #ifndef arch_atomic64_fetch_and_release static __always_inline s64 arch_atomic64_fetch_and_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_and_relaxed(i, v); } #define arch_atomic64_fetch_and_release arch_atomic64_fetch_and_release #endif #ifndef arch_atomic64_fetch_and static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_and_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_and arch_atomic64_fetch_and #endif #endif /* arch_atomic64_fetch_and_relaxed */ #ifndef arch_atomic64_andnot static __always_inline void arch_atomic64_andnot(s64 i, atomic64_t *v) { arch_atomic64_and(~i, v); } #define arch_atomic64_andnot arch_atomic64_andnot #endif #ifndef arch_atomic64_fetch_andnot_relaxed #ifdef arch_atomic64_fetch_andnot #define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot #define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot #define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot #endif /* arch_atomic64_fetch_andnot */ #ifndef arch_atomic64_fetch_andnot static __always_inline s64 arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) { return arch_atomic64_fetch_and(~i, v); } #define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot #endif #ifndef arch_atomic64_fetch_andnot_acquire static __always_inline s64 arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { return arch_atomic64_fetch_and_acquire(~i, v); } #define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire #endif #ifndef arch_atomic64_fetch_andnot_release static __always_inline s64 arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { return arch_atomic64_fetch_and_release(~i, v); } #define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release #endif #ifndef arch_atomic64_fetch_andnot_relaxed static __always_inline s64 arch_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v) { return arch_atomic64_fetch_and_relaxed(~i, v); } #define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed #endif #else /* arch_atomic64_fetch_andnot_relaxed */ #ifndef arch_atomic64_fetch_andnot_acquire static __always_inline s64 arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire #endif #ifndef arch_atomic64_fetch_andnot_release static __always_inline s64 arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_andnot_relaxed(i, v); } #define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release #endif #ifndef arch_atomic64_fetch_andnot static __always_inline s64 arch_atomic64_fetch_andnot(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_andnot_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot #endif #endif /* arch_atomic64_fetch_andnot_relaxed */ #ifndef arch_atomic64_fetch_or_relaxed #define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or #define arch_atomic64_fetch_or_release arch_atomic64_fetch_or #define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or #else /* arch_atomic64_fetch_or_relaxed */ #ifndef arch_atomic64_fetch_or_acquire static __always_inline s64 arch_atomic64_fetch_or_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_or_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or_acquire #endif #ifndef arch_atomic64_fetch_or_release static __always_inline s64 arch_atomic64_fetch_or_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_or_relaxed(i, v); } #define arch_atomic64_fetch_or_release arch_atomic64_fetch_or_release #endif #ifndef arch_atomic64_fetch_or static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_or_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_or arch_atomic64_fetch_or #endif #endif /* arch_atomic64_fetch_or_relaxed */ #ifndef arch_atomic64_fetch_xor_relaxed #define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor #define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor #define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor #else /* arch_atomic64_fetch_xor_relaxed */ #ifndef arch_atomic64_fetch_xor_acquire static __always_inline s64 arch_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) { s64 ret = arch_atomic64_fetch_xor_relaxed(i, v); __atomic_acquire_fence(); return ret; } #define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor_acquire #endif #ifndef arch_atomic64_fetch_xor_release static __always_inline s64 arch_atomic64_fetch_xor_release(s64 i, atomic64_t *v) { __atomic_release_fence(); return arch_atomic64_fetch_xor_relaxed(i, v); } #define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor_release #endif #ifndef arch_atomic64_fetch_xor static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_fetch_xor_relaxed(i, v); __atomic_post_full_fence(); return ret; } #define arch_atomic64_fetch_xor arch_atomic64_fetch_xor #endif #endif /* arch_atomic64_fetch_xor_relaxed */ #ifndef arch_atomic64_xchg_relaxed #define arch_atomic64_xchg_acquire arch_atomic64_xchg #define arch_atomic64_xchg_release arch_atomic64_xchg #define arch_atomic64_xchg_relaxed arch_atomic64_xchg #else /* arch_atomic64_xchg_relaxed */ #ifndef arch_atomic64_xchg_acquire static __always_inline s64 arch_atomic64_xchg_acquire(atomic64_t *v, s64 i) { s64 ret = arch_atomic64_xchg_relaxed(v, i); __atomic_acquire_fence(); return ret; } #define arch_atomic64_xchg_acquire arch_atomic64_xchg_acquire #endif #ifndef arch_atomic64_xchg_release static __always_inline s64 arch_atomic64_xchg_release(atomic64_t *v, s64 i) { __atomic_release_fence(); return arch_atomic64_xchg_relaxed(v, i); } #define arch_atomic64_xchg_release arch_atomic64_xchg_release #endif #ifndef arch_atomic64_xchg static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 i) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_xchg_relaxed(v, i); __atomic_post_full_fence(); return ret; } #define arch_atomic64_xchg arch_atomic64_xchg #endif #endif /* arch_atomic64_xchg_relaxed */ #ifndef arch_atomic64_cmpxchg_relaxed #define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg #define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg #define arch_atomic64_cmpxchg_relaxed arch_atomic64_cmpxchg #else /* arch_atomic64_cmpxchg_relaxed */ #ifndef arch_atomic64_cmpxchg_acquire static __always_inline s64 arch_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) { s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; } #define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg_acquire #endif #ifndef arch_atomic64_cmpxchg_release static __always_inline s64 arch_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { __atomic_release_fence(); return arch_atomic64_cmpxchg_relaxed(v, old, new); } #define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg_release #endif #ifndef arch_atomic64_cmpxchg static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { s64 ret; __atomic_pre_full_fence(); ret = arch_atomic64_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; } #define arch_atomic64_cmpxchg arch_atomic64_cmpxchg #endif #endif /* arch_atomic64_cmpxchg_relaxed */ #ifndef arch_atomic64_try_cmpxchg_relaxed #ifdef arch_atomic64_try_cmpxchg #define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg #define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg #define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg #endif /* arch_atomic64_try_cmpxchg */ #ifndef arch_atomic64_try_cmpxchg static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; r = arch_atomic64_cmpxchg(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg #endif #ifndef arch_atomic64_try_cmpxchg_acquire static __always_inline bool arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; r = arch_atomic64_cmpxchg_acquire(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire #endif #ifndef arch_atomic64_try_cmpxchg_release static __always_inline bool arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; r = arch_atomic64_cmpxchg_release(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release #endif #ifndef arch_atomic64_try_cmpxchg_relaxed static __always_inline bool arch_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { s64 r, o = *old; r = arch_atomic64_cmpxchg_relaxed(v, o, new); if (unlikely(r != o)) *old = r; return likely(r == o); } #define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg_relaxed #endif #else /* arch_atomic64_try_cmpxchg_relaxed */ #ifndef arch_atomic64_try_cmpxchg_acquire static __always_inline bool arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); __atomic_acquire_fence(); return ret; } #define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire #endif #ifndef arch_atomic64_try_cmpxchg_release static __always_inline bool arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { __atomic_release_fence(); return arch_atomic64_try_cmpxchg_relaxed(v, old, new); } #define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release #endif #ifndef arch_atomic64_try_cmpxchg static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { bool ret; __atomic_pre_full_fence(); ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new); __atomic_post_full_fence(); return ret; } #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg #endif #endif /* arch_atomic64_try_cmpxchg_relaxed */ #ifndef arch_atomic64_sub_and_test /** * arch_atomic64_sub_and_test - subtract value from variable and test result * @i: integer value to subtract * @v: pointer of type atomic64_t * * Atomically subtracts @i from @v and returns * true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v) { return arch_atomic64_sub_return(i, v) == 0; } #define arch_atomic64_sub_and_test arch_atomic64_sub_and_test #endif #ifndef arch_atomic64_dec_and_test /** * arch_atomic64_dec_and_test - decrement and test * @v: pointer of type atomic64_t * * Atomically decrements @v by 1 and * returns true if the result is 0, or false for all other * cases. */ static __always_inline bool arch_atomic64_dec_and_test(atomic64_t *v) { return arch_atomic64_dec_return(v) == 0; } #define arch_atomic64_dec_and_test arch_atomic64_dec_and_test #endif #ifndef arch_atomic64_inc_and_test /** * arch_atomic64_inc_and_test - increment and test * @v: pointer of type atomic64_t * * Atomically increments @v by 1 * and returns true if the result is zero, or false for all * other cases. */ static __always_inline bool arch_atomic64_inc_and_test(atomic64_t *v) { return arch_atomic64_inc_return(v) == 0; } #define arch_atomic64_inc_and_test arch_atomic64_inc_and_test #endif #ifndef arch_atomic64_add_negative /** * arch_atomic64_add_negative - add and test if negative * @i: integer value to add * @v: pointer of type atomic64_t * * Atomically adds @i to @v and returns true * if the result is negative, or false when * result is greater than or equal to zero. */ static __always_inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v) { return arch_atomic64_add_return(i, v) < 0; } #define arch_atomic64_add_negative arch_atomic64_add_negative #endif #ifndef arch_atomic64_fetch_add_unless /** * arch_atomic64_fetch_add_unless - add unless the number is already a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, so long as @v was not already @u. * Returns original value of @v */ static __always_inline s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { s64 c = arch_atomic64_read(v); do { if (unlikely(c == u)) break; } while (!arch_atomic64_try_cmpxchg(v, &c, c + a)); return c; } #define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless #endif #ifndef arch_atomic64_add_unless /** * arch_atomic64_add_unless - add unless the number is already a given value * @v: pointer of type atomic64_t * @a: the amount to add to v... * @u: ...unless v is equal to u. * * Atomically adds @a to @v, if @v was not already @u. * Returns true if the addition was done. */ static __always_inline bool arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { return arch_atomic64_fetch_add_unless(v, a, u) != u; } #define arch_atomic64_add_unless arch_atomic64_add_unless #endif #ifndef arch_atomic64_inc_not_zero /** * arch_atomic64_inc_not_zero - increment unless the number is zero * @v: pointer of type atomic64_t * * Atomically increments @v by 1, if @v is non-zero. * Returns true if the increment was done. */ static __always_inline bool arch_atomic64_inc_not_zero(atomic64_t *v) { return arch_atomic64_add_unless(v, 1, 0); } #define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero #endif #ifndef arch_atomic64_inc_unless_negative static __always_inline bool arch_atomic64_inc_unless_negative(atomic64_t *v) { s64 c = arch_atomic64_read(v); do { if (unlikely(c < 0)) return false; } while (!arch_atomic64_try_cmpxchg(v, &c, c + 1)); return true; } #define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative #endif #ifndef arch_atomic64_dec_unless_positive static __always_inline bool arch_atomic64_dec_unless_positive(atomic64_t *v) { s64 c = arch_atomic64_read(v); do { if (unlikely(c > 0)) return false; } while (!arch_atomic64_try_cmpxchg(v, &c, c - 1)); return true; } #define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive #endif #ifndef arch_atomic64_dec_if_positive static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v) { s64 dec, c = arch_atomic64_read(v); do { dec = c - 1; if (unlikely(dec < 0)) break; } while (!arch_atomic64_try_cmpxchg(v, &c, dec)); return dec; } #define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ // 90cd26cfd69d2250303d654955a0cc12620fb91b |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 | // SPDX-License-Identifier: GPL-2.0-only #include <crypto/hash.h> #include <linux/export.h> #include <linux/bvec.h> #include <linux/fault-inject-usercopy.h> #include <linux/uio.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/splice.h> #include <linux/compat.h> #include <net/checksum.h> #include <linux/scatterlist.h> #include <linux/instrumented.h> #define PIPE_PARANOIA /* for now */ #define iterate_iovec(i, n, __v, __p, skip, STEP) { \ size_t left; \ size_t wanted = n; \ __p = i->iov; \ __v.iov_len = min(n, __p->iov_len - skip); \ if (likely(__v.iov_len)) { \ __v.iov_base = __p->iov_base + skip; \ left = (STEP); \ __v.iov_len -= left; \ skip += __v.iov_len; \ n -= __v.iov_len; \ } else { \ left = 0; \ } \ while (unlikely(!left && n)) { \ __p++; \ __v.iov_len = min(n, __p->iov_len); \ if (unlikely(!__v.iov_len)) \ continue; \ __v.iov_base = __p->iov_base; \ left = (STEP); \ __v.iov_len -= left; \ skip = __v.iov_len; \ n -= __v.iov_len; \ } \ n = wanted - n; \ } #define iterate_kvec(i, n, __v, __p, skip, STEP) { \ size_t wanted = n; \ __p = i->kvec; \ __v.iov_len = min(n, __p->iov_len - skip); \ if (likely(__v.iov_len)) { \ __v.iov_base = __p->iov_base + skip; \ (void)(STEP); \ skip += __v.iov_len; \ n -= __v.iov_len; \ } \ while (unlikely(n)) { \ __p++; \ __v.iov_len = min(n, __p->iov_len); \ if (unlikely(!__v.iov_len)) \ continue; \ __v.iov_base = __p->iov_base; \ (void)(STEP); \ skip = __v.iov_len; \ n -= __v.iov_len; \ } \ n = wanted; \ } #define iterate_bvec(i, n, __v, __bi, skip, STEP) { \ struct bvec_iter __start; \ __start.bi_size = n; \ __start.bi_bvec_done = skip; \ __start.bi_idx = 0; \ for_each_bvec(__v, i->bvec, __bi, __start) { \ if (!__v.bv_len) \ continue; \ (void)(STEP); \ } \ } #define iterate_all_kinds(i, n, v, I, B, K) { \ if (likely(n)) { \ size_t skip = i->iov_offset; \ if (unlikely(i->type & ITER_BVEC)) { \ struct bio_vec v; \ struct bvec_iter __bi; \ iterate_bvec(i, n, v, __bi, skip, (B)) \ } else if (unlikely(i->type & ITER_KVEC)) { \ const struct kvec *kvec; \ struct kvec v; \ iterate_kvec(i, n, v, kvec, skip, (K)) \ } else if (unlikely(i->type & ITER_DISCARD)) { \ } else { \ const struct iovec *iov; \ struct iovec v; \ iterate_iovec(i, n, v, iov, skip, (I)) \ } \ } \ } #define iterate_and_advance(i, n, v, I, B, K) { \ if (unlikely(i->count < n)) \ n = i->count; \ if (i->count) { \ size_t skip = i->iov_offset; \ if (unlikely(i->type & ITER_BVEC)) { \ const struct bio_vec *bvec = i->bvec; \ struct bio_vec v; \ struct bvec_iter __bi; \ iterate_bvec(i, n, v, __bi, skip, (B)) \ i->bvec = __bvec_iter_bvec(i->bvec, __bi); \ i->nr_segs -= i->bvec - bvec; \ skip = __bi.bi_bvec_done; \ } else if (unlikely(i->type & ITER_KVEC)) { \ const struct kvec *kvec; \ struct kvec v; \ iterate_kvec(i, n, v, kvec, skip, (K)) \ if (skip == kvec->iov_len) { \ kvec++; \ skip = 0; \ } \ i->nr_segs -= kvec - i->kvec; \ i->kvec = kvec; \ } else if (unlikely(i->type & ITER_DISCARD)) { \ skip += n; \ } else { \ const struct iovec *iov; \ struct iovec v; \ iterate_iovec(i, n, v, iov, skip, (I)) \ if (skip == iov->iov_len) { \ iov++; \ skip = 0; \ } \ i->nr_segs -= iov - i->iov; \ i->iov = iov; \ } \ i->count -= n; \ i->iov_offset = skip; \ } \ } static int copyout(void __user *to, const void *from, size_t n) { if (should_fail_usercopy()) return n; if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } static int copyin(void *to, const void __user *from, size_t n) { if (should_fail_usercopy()) return n; if (access_ok(from, n)) { instrument_copy_from_user(to, from, n); n = raw_copy_from_user(to, from, n); } return n; } static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t skip, copy, left, wanted; const struct iovec *iov; char __user *buf; void *kaddr, *from; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; might_fault(); wanted = bytes; iov = i->iov; skip = i->iov_offset; buf = iov->iov_base + skip; copy = min(bytes, iov->iov_len - skip); if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_writeable(buf, copy)) { kaddr = kmap_atomic(page); from = kaddr + offset; /* first chunk, usually the only one */ left = copyout(buf, from, copy); copy -= left; skip += copy; from += copy; bytes -= copy; while (unlikely(!left && bytes)) { iov++; buf = iov->iov_base; copy = min(bytes, iov->iov_len); left = copyout(buf, from, copy); copy -= left; skip = copy; from += copy; bytes -= copy; } if (likely(!bytes)) { kunmap_atomic(kaddr); goto done; } offset = from - kaddr; buf += copy; kunmap_atomic(kaddr); copy = min(bytes, iov->iov_len - skip); } /* Too bad - revert to non-atomic kmap */ kaddr = kmap(page); from = kaddr + offset; left = copyout(buf, from, copy); copy -= left; skip += copy; from += copy; bytes -= copy; while (unlikely(!left && bytes)) { iov++; buf = iov->iov_base; copy = min(bytes, iov->iov_len); left = copyout(buf, from, copy); copy -= left; skip = copy; from += copy; bytes -= copy; } kunmap(page); done: if (skip == iov->iov_len) { iov++; skip = 0; } i->count -= wanted - bytes; i->nr_segs -= iov - i->iov; i->iov = iov; i->iov_offset = skip; return wanted - bytes; } static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t skip, copy, left, wanted; const struct iovec *iov; char __user *buf; void *kaddr, *to; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; might_fault(); wanted = bytes; iov = i->iov; skip = i->iov_offset; buf = iov->iov_base + skip; copy = min(bytes, iov->iov_len - skip); if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_readable(buf, copy)) { kaddr = kmap_atomic(page); to = kaddr + offset; /* first chunk, usually the only one */ left = copyin(to, buf, copy); copy -= left; skip += copy; to += copy; bytes -= copy; while (unlikely(!left && bytes)) { iov++; buf = iov->iov_base; copy = min(bytes, iov->iov_len); left = copyin(to, buf, copy); copy -= left; skip = copy; to += copy; bytes -= copy; } if (likely(!bytes)) { kunmap_atomic(kaddr); goto done; } offset = to - kaddr; buf += copy; kunmap_atomic(kaddr); copy = min(bytes, iov->iov_len - skip); } /* Too bad - revert to non-atomic kmap */ kaddr = kmap(page); to = kaddr + offset; left = copyin(to, buf, copy); copy -= left; skip += copy; to += copy; bytes -= copy; while (unlikely(!left && bytes)) { iov++; buf = iov->iov_base; copy = min(bytes, iov->iov_len); left = copyin(to, buf, copy); copy -= left; skip = copy; to += copy; bytes -= copy; } kunmap(page); done: if (skip == iov->iov_len) { iov++; skip = 0; } i->count -= wanted - bytes; i->nr_segs -= iov - i->iov; i->iov = iov; i->iov_offset = skip; return wanted - bytes; } #ifdef PIPE_PARANOIA static bool sanity(const struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_head = pipe->head; unsigned int p_tail = pipe->tail; unsigned int p_mask = pipe->ring_size - 1; unsigned int p_occupancy = pipe_occupancy(p_head, p_tail); unsigned int i_head = i->head; unsigned int idx; if (i->iov_offset) { struct pipe_buffer *p; if (unlikely(p_occupancy == 0)) goto Bad; // pipe must be non-empty if (unlikely(i_head != p_head - 1)) goto Bad; // must be at the last buffer... p = &pipe->bufs[i_head & p_mask]; if (unlikely(p->offset + p->len != i->iov_offset)) goto Bad; // ... at the end of segment } else { if (i_head != p_head) goto Bad; // must be right after the last buffer } return true; Bad: printk(KERN_ERR "idx = %d, offset = %zd\n", i_head, i->iov_offset); printk(KERN_ERR "head = %d, tail = %d, buffers = %d\n", p_head, p_tail, pipe->ring_size); for (idx = 0; idx < pipe->ring_size; idx++) printk(KERN_ERR "[%p %p %d %d]\n", pipe->bufs[idx].ops, pipe->bufs[idx].page, pipe->bufs[idx].offset, pipe->bufs[idx].len); WARN_ON(1); return false; } #else #define sanity(i) true #endif static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; struct pipe_buffer *buf; unsigned int p_tail = pipe->tail; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head = i->head; size_t off; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; if (!sanity(i)) return 0; off = i->iov_offset; buf = &pipe->bufs[i_head & p_mask]; if (off) { if (offset == off && buf->page == page) { /* merge with the last one */ buf->len += bytes; i->iov_offset += bytes; goto out; } i_head++; buf = &pipe->bufs[i_head & p_mask]; } if (pipe_full(i_head, p_tail, pipe->max_usage)) return 0; buf->ops = &page_cache_pipe_buf_ops; buf->flags = 0; get_page(page); buf->page = page; buf->offset = offset; buf->len = bytes; pipe->head = i_head + 1; i->iov_offset = offset + bytes; i->head = i_head; out: i->count -= bytes; return bytes; } /* * Fault in one or more iovecs of the given iov_iter, to a maximum length of * bytes. For each iovec, fault in each page that constitutes the iovec. * * Return 0 on success, or non-zero if the memory could not be accessed (i.e. * because it is an invalid address). */ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) { size_t skip = i->iov_offset; const struct iovec *iov; int err; struct iovec v; if (iter_is_iovec(i)) { iterate_iovec(i, bytes, v, iov, skip, ({ err = fault_in_pages_readable(v.iov_base, v.iov_len); if (unlikely(err)) return err; 0;})) } return 0; } EXPORT_SYMBOL(iov_iter_fault_in_readable); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); direction &= READ | WRITE; /* It will get better. Eventually... */ if (uaccess_kernel()) { i->type = ITER_KVEC | direction; i->kvec = (struct kvec *)iov; } else { i->type = ITER_IOVEC | direction; i->iov = iov; } i->nr_segs = nr_segs; i->iov_offset = 0; i->count = count; } EXPORT_SYMBOL(iov_iter_init); static void memzero_page(struct page *page, size_t offset, size_t len) { char *addr = kmap_atomic(page); memset(addr + offset, 0, len); kunmap_atomic(addr); } static inline bool allocated(struct pipe_buffer *buf) { return buf->ops == &default_pipe_buf_ops; } static inline void data_start(const struct iov_iter *i, unsigned int *iter_headp, size_t *offp) { unsigned int p_mask = i->pipe->ring_size - 1; unsigned int iter_head = i->head; size_t off = i->iov_offset; if (off && (!allocated(&i->pipe->bufs[iter_head & p_mask]) || off == PAGE_SIZE)) { iter_head++; off = 0; } *iter_headp = iter_head; *offp = off; } static size_t push_pipe(struct iov_iter *i, size_t size, int *iter_headp, size_t *offp) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_tail = pipe->tail; unsigned int p_mask = pipe->ring_size - 1; unsigned int iter_head; size_t off; ssize_t left; if (unlikely(size > i->count)) size = i->count; if (unlikely(!size)) return 0; left = size; data_start(i, &iter_head, &off); *iter_headp = iter_head; *offp = off; if (off) { left -= PAGE_SIZE - off; if (left <= 0) { pipe->bufs[iter_head & p_mask].len += size; return size; } pipe->bufs[iter_head & p_mask].len = PAGE_SIZE; iter_head++; } while (!pipe_full(iter_head, p_tail, pipe->max_usage)) { struct pipe_buffer *buf = &pipe->bufs[iter_head & p_mask]; struct page *page = alloc_page(GFP_USER); if (!page) break; buf->ops = &default_pipe_buf_ops; buf->flags = 0; buf->page = page; buf->offset = 0; buf->len = min_t(ssize_t, left, PAGE_SIZE); left -= buf->len; iter_head++; pipe->head = iter_head; if (left == 0) return size; } return size - left; } static size_t copy_pipe_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head; size_t n, off; if (!sanity(i)) return 0; bytes = n = push_pipe(i, bytes, &i_head, &off); if (unlikely(!n)) return 0; do { size_t chunk = min_t(size_t, n, PAGE_SIZE - off); memcpy_to_page(pipe->bufs[i_head & p_mask].page, off, addr, chunk); i->head = i_head; i->iov_offset = off + chunk; n -= chunk; addr += chunk; off = 0; i_head++; } while (n); i->count -= bytes; return bytes; } static __wsum csum_and_memcpy(void *to, const void *from, size_t len, __wsum sum, size_t off) { __wsum next = csum_partial_copy_nocheck(from, to, len); return csum_block_add(sum, next, off); } static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes, struct csum_state *csstate, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; __wsum sum = csstate->csum; size_t off = csstate->off; unsigned int i_head; size_t n, r; if (!sanity(i)) return 0; bytes = n = push_pipe(i, bytes, &i_head, &r); if (unlikely(!n)) return 0; do { size_t chunk = min_t(size_t, n, PAGE_SIZE - r); char *p = kmap_atomic(pipe->bufs[i_head & p_mask].page); sum = csum_and_memcpy(p + r, addr, chunk, sum, off); kunmap_atomic(p); i->head = i_head; i->iov_offset = r + chunk; n -= chunk; off += chunk; addr += chunk; r = 0; i_head++; } while (n); i->count -= bytes; csstate->csum = sum; csstate->off = off; return bytes; } size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; if (unlikely(iov_iter_is_pipe(i))) return copy_pipe_to_iter(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, v, copyout(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len), memcpy_to_page(v.bv_page, v.bv_offset, (from += v.bv_len) - v.bv_len, v.bv_len), memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len) ) return bytes; } EXPORT_SYMBOL(_copy_to_iter); #ifdef CONFIG_ARCH_HAS_COPY_MC static int copyout_mc(void __user *to, const void *from, size_t n) { if (access_ok(to, n)) { instrument_copy_to_user(to, from, n); n = copy_mc_to_user((__force void *) to, from, n); } return n; } static unsigned long copy_mc_to_page(struct page *page, size_t offset, const char *from, size_t len) { unsigned long ret; char *to; to = kmap_atomic(page); ret = copy_mc_to_kernel(to + offset, from, len); kunmap_atomic(to); return ret; } static size_t copy_mc_pipe_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head; size_t n, off, xfer = 0; if (!sanity(i)) return 0; bytes = n = push_pipe(i, bytes, &i_head, &off); if (unlikely(!n)) return 0; do { size_t chunk = min_t(size_t, n, PAGE_SIZE - off); unsigned long rem; rem = copy_mc_to_page(pipe->bufs[i_head & p_mask].page, off, addr, chunk); i->head = i_head; i->iov_offset = off + chunk - rem; xfer += chunk - rem; if (rem) break; n -= chunk; addr += chunk; off = 0; i_head++; } while (n); i->count -= xfer; return xfer; } /** * _copy_mc_to_iter - copy to iter with source memory error exception handling * @addr: source kernel address * @bytes: total transfer length * @iter: destination iterator * * The pmem driver deploys this for the dax operation * (dax_copy_to_iter()) for dax reads (bypass page-cache and the * block-layer). Upon #MC read(2) aborts and returns EIO or the bytes * successfully copied. * * The main differences between this and typical _copy_to_iter(). * * * Typical tail/residue handling after a fault retries the copy * byte-by-byte until the fault happens again. Re-triggering machine * checks is potentially fatal so the implementation uses source * alignment and poison alignment assumptions to avoid re-triggering * hardware exceptions. * * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies. * Compare to copy_to_iter() where only ITER_IOVEC attempts might return * a short copy. */ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; unsigned long rem, curr_addr, s_addr = (unsigned long) addr; if (unlikely(iov_iter_is_pipe(i))) return copy_mc_pipe_to_iter(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, v, copyout_mc(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len), ({ rem = copy_mc_to_page(v.bv_page, v.bv_offset, (from += v.bv_len) - v.bv_len, v.bv_len); if (rem) { curr_addr = (unsigned long) from; bytes = curr_addr - s_addr - rem; return bytes; } }), ({ rem = copy_mc_to_kernel(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len); if (rem) { curr_addr = (unsigned long) from; bytes = curr_addr - s_addr - rem; return bytes; } }) ) return bytes; } EXPORT_SYMBOL_GPL(_copy_mc_to_iter); #endif /* CONFIG_ARCH_HAS_COPY_MC */ size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } if (iter_is_iovec(i)) might_fault(); iterate_and_advance(i, bytes, v, copyin((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) ) return bytes; } EXPORT_SYMBOL(_copy_from_iter); bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return false; } if (unlikely(i->count < bytes)) return false; if (iter_is_iovec(i)) might_fault(); iterate_all_kinds(i, bytes, v, ({ if (copyin((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)) return false; 0;}), memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) ) iov_iter_advance(i, bytes); return true; } EXPORT_SYMBOL(_copy_from_iter_full); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } iterate_and_advance(i, bytes, v, __copy_from_user_inatomic_nocache((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) ) return bytes; } EXPORT_SYMBOL(_copy_from_iter_nocache); #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /** * _copy_from_iter_flushcache - write destination through cpu cache * @addr: destination kernel address * @bytes: total transfer length * @iter: source iterator * * The pmem driver arranges for filesystem-dax to use this facility via * dax_copy_from_iter() for ensuring that writes to persistent memory * are flushed through the CPU cache. It is differentiated from * _copy_from_iter_nocache() in that guarantees all data is flushed for * all iterator types. The _copy_from_iter_nocache() only attempts to * bypass the cache for the ITER_IOVEC case, and on some archs may use * instructions that strand dirty-data in the cache. */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } iterate_and_advance(i, bytes, v, __copy_from_user_flushcache((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), memcpy_page_flushcache((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy_flushcache((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) ) return bytes; } EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache); #endif bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return false; } if (unlikely(i->count < bytes)) return false; iterate_all_kinds(i, bytes, v, ({ if (__copy_from_user_inatomic_nocache((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len)) return false; 0;}), memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) ) iov_iter_advance(i, bytes); return true; } EXPORT_SYMBOL(_copy_from_iter_full_nocache); static inline bool page_copy_sane(struct page *page, size_t offset, size_t n) { struct page *head; size_t v = n + offset; /* * The general case needs to access the page order in order * to compute the page size. * However, we mostly deal with order-0 pages and thus can * avoid a possible cache line miss for requests that fit all * page orders. */ if (n <= v && v <= PAGE_SIZE) return true; head = compound_head(page); v += (page - head) << PAGE_SHIFT; if (likely(n <= v && v <= (page_size(head)))) return true; WARN_ON(1); return false; } size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { if (unlikely(!page_copy_sane(page, offset, bytes))) return 0; if (i->type & (ITER_BVEC|ITER_KVEC)) { void *kaddr = kmap_atomic(page); size_t wanted = copy_to_iter(kaddr + offset, bytes, i); kunmap_atomic(kaddr); return wanted; } else if (unlikely(iov_iter_is_discard(i))) { if (unlikely(i->count < bytes)) bytes = i->count; i->count -= bytes; return bytes; } else if (likely(!iov_iter_is_pipe(i))) return copy_page_to_iter_iovec(page, offset, bytes, i); else return copy_page_to_iter_pipe(page, offset, bytes, i); } EXPORT_SYMBOL(copy_page_to_iter); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { if (unlikely(!page_copy_sane(page, offset, bytes))) return 0; if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return 0; } if (i->type & (ITER_BVEC|ITER_KVEC)) { void *kaddr = kmap_atomic(page); size_t wanted = _copy_from_iter(kaddr + offset, bytes, i); kunmap_atomic(kaddr); return wanted; } else return copy_page_from_iter_iovec(page, offset, bytes, i); } EXPORT_SYMBOL(copy_page_from_iter); static size_t pipe_zero(size_t bytes, struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head; size_t n, off; if (!sanity(i)) return 0; bytes = n = push_pipe(i, bytes, &i_head, &off); if (unlikely(!n)) return 0; do { size_t chunk = min_t(size_t, n, PAGE_SIZE - off); memzero_page(pipe->bufs[i_head & p_mask].page, off, chunk); i->head = i_head; i->iov_offset = off + chunk; n -= chunk; off = 0; i_head++; } while (n); i->count -= bytes; return bytes; } size_t iov_iter_zero(size_t bytes, struct iov_iter *i) { if (unlikely(iov_iter_is_pipe(i))) return pipe_zero(bytes, i); iterate_and_advance(i, bytes, v, clear_user(v.iov_base, v.iov_len), memzero_page(v.bv_page, v.bv_offset, v.bv_len), memset(v.iov_base, 0, v.iov_len) ) return bytes; } EXPORT_SYMBOL(iov_iter_zero); size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes) { char *kaddr = kmap_atomic(page), *p = kaddr + offset; if (unlikely(!page_copy_sane(page, offset, bytes))) { kunmap_atomic(kaddr); return 0; } if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { kunmap_atomic(kaddr); WARN_ON(1); return 0; } iterate_all_kinds(i, bytes, v, copyin((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len), memcpy_from_page((p += v.bv_len) - v.bv_len, v.bv_page, v.bv_offset, v.bv_len), memcpy((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) ) kunmap_atomic(kaddr); return bytes; } EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); static inline void pipe_truncate(struct iov_iter *i) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_tail = pipe->tail; unsigned int p_head = pipe->head; unsigned int p_mask = pipe->ring_size - 1; if (!pipe_empty(p_head, p_tail)) { struct pipe_buffer *buf; unsigned int i_head = i->head; size_t off = i->iov_offset; if (off) { buf = &pipe->bufs[i_head & p_mask]; buf->len = off - buf->offset; i_head++; } while (p_head != i_head) { p_head--; pipe_buf_release(pipe, &pipe->bufs[p_head & p_mask]); } pipe->head = p_head; } } static void pipe_advance(struct iov_iter *i, size_t size) { struct pipe_inode_info *pipe = i->pipe; if (unlikely(i->count < size)) size = i->count; if (size) { struct pipe_buffer *buf; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head = i->head; size_t off = i->iov_offset, left = size; if (off) /* make it relative to the beginning of buffer */ left += off - pipe->bufs[i_head & p_mask].offset; while (1) { buf = &pipe->bufs[i_head & p_mask]; if (left <= buf->len) break; left -= buf->len; i_head++; } i->head = i_head; i->iov_offset = buf->offset + left; } i->count -= size; /* ... and discard everything past that point */ pipe_truncate(i); } void iov_iter_advance(struct iov_iter *i, size_t size) { if (unlikely(iov_iter_is_pipe(i))) { pipe_advance(i, size); return; } if (unlikely(iov_iter_is_discard(i))) { i->count -= size; return; } iterate_and_advance(i, size, v, 0, 0, 0) } EXPORT_SYMBOL(iov_iter_advance); void iov_iter_revert(struct iov_iter *i, size_t unroll) { if (!unroll) return; if (WARN_ON(unroll > MAX_RW_COUNT)) return; i->count += unroll; if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; unsigned int i_head = i->head; size_t off = i->iov_offset; while (1) { struct pipe_buffer *b = &pipe->bufs[i_head & p_mask]; size_t n = off - b->offset; if (unroll < n) { off -= unroll; break; } unroll -= n; if (!unroll && i_head == i->start_head) { off = 0; break; } i_head--; b = &pipe->bufs[i_head & p_mask]; off = b->offset + b->len; } i->iov_offset = off; i->head = i_head; pipe_truncate(i); return; } if (unlikely(iov_iter_is_discard(i))) return; if (unroll <= i->iov_offset) { i->iov_offset -= unroll; return; } unroll -= i->iov_offset; if (iov_iter_is_bvec(i)) { const struct bio_vec *bvec = i->bvec; while (1) { size_t n = (--bvec)->bv_len; i->nr_segs++; if (unroll <= n) { i->bvec = bvec; i->iov_offset = n - unroll; return; } unroll -= n; } } else { /* same logics for iovec and kvec */ const struct iovec *iov = i->iov; while (1) { size_t n = (--iov)->iov_len; i->nr_segs++; if (unroll <= n) { i->iov = iov; i->iov_offset = n - unroll; return; } unroll -= n; } } } EXPORT_SYMBOL(iov_iter_revert); /* * Return the count of just the current iov_iter segment. */ size_t iov_iter_single_seg_count(const struct iov_iter *i) { if (unlikely(iov_iter_is_pipe(i))) return i->count; // it is a silly place, anyway if (i->nr_segs == 1) return i->count; if (unlikely(iov_iter_is_discard(i))) return i->count; else if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); else return min(i->count, i->iov->iov_len - i->iov_offset); } EXPORT_SYMBOL(iov_iter_single_seg_count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); i->type = ITER_KVEC | (direction & (READ | WRITE)); i->kvec = kvec; i->nr_segs = nr_segs; i->iov_offset = 0; i->count = count; } EXPORT_SYMBOL(iov_iter_kvec); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); i->type = ITER_BVEC | (direction & (READ | WRITE)); i->bvec = bvec; i->nr_segs = nr_segs; i->iov_offset = 0; i->count = count; } EXPORT_SYMBOL(iov_iter_bvec); void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count) { BUG_ON(direction != READ); WARN_ON(pipe_full(pipe->head, pipe->tail, pipe->ring_size)); i->type = ITER_PIPE | READ; i->pipe = pipe; i->head = pipe->head; i->iov_offset = 0; i->count = count; i->start_head = i->head; } EXPORT_SYMBOL(iov_iter_pipe); /** * iov_iter_discard - Initialise an I/O iterator that discards data * @i: The iterator to initialise. * @direction: The direction of the transfer. * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator that just discards everything that's written to it. * It's only available as a READ iterator. */ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) { BUG_ON(direction != READ); i->type = ITER_DISCARD | READ; i->count = count; i->iov_offset = 0; } EXPORT_SYMBOL(iov_iter_discard); unsigned long iov_iter_alignment(const struct iov_iter *i) { unsigned long res = 0; size_t size = i->count; if (unlikely(iov_iter_is_pipe(i))) { unsigned int p_mask = i->pipe->ring_size - 1; if (size && i->iov_offset && allocated(&i->pipe->bufs[i->head & p_mask])) return size | i->iov_offset; return size; } iterate_all_kinds(i, size, v, (res |= (unsigned long)v.iov_base | v.iov_len, 0), res |= v.bv_offset | v.bv_len, res |= (unsigned long)v.iov_base | v.iov_len ) return res; } EXPORT_SYMBOL(iov_iter_alignment); unsigned long iov_iter_gap_alignment(const struct iov_iter *i) { unsigned long res = 0; size_t size = i->count; if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return ~0U; } iterate_all_kinds(i, size, v, (res |= (!res ? 0 : (unsigned long)v.iov_base) | (size != v.iov_len ? size : 0), 0), (res |= (!res ? 0 : (unsigned long)v.bv_offset) | (size != v.bv_len ? size : 0)), (res |= (!res ? 0 : (unsigned long)v.iov_base) | (size != v.iov_len ? size : 0)) ); return res; } EXPORT_SYMBOL(iov_iter_gap_alignment); static inline ssize_t __pipe_get_pages(struct iov_iter *i, size_t maxsize, struct page **pages, int iter_head, size_t *start) { struct pipe_inode_info *pipe = i->pipe; unsigned int p_mask = pipe->ring_size - 1; ssize_t n = push_pipe(i, maxsize, &iter_head, start); if (!n) return -EFAULT; maxsize = n; n += *start; while (n > 0) { get_page(*pages++ = pipe->bufs[iter_head & p_mask].page); iter_head++; n -= PAGE_SIZE; } return maxsize; } static ssize_t pipe_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { unsigned int iter_head, npages; size_t capacity; if (!maxsize) return 0; if (!sanity(i)) return -EFAULT; data_start(i, &iter_head, start); /* Amount of free space: some of this one + all after this one */ npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe); capacity = min(npages, maxpages) * PAGE_SIZE - *start; return __pipe_get_pages(i, min(maxsize, capacity), pages, iter_head, start); } ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { if (maxsize > i->count) maxsize = i->count; if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages(i, pages, maxsize, maxpages, start); if (unlikely(iov_iter_is_discard(i))) return -EFAULT; iterate_all_kinds(i, maxsize, v, ({ unsigned long addr = (unsigned long)v.iov_base; size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); int n; int res; if (len > maxpages * PAGE_SIZE) len = maxpages * PAGE_SIZE; addr &= ~(PAGE_SIZE - 1); n = DIV_ROUND_UP(len, PAGE_SIZE); res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE ? FOLL_WRITE : 0, pages); if (unlikely(res <= 0)) return res; return (res == n ? len : res * PAGE_SIZE) - *start; 0;}),({ /* can't be more than PAGE_SIZE */ *start = v.bv_offset; get_page(*pages = v.bv_page); return v.bv_len; }),({ return -EFAULT; }) ) return 0; } EXPORT_SYMBOL(iov_iter_get_pages); static struct page **get_pages_array(size_t n) { return kvmalloc_array(n, sizeof(struct page *), GFP_KERNEL); } static ssize_t pipe_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start) { struct page **p; unsigned int iter_head, npages; ssize_t n; if (!maxsize) return 0; if (!sanity(i)) return -EFAULT; data_start(i, &iter_head, start); /* Amount of free space: some of this one + all after this one */ npages = pipe_space_for_user(iter_head, i->pipe->tail, i->pipe); n = npages * PAGE_SIZE - *start; if (maxsize > n) maxsize = n; else npages = DIV_ROUND_UP(maxsize + *start, PAGE_SIZE); p = get_pages_array(npages); if (!p) return -ENOMEM; n = __pipe_get_pages(i, maxsize, p, iter_head, start); if (n > 0) *pages = p; else kvfree(p); return n; } ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start) { struct page **p; if (maxsize > i->count) maxsize = i->count; if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages_alloc(i, pages, maxsize, start); if (unlikely(iov_iter_is_discard(i))) return -EFAULT; iterate_all_kinds(i, maxsize, v, ({ unsigned long addr = (unsigned long)v.iov_base; size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); int n; int res; addr &= ~(PAGE_SIZE - 1); n = DIV_ROUND_UP(len, PAGE_SIZE); p = get_pages_array(n); if (!p) return -ENOMEM; res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE ? FOLL_WRITE : 0, p); if (unlikely(res <= 0)) { kvfree(p); *pages = NULL; return res; } *pages = p; return (res == n ? len : res * PAGE_SIZE) - *start; 0;}),({ /* can't be more than PAGE_SIZE */ *start = v.bv_offset; *pages = p = get_pages_array(1); if (!p) return -ENOMEM; get_page(*p = v.bv_page); return v.bv_len; }),({ return -EFAULT; }) ) return 0; } EXPORT_SYMBOL(iov_iter_get_pages_alloc); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) { char *to = addr; __wsum sum, next; size_t off = 0; sum = *csum; if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return 0; } iterate_and_advance(i, bytes, v, ({ next = csum_and_copy_from_user(v.iov_base, (to += v.iov_len) - v.iov_len, v.iov_len); if (next) { sum = csum_block_add(sum, next, off); off += v.iov_len; } next ? 0 : v.iov_len; }), ({ char *p = kmap_atomic(v.bv_page); sum = csum_and_memcpy((to += v.bv_len) - v.bv_len, p + v.bv_offset, v.bv_len, sum, off); kunmap_atomic(p); off += v.bv_len; }),({ sum = csum_and_memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len, sum, off); off += v.iov_len; }) ) *csum = sum; return bytes; } EXPORT_SYMBOL(csum_and_copy_from_iter); bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) { char *to = addr; __wsum sum, next; size_t off = 0; sum = *csum; if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return false; } if (unlikely(i->count < bytes)) return false; iterate_all_kinds(i, bytes, v, ({ next = csum_and_copy_from_user(v.iov_base, (to += v.iov_len) - v.iov_len, v.iov_len); if (!next) return false; sum = csum_block_add(sum, next, off); off += v.iov_len; 0; }), ({ char *p = kmap_atomic(v.bv_page); sum = csum_and_memcpy((to += v.bv_len) - v.bv_len, p + v.bv_offset, v.bv_len, sum, off); kunmap_atomic(p); off += v.bv_len; }),({ sum = csum_and_memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len, sum, off); off += v.iov_len; }) ) *csum = sum; iov_iter_advance(i, bytes); return true; } EXPORT_SYMBOL(csum_and_copy_from_iter_full); size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *_csstate, struct iov_iter *i) { struct csum_state *csstate = _csstate; const char *from = addr; __wsum sum, next; size_t off; if (unlikely(iov_iter_is_pipe(i))) return csum_and_copy_to_pipe_iter(addr, bytes, _csstate, i); sum = csstate->csum; off = csstate->off; if (unlikely(iov_iter_is_discard(i))) { WARN_ON(1); /* for now */ return 0; } iterate_and_advance(i, bytes, v, ({ next = csum_and_copy_to_user((from += v.iov_len) - v.iov_len, v.iov_base, v.iov_len); if (next) { sum = csum_block_add(sum, next, off); off += v.iov_len; } next ? 0 : v.iov_len; }), ({ char *p = kmap_atomic(v.bv_page); sum = csum_and_memcpy(p + v.bv_offset, (from += v.bv_len) - v.bv_len, v.bv_len, sum, off); kunmap_atomic(p); off += v.bv_len; }),({ sum = csum_and_memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len, sum, off); off += v.iov_len; }) ) csstate->csum = sum; csstate->off = off; return bytes; } EXPORT_SYMBOL(csum_and_copy_to_iter); size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, struct iov_iter *i) { #ifdef CONFIG_CRYPTO_HASH struct ahash_request *hash = hashp; struct scatterlist sg; size_t copied; copied = copy_to_iter(addr, bytes, i); sg_init_one(&sg, addr, copied); ahash_request_set_crypt(hash, &sg, NULL, copied); crypto_ahash_update(hash); return copied; #else return 0; #endif } EXPORT_SYMBOL(hash_and_copy_to_iter); int iov_iter_npages(const struct iov_iter *i, int maxpages) { size_t size = i->count; int npages = 0; if (!size) return 0; if (unlikely(iov_iter_is_discard(i))) return 0; if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; unsigned int iter_head; size_t off; if (!sanity(i)) return 0; data_start(i, &iter_head, &off); /* some of this one + all after this one */ npages = pipe_space_for_user(iter_head, pipe->tail, pipe); if (npages >= maxpages) return maxpages; } else iterate_all_kinds(i, size, v, ({ unsigned long p = (unsigned long)v.iov_base; npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE) - p / PAGE_SIZE; if (npages >= maxpages) return maxpages; 0;}),({ npages++; if (npages >= maxpages) return maxpages; }),({ unsigned long p = (unsigned long)v.iov_base; npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE) - p / PAGE_SIZE; if (npages >= maxpages) return maxpages; }) ) return npages; } EXPORT_SYMBOL(iov_iter_npages); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) { *new = *old; if (unlikely(iov_iter_is_pipe(new))) { WARN_ON(1); return NULL; } if (unlikely(iov_iter_is_discard(new))) return NULL; if (iov_iter_is_bvec(new)) return new->bvec = kmemdup(new->bvec, new->nr_segs * sizeof(struct bio_vec), flags); else /* iovec and kvec have identical layout */ return new->iov = kmemdup(new->iov, new->nr_segs * sizeof(struct iovec), flags); } EXPORT_SYMBOL(dup_iter); static int copy_compat_iovec_from_user(struct iovec *iov, const struct iovec __user *uvec, unsigned long nr_segs) { const struct compat_iovec __user *uiov = (const struct compat_iovec __user *)uvec; int ret = -EFAULT, i; if (!user_access_begin(uiov, nr_segs * sizeof(*uiov))) return -EFAULT; for (i = 0; i < nr_segs; i++) { compat_uptr_t buf; compat_ssize_t len; unsafe_get_user(len, &uiov[i].iov_len, uaccess_end); unsafe_get_user(buf, &uiov[i].iov_base, uaccess_end); /* check for compat_size_t not fitting in compat_ssize_t .. */ if (len < 0) { ret = -EINVAL; goto uaccess_end; } iov[i].iov_base = compat_ptr(buf); iov[i].iov_len = len; } ret = 0; uaccess_end: user_access_end(); return ret; } static int copy_iovec_from_user(struct iovec *iov, const struct iovec __user *uvec, unsigned long nr_segs) { unsigned long seg; if (copy_from_user(iov, uvec, nr_segs * sizeof(*uvec))) return -EFAULT; for (seg = 0; seg < nr_segs; seg++) { if ((ssize_t)iov[seg].iov_len < 0) return -EINVAL; } return 0; } struct iovec *iovec_from_user(const struct iovec __user *uvec, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat) { struct iovec *iov = fast_iov; int ret; /* * SuS says "The readv() function *may* fail if the iovcnt argument was * less than or equal to 0, or greater than {IOV_MAX}. Linux has * traditionally returned zero for zero segments, so... */ if (nr_segs == 0) return iov; if (nr_segs > UIO_MAXIOV) return ERR_PTR(-EINVAL); if (nr_segs > fast_segs) { iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL); if (!iov) return ERR_PTR(-ENOMEM); } if (compat) ret = copy_compat_iovec_from_user(iov, uvec, nr_segs); else ret = copy_iovec_from_user(iov, uvec, nr_segs); if (ret) { if (iov != fast_iov) kfree(iov); return ERR_PTR(ret); } return iov; } ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat) { ssize_t total_len = 0; unsigned long seg; struct iovec *iov; iov = iovec_from_user(uvec, nr_segs, fast_segs, *iovp, compat); if (IS_ERR(iov)) { *iovp = NULL; return PTR_ERR(iov); } /* * According to the Single Unix Specification we should return EINVAL if * an element length is < 0 when cast to ssize_t or if the total length * would overflow the ssize_t return value of the system call. * * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the * overflow case. */ for (seg = 0; seg < nr_segs; seg++) { ssize_t len = (ssize_t)iov[seg].iov_len; if (!access_ok(iov[seg].iov_base, len)) { if (iov != *iovp) kfree(iov); *iovp = NULL; return -EFAULT; } if (len > MAX_RW_COUNT - total_len) { len = MAX_RW_COUNT - total_len; iov[seg].iov_len = len; } total_len += len; } iov_iter_init(i, type, iov, nr_segs, total_len); if (iov == *iovp) *iovp = NULL; else *iovp = iov; return total_len; } /** * import_iovec() - Copy an array of &struct iovec from userspace * into the kernel, check that it is valid, and initialize a new * &struct iov_iter iterator to access it. * * @type: One of %READ or %WRITE. * @uvec: Pointer to the userspace array. * @nr_segs: Number of elements in userspace array. * @fast_segs: Number of elements in @iov. * @iovp: (input and output parameter) Pointer to pointer to (usually small * on-stack) kernel array. * @i: Pointer to iterator that will be initialized on success. * * If the array pointed to by *@iov is large enough to hold all @nr_segs, * then this function places %NULL in *@iov on return. Otherwise, a new * array will be allocated and the result placed in *@iov. This means that * the caller may call kfree() on *@iov regardless of whether the small * on-stack array was used or not (and regardless of whether this function * returns an error or not). * * Return: Negative error code on error, bytes imported on success */ ssize_t import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i) { return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i, in_compat_syscall()); } EXPORT_SYMBOL(import_iovec); int import_single_range(int rw, void __user *buf, size_t len, struct iovec *iov, struct iov_iter *i) { if (len > MAX_RW_COUNT) len = MAX_RW_COUNT; if (unlikely(!access_ok(buf, len))) return -EFAULT; iov->iov_base = buf; iov->iov_len = len; iov_iter_init(i, rw, iov, 1, len); return 0; } EXPORT_SYMBOL(import_single_range); /** * iov_iter_restore() - Restore a &struct iov_iter to the same state as when * iov_iter_save_state() was called. * * @i: &struct iov_iter to restore * @state: state to restore from * * Used after iov_iter_save_state() to bring restore @i, if operations may * have advanced it. * * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC */ void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) { if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i)) && !iov_iter_is_kvec(i)) return; i->iov_offset = state->iov_offset; i->count = state->count; /* * For the *vec iters, nr_segs + iov is constant - if we increment * the vec, then we also decrement the nr_segs count. Hence we don't * need to track both of these, just one is enough and we can deduct * the other from that. ITER_KVEC and ITER_IOVEC are the same struct * size, so we can just increment the iov pointer as they are unionzed. * ITER_BVEC _may_ be the same size on some archs, but on others it is * not. Be safe and handle it separately. */ BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec)); if (iov_iter_is_bvec(i)) i->bvec -= state->nr_segs - i->nr_segs; else i->iov -= state->nr_segs - i->nr_segs; i->nr_segs = state->nr_segs; } |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGE_REF_H #define _LINUX_PAGE_REF_H #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/tracepoint-defs.h> DECLARE_TRACEPOINT(page_ref_set); DECLARE_TRACEPOINT(page_ref_mod); DECLARE_TRACEPOINT(page_ref_mod_and_test); DECLARE_TRACEPOINT(page_ref_mod_and_return); DECLARE_TRACEPOINT(page_ref_mod_unless); DECLARE_TRACEPOINT(page_ref_freeze); DECLARE_TRACEPOINT(page_ref_unfreeze); #ifdef CONFIG_DEBUG_PAGE_REF /* * Ideally we would want to use the trace_<tracepoint>_enabled() helper * functions. But due to include header file issues, that is not * feasible. Instead we have to open code the static key functions. * * See trace_##name##_enabled(void) in include/linux/tracepoint.h */ #define page_ref_tracepoint_active(t) tracepoint_enabled(t) extern void __page_ref_set(struct page *page, int v); extern void __page_ref_mod(struct page *page, int v); extern void __page_ref_mod_and_test(struct page *page, int v, int ret); extern void __page_ref_mod_and_return(struct page *page, int v, int ret); extern void __page_ref_mod_unless(struct page *page, int v, int u); extern void __page_ref_freeze(struct page *page, int v, int ret); extern void __page_ref_unfreeze(struct page *page, int v); #else #define page_ref_tracepoint_active(t) false static inline void __page_ref_set(struct page *page, int v) { } static inline void __page_ref_mod(struct page *page, int v) { } static inline void __page_ref_mod_and_test(struct page *page, int v, int ret) { } static inline void __page_ref_mod_and_return(struct page *page, int v, int ret) { } static inline void __page_ref_mod_unless(struct page *page, int v, int u) { } static inline void __page_ref_freeze(struct page *page, int v, int ret) { } static inline void __page_ref_unfreeze(struct page *page, int v) { } #endif static inline int page_ref_count(struct page *page) { return atomic_read(&page->_refcount); } static inline int page_count(struct page *page) { return atomic_read(&compound_head(page)->_refcount); } static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_refcount, v); if (page_ref_tracepoint_active(page_ref_set)) __page_ref_set(page, v); } /* * Setup the page count before being freed into the page allocator for * the first time (boot or memory hotplug) */ static inline void init_page_count(struct page *page) { set_page_count(page, 1); } static inline void page_ref_add(struct page *page, int nr) { atomic_add(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, nr); } static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -nr); } static inline int page_ref_sub_return(struct page *page, int nr) { int ret = atomic_sub_return(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -nr, ret); return ret; } static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, 1); } static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod)) __page_ref_mod(page, -1); } static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -nr, ret); return ret; } static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, 1, ret); return ret; } static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_test)) __page_ref_mod_and_test(page, -1, ret); return ret; } static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) __page_ref_mod_and_return(page, -1, ret); return ret; } static inline int page_ref_add_unless(struct page *page, int nr, int u) { int ret = atomic_add_unless(&page->_refcount, nr, u); if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); return ret; } static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); if (page_ref_tracepoint_active(page_ref_freeze)) __page_ref_freeze(page, count, ret); return ret; } static inline void page_ref_unfreeze(struct page *page, int count) { VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); atomic_set_release(&page->_refcount, count); if (page_ref_tracepoint_active(page_ref_unfreeze)) __page_ref_unfreeze(page, count); } #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TASK_WORK_H #define _LINUX_TASK_WORK_H #include <linux/list.h> #include <linux/sched.h> typedef void (*task_work_func_t)(struct callback_head *); static inline void init_task_work(struct callback_head *twork, task_work_func_t func) { twork->func = func; } enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, }; int task_work_add(struct task_struct *task, struct callback_head *twork, enum task_work_notify_mode mode); struct callback_head *task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data); struct callback_head *task_work_cancel_func(struct task_struct *, task_work_func_t); bool task_work_cancel(struct task_struct *task, struct callback_head *cb); void task_work_run(void); static inline void exit_task_work(struct task_struct *task) { task_work_run(); } #endif /* _LINUX_TASK_WORK_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_WORD_AT_A_TIME_H #define _ASM_WORD_AT_A_TIME_H #include <linux/kernel.h> /* * This is largely generic for little-endian machines, but the * optimal byte mask counting is probably going to be something * that is architecture-specific. If you have a reliably fast * bit count instruction, that might be better than the multiply * and shift, for example. */ struct word_at_a_time { const unsigned long one_bits, high_bits; }; #define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } #ifdef CONFIG_64BIT /* * Jan Achrenius on G+: microoptimized version of * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56" * that works for the bytemasks without having to * mask them first. */ static inline long count_masked_bytes(unsigned long mask) { return mask*0x0001020304050608ul >> 56; } #else /* 32-bit case */ /* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ static inline long count_masked_bytes(long mask) { /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ long a = (0x0ff0001+mask) >> 23; /* Fix the 1 for 00 case */ return a & mask; } #endif /* Return nonzero if it has a zero */ static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) { unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; *bits = mask; return mask; } static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c) { return bits; } static inline unsigned long create_zero_mask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } /* The mask we created is directly usable as a bytemask */ #define zero_bytemask(mask) (mask) static inline unsigned long find_zero(unsigned long mask) { return count_masked_bytes(mask); } /* * Load an unaligned word from kernel space. * * In the (very unlikely) case of the word being a page-crosser * and the next page not being mapped, take the exception and * return zeroes in the non-existing part. */ static inline unsigned long load_unaligned_zeropad(const void *addr) { unsigned long ret, dummy; asm( "1:\tmov %2,%0\n" "2:\n" ".section .fixup,\"ax\"\n" "3:\t" "lea %2,%1\n\t" "and %3,%1\n\t" "mov (%1),%0\n\t" "leal %2,%%ecx\n\t" "andl %4,%%ecx\n\t" "shll $3,%%ecx\n\t" "shr %%cl,%0\n\t" "jmp 2b\n" ".previous\n" _ASM_EXTABLE(1b, 3b) :"=&r" (ret),"=&c" (dummy) :"m" (*(unsigned long *)addr), "i" (-sizeof(unsigned long)), "i" (sizeof(unsigned long)-1)); return ret; } #endif /* _ASM_WORD_AT_A_TIME_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Berkeley style UIO structures - Alan Cox 1994. */ #ifndef __LINUX_UIO_H #define __LINUX_UIO_H #include <linux/kernel.h> #include <linux/thread_info.h> #include <uapi/linux/uio.h> struct page; struct pipe_inode_info; struct kvec { void *iov_base; /* and that should *never* hold a userland pointer */ size_t iov_len; }; enum iter_type { /* iter types */ ITER_IOVEC = 4, ITER_KVEC = 8, ITER_BVEC = 16, ITER_PIPE = 32, ITER_DISCARD = 64, }; struct iov_iter_state { size_t iov_offset; size_t count; unsigned long nr_segs; }; struct iov_iter { /* * Bit 0 is the read/write bit, set if we're writing. * Bit 1 is the BVEC_FLAG_NO_REF bit, set if type is a bvec and * the caller isn't expecting to drop a page reference when done. */ unsigned int type; size_t iov_offset; size_t count; union { const struct iovec *iov; const struct kvec *kvec; const struct bio_vec *bvec; struct pipe_inode_info *pipe; }; union { unsigned long nr_segs; struct { unsigned int head; unsigned int start_head; }; }; }; static inline enum iter_type iov_iter_type(const struct iov_iter *i) { return i->type & ~(READ | WRITE); } static inline void iov_iter_save_state(struct iov_iter *iter, struct iov_iter_state *state) { state->iov_offset = iter->iov_offset; state->count = iter->count; state->nr_segs = iter->nr_segs; } static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; } static inline bool iov_iter_is_kvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_KVEC; } static inline bool iov_iter_is_bvec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_BVEC; } static inline bool iov_iter_is_pipe(const struct iov_iter *i) { return iov_iter_type(i) == ITER_PIPE; } static inline bool iov_iter_is_discard(const struct iov_iter *i) { return iov_iter_type(i) == ITER_DISCARD; } static inline unsigned char iov_iter_rw(const struct iov_iter *i) { return i->type & (READ | WRITE); } /* * Total number of bytes covered by an iovec. * * NOTE that it is not safe to use this function until all the iovec's * segment lengths have been validated. Because the individual lengths can * overflow a size_t when added together. */ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs) { unsigned long seg; size_t ret = 0; for (seg = 0; seg < nr_segs; seg++) ret += iov[seg].iov_len; return ret; } static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) { return (struct iovec) { .iov_base = iter->iov->iov_base + iter->iov_offset, .iov_len = min(iter->count, iter->iov->iov_len - iter->iov_offset), }; } size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); void iov_iter_revert(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i); static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, true))) return 0; else return _copy_to_iter(addr, bytes, i); } static __always_inline __must_check size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, false))) return 0; else return _copy_from_iter(addr, bytes, i); } static __always_inline __must_check bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, false))) return false; else return _copy_from_iter_full(addr, bytes, i); } static __always_inline __must_check size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, false))) return 0; else return _copy_from_iter_nocache(addr, bytes, i); } static __always_inline __must_check bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, false))) return false; else return _copy_from_iter_full_nocache(addr, bytes, i); } #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /* * Note, users like pmem that depend on the stricter semantics of * copy_from_iter_flushcache() than copy_from_iter_nocache() must check for * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the * destination is flushed from the cache on return. */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_from_iter_flushcache _copy_from_iter_nocache #endif #ifdef CONFIG_ARCH_HAS_COPY_MC size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); #else #define _copy_mc_to_iter _copy_to_iter #endif static __always_inline __must_check size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, false))) return 0; else return _copy_from_iter_flushcache(addr, bytes, i); } static __always_inline __must_check size_t copy_mc_to_iter(void *addr, size_t bytes, struct iov_iter *i) { if (unlikely(!check_copy_size(addr, bytes, true))) return 0; else return _copy_mc_to_iter(addr, bytes, i); } size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); static inline size_t iov_iter_count(const struct iov_iter *i) { return i->count; } /* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value * greater than the amount of data in iov_iter is fine - it'll just do * nothing in that case. */ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) { /* * count doesn't have to fit in size_t - comparison extends both * operands to u64 here and any value that would be truncated by * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ if (i->count > count) i->count = count; } /* * reexpand a previously truncated iterator; count must be no more than how much * we had shrunk it. */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { i->count = count; } struct csum_state { __wsum csum; size_t off; }; size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csstate, struct iov_iter *i); size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp, struct iov_iter *i); struct iovec *iovec_from_user(const struct iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat); ssize_t import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i); ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat); int import_single_range(int type, void __user *buf, size_t len, struct iovec *iov, struct iov_iter *i); int iov_iter_for_each_range(struct iov_iter *i, size_t bytes, int (*f)(struct kvec *vec, void *context), void *context); #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 | #ifndef _LINUX_HASH_H #define _LINUX_HASH_H /* Fast hashing routine for ints, longs and pointers. (C) 2002 Nadia Yvette Chambers, IBM */ #include <asm/types.h> #include <linux/compiler.h> /* * The "GOLDEN_RATIO_PRIME" is used in ifs/btrfs/brtfs_inode.h and * fs/inode.c. It's not actually prime any more (the previous primes * were actively bad for hashing), but the name remains. */ #if BITS_PER_LONG == 32 #define GOLDEN_RATIO_PRIME GOLDEN_RATIO_32 #define hash_long(val, bits) hash_32(val, bits) #elif BITS_PER_LONG == 64 #define hash_long(val, bits) hash_64(val, bits) #define GOLDEN_RATIO_PRIME GOLDEN_RATIO_64 #else #error Wordsize not 32 or 64 #endif /* * This hash multiplies the input by a large odd number and takes the * high bits. Since multiplication propagates changes to the most * significant end only, it is essential that the high bits of the * product be used for the hash value. * * Chuck Lever verified the effectiveness of this technique: * http://www.citi.umich.edu/techreports/reports/citi-tr-00-1.pdf * * Although a random odd number will do, it turns out that the golden * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice * properties. (See Knuth vol 3, section 6.4, exercise 9.) * * These are the negative, (1 - phi) = phi**2 = (3 - sqrt(5))/2, * which is very slightly easier to multiply by and makes no * difference to the hash distribution. */ #define GOLDEN_RATIO_32 0x61C88647 #define GOLDEN_RATIO_64 0x61C8864680B583EBull #ifdef CONFIG_HAVE_ARCH_HASH /* This header may use the GOLDEN_RATIO_xx constants */ #include <asm/hash.h> #endif /* * The _generic versions exist only so lib/test_hash.c can compare * the arch-optimized versions with the generic. * * Note that if you change these, any <asm/hash.h> that aren't updated * to match need to have their HAVE_ARCH_* define values updated so the * self-test will not false-positive. */ #ifndef HAVE_ARCH__HASH_32 #define __hash_32 __hash_32_generic #endif static inline u32 __hash_32_generic(u32 val) { return val * GOLDEN_RATIO_32; } #ifndef HAVE_ARCH_HASH_32 #define hash_32 hash_32_generic #endif static inline u32 hash_32_generic(u32 val, unsigned int bits) { /* High bits are more random, so use them. */ return __hash_32(val) >> (32 - bits); } #ifndef HAVE_ARCH_HASH_64 #define hash_64 hash_64_generic #endif static __always_inline u32 hash_64_generic(u64 val, unsigned int bits) { #if BITS_PER_LONG == 64 /* 64x64-bit multiply is efficient on all 64-bit processors */ return val * GOLDEN_RATIO_64 >> (64 - bits); #else /* Hash 64 bits using only 32x32-bit multiply. */ return hash_32((u32)val ^ __hash_32(val >> 32), bits); #endif } static inline u32 hash_ptr(const void *ptr, unsigned int bits) { return hash_long((unsigned long)ptr, bits); } /* This really should be called fold32_ptr; it does no hashing to speak of. */ static inline u32 hash32_ptr(const void *ptr) { unsigned long val = (unsigned long)ptr; #if BITS_PER_LONG == 64 val ^= (val >> 32); #endif return (u32)val; } #endif /* _LINUX_HASH_H */ |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/compiler.h> #include <linux/export.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task_stack.h> #include <linux/security.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/mman.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> #include <linux/userfaultfd_k.h> #include <linux/elf.h> #include <linux/elf-randomize.h> #include <linux/personality.h> #include <linux/random.h> #include <linux/processor.h> #include <linux/sizes.h> #include <linux/compat.h> #include <linux/uaccess.h> #include "internal.h" /** * kfree_const - conditionally free memory * @x: pointer to the memory * * Function calls kfree only if @x is not in .rodata section. */ void kfree_const(const void *x) { if (!is_kernel_rodata((unsigned long)x)) kfree(x); } EXPORT_SYMBOL(kfree_const); /** * kstrdup - allocate space for and copy an existing string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s or %NULL in case of error */ char *kstrdup(const char *s, gfp_t gfp) { size_t len; char *buf; if (!s) return NULL; len = strlen(s) + 1; buf = kmalloc_track_caller(len, gfp); if (buf) memcpy(buf, s, len); return buf; } EXPORT_SYMBOL(kstrdup); /** * kstrdup_const - conditionally duplicate an existing const string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Note: Strings allocated by kstrdup_const should be freed by kfree_const and * must not be passed to krealloc(). * * Return: source string if it is in .rodata section otherwise * fallback to kstrdup. */ const char *kstrdup_const(const char *s, gfp_t gfp) { if (is_kernel_rodata((unsigned long)s)) return s; return kstrdup(s, gfp); } EXPORT_SYMBOL(kstrdup_const); /** * kstrndup - allocate space for and copy an existing string * @s: the string to duplicate * @max: read at most @max chars from @s * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Note: Use kmemdup_nul() instead if the size is known exactly. * * Return: newly allocated copy of @s or %NULL in case of error */ char *kstrndup(const char *s, size_t max, gfp_t gfp) { size_t len; char *buf; if (!s) return NULL; len = strnlen(s, max); buf = kmalloc_track_caller(len+1, gfp); if (buf) { memcpy(buf, s, len); buf[len] = '\0'; } return buf; } EXPORT_SYMBOL(kstrndup); /** * kmemdup - duplicate region of memory * * @src: memory region to duplicate * @len: memory region length * @gfp: GFP mask to use * * Return: newly allocated copy of @src or %NULL in case of error */ void *kmemdup(const void *src, size_t len, gfp_t gfp) { void *p; p = kmalloc_track_caller(len, gfp); if (p) memcpy(p, src, len); return p; } EXPORT_SYMBOL(kmemdup); /** * kmemdup_nul - Create a NUL-terminated string from unterminated data * @s: The data to stringify * @len: The size of the data * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s with NUL-termination or %NULL in * case of error */ char *kmemdup_nul(const char *s, size_t len, gfp_t gfp) { char *buf; if (!s) return NULL; buf = kmalloc_track_caller(len + 1, gfp); if (buf) { memcpy(buf, s, len); buf[len] = '\0'; } return buf; } EXPORT_SYMBOL(kmemdup_nul); /** * memdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. Result is physically * contiguous, to be freed by kfree(). */ void *memdup_user(const void __user *src, size_t len) { void *p; p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } return p; } EXPORT_SYMBOL(memdup_user); /** * vmemdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. Result may be not * physically contiguous. Use kvfree() to free. */ void *vmemdup_user(const void __user *src, size_t len) { void *p; p = kvmalloc(len, GFP_USER); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kvfree(p); return ERR_PTR(-EFAULT); } return p; } EXPORT_SYMBOL(vmemdup_user); /** * strndup_user - duplicate an existing string from user space * @s: The string to duplicate * @n: Maximum number of bytes to copy, including the trailing NUL. * * Return: newly allocated copy of @s or an ERR_PTR() in case of error */ char *strndup_user(const char __user *s, long n) { char *p; long length; length = strnlen_user(s, n); if (!length) return ERR_PTR(-EFAULT); if (length > n) return ERR_PTR(-EINVAL); p = memdup_user(s, length); if (IS_ERR(p)) return p; p[length - 1] = '\0'; return p; } EXPORT_SYMBOL(strndup_user); /** * memdup_user_nul - duplicate memory region from user space and NUL-terminate * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. */ void *memdup_user_nul(const void __user *src, size_t len) { char *p; /* * Always use GFP_KERNEL, since copy_from_user() can sleep and * cause pagefault, which makes it pointless to use GFP_NOFS * or GFP_ATOMIC. */ p = kmalloc_track_caller(len + 1, GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } p[len] = '\0'; return p; } EXPORT_SYMBOL(memdup_user_nul); void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev) { struct vm_area_struct *next; vma->vm_prev = prev; if (prev) { next = prev->vm_next; prev->vm_next = vma; } else { next = mm->mmap; mm->mmap = vma; } vma->vm_next = next; if (next) next->vm_prev = vma; } void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma) { struct vm_area_struct *prev, *next; next = vma->vm_next; prev = vma->vm_prev; if (prev) prev->vm_next = next; else mm->mmap = next; if (next) next->vm_prev = prev; } /* Check if the vma is being used as a stack by this task */ int vma_is_stack_for_current(struct vm_area_struct *vma) { struct task_struct * __maybe_unused t = current; return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } #ifndef STACK_RND_MASK #define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */ #endif unsigned long randomize_stack_top(unsigned long stack_top) { unsigned long random_variable = 0; if (current->flags & PF_RANDOMIZE) { random_variable = get_random_long(); random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } #ifdef CONFIG_STACK_GROWSUP return PAGE_ALIGN(stack_top) + random_variable; #else return PAGE_ALIGN(stack_top) - random_variable; #endif } /** * randomize_page - Generate a random, page aligned address * @start: The smallest acceptable address the caller will take. * @range: The size of the area, starting at @start, within which the * random address must fall. * * If @start + @range would overflow, @range is capped. * * NOTE: Historical use of randomize_range, which this replaces, presumed that * @start was already page aligned. We now align it regardless. * * Return: A page aligned address within [start, start + range). On error, * @start is returned. */ unsigned long randomize_page(unsigned long start, unsigned long range) { if (!PAGE_ALIGNED(start)) { range -= PAGE_ALIGN(start) - start; start = PAGE_ALIGN(start); } if (start > ULONG_MAX - range) range = ULONG_MAX - start; range >>= PAGE_SHIFT; if (range == 0) return start; return start + (get_random_long() % range << PAGE_SHIFT); } #ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT unsigned long arch_randomize_brk(struct mm_struct *mm) { /* Is the current task 32bit ? */ if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task()) return randomize_page(mm->brk, SZ_32M); return randomize_page(mm->brk, SZ_1G); } unsigned long arch_mmap_rnd(void) { unsigned long rnd; #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS if (is_compat_task()) rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); else #endif /* CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS */ rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } static int mmap_is_legacy(struct rlimit *rlim_stack) { if (current->personality & ADDR_COMPAT_LAYOUT) return 1; if (rlim_stack->rlim_cur == RLIM_INFINITY) return 1; return sysctl_legacy_va_layout; } /* * Leave enough space between the mmap area and the stack to honour ulimit in * the face of randomisation. */ #define MIN_GAP (SZ_128M) #define MAX_GAP (STACK_TOP / 6 * 5) static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) { unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_guard_gap; /* Account for stack randomization if necessary */ if (current->flags & PF_RANDOMIZE) pad += (STACK_RND_MASK << PAGE_SHIFT); /* Values close to RLIM_INFINITY can overflow. */ if (gap + pad > gap) gap += pad; if (gap < MIN_GAP && MIN_GAP < MAX_GAP) gap = MIN_GAP; else if (gap > MAX_GAP) gap = MAX_GAP; return PAGE_ALIGN(STACK_TOP - gap - rnd); } void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { unsigned long random_factor = 0UL; if (current->flags & PF_RANDOMIZE) random_factor = arch_mmap_rnd(); if (mmap_is_legacy(rlim_stack)) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; mm->get_unmapped_area = arch_get_unmapped_area; } else { mm->mmap_base = mmap_base(random_factor, rlim_stack); mm->get_unmapped_area = arch_get_unmapped_area_topdown; } } #elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; } #endif /** * __account_locked_vm - account locked pages to an mm's locked_vm * @mm: mm to account against * @pages: number of pages to account * @inc: %true if @pages should be considered positive, %false if not * @task: task used to check RLIMIT_MEMLOCK * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped * * Assumes @task and @mm are valid (i.e. at least one reference on each), and * that mmap_lock is held as writer. * * Return: * * 0 on success * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim) { unsigned long locked_vm, limit; int ret = 0; mmap_assert_write_locked(mm); locked_vm = mm->locked_vm; if (inc) { if (!bypass_rlim) { limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT; if (locked_vm + pages > limit) ret = -ENOMEM; } if (!ret) mm->locked_vm = locked_vm + pages; } else { WARN_ON_ONCE(pages > locked_vm); mm->locked_vm = locked_vm - pages; } pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid, (void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT, locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK), ret ? " - exceeded" : ""); return ret; } EXPORT_SYMBOL_GPL(__account_locked_vm); /** * account_locked_vm - account locked pages to an mm's locked_vm * @mm: mm to account against, may be NULL * @pages: number of pages to account * @inc: %true if @pages should be considered positive, %false if not * * Assumes a non-NULL @mm is valid (i.e. at least one reference on it). * * Return: * * 0 on success, or if mm is NULL * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc) { int ret; if (pages == 0 || !mm) return 0; mmap_write_lock(mm); ret = __account_locked_vm(mm, pages, inc, current, capable(CAP_IPC_LOCK)); mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL_GPL(account_locked_vm); unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long pgoff) { unsigned long ret; struct mm_struct *mm = current->mm; unsigned long populate; LIST_HEAD(uf); ret = security_mmap_file(file, prot, flag); if (!ret) { if (mmap_write_lock_killable(mm)) return -EINTR; ret = do_mmap(file, addr, len, prot, flag, pgoff, &populate, &uf); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(ret, populate); } return ret; } unsigned long vm_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long offset) { if (unlikely(offset + PAGE_ALIGN(len) < offset)) return -EINVAL; if (unlikely(offset_in_page(offset))) return -EINVAL; return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT); } EXPORT_SYMBOL(vm_mmap); /** * kvmalloc_node - attempt to allocate physically contiguous memory, but upon * failure, fall back to non-contiguous (vmalloc) allocation. * @size: size of the request. * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL. * @node: numa node to allocate from * * Uses kmalloc to get the memory but if the allocation fails then falls back * to the vmalloc allocator. Use kvfree for freeing the memory. * * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is * preferable to the vmalloc fallback, due to visible performance drawbacks. * * Please note that any use of gfp flags outside of GFP_KERNEL is careful to not * fall back to vmalloc. * * Return: pointer to the allocated memory of %NULL in case of failure */ void *kvmalloc_node(size_t size, gfp_t flags, int node) { gfp_t kmalloc_flags = flags; void *ret; /* * vmalloc uses GFP_KERNEL for some internal allocations (e.g page tables) * so the given set of flags has to be compatible. */ if ((flags & GFP_KERNEL) != GFP_KERNEL) return kmalloc_node(size, flags, node); /* * We want to attempt a large physically contiguous block first because * it is less likely to fragment multiple larger blocks and therefore * contribute to a long term fragmentation less than vmalloc fallback. * However make sure that larger requests are not too disruptive - no * OOM killer and no allocation failure warnings as we have a fallback. */ if (size > PAGE_SIZE) { kmalloc_flags |= __GFP_NOWARN; if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL)) kmalloc_flags |= __GFP_NORETRY; } ret = kmalloc_node(size, kmalloc_flags, node); /* * It doesn't really make sense to fallback to vmalloc for sub page * requests */ if (ret || size <= PAGE_SIZE) return ret; /* Don't even allow crazy sizes */ if (unlikely(size > INT_MAX)) { WARN_ON_ONCE(!(flags & __GFP_NOWARN)); return NULL; } return __vmalloc_node(size, 1, flags, node, __builtin_return_address(0)); } EXPORT_SYMBOL(kvmalloc_node); /** * kvfree() - Free memory. * @addr: Pointer to allocated memory. * * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc(). * It is slightly more efficient to use kfree() or vfree() if you are certain * that you know which one to use. * * Context: Either preemptible task context or not-NMI interrupt. */ void kvfree(const void *addr) { if (is_vmalloc_addr(addr)) vfree(addr); else kfree(addr); } EXPORT_SYMBOL(kvfree); /** * kvfree_sensitive - Free a data object containing sensitive information. * @addr: address of the data object to be freed. * @len: length of the data object. * * Use the special memzero_explicit() function to clear the content of a * kvmalloc'ed object containing sensitive data to make sure that the * compiler won't optimize out the data clearing. */ void kvfree_sensitive(const void *addr, size_t len) { if (likely(!ZERO_OR_NULL_PTR(addr))) { memzero_explicit((void *)addr, len); kvfree(addr); } } EXPORT_SYMBOL(kvfree_sensitive); void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) { void *newp; if (oldsize >= newsize) return (void *)p; newp = kvmalloc(newsize, flags); if (!newp) return NULL; memcpy(newp, p, oldsize); kvfree(p); return newp; } EXPORT_SYMBOL(kvrealloc); static inline void *__page_rmapping(struct page *page) { unsigned long mapping; mapping = (unsigned long)page->mapping; mapping &= ~PAGE_MAPPING_FLAGS; return (void *)mapping; } /** * __vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ void *__vmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return __vmalloc(bytes, flags); } EXPORT_SYMBOL(__vmalloc_array); /** * vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ void *vmalloc_array(size_t n, size_t size) { return __vmalloc_array(n, size, GFP_KERNEL); } EXPORT_SYMBOL(vmalloc_array); /** * __vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ void *__vcalloc(size_t n, size_t size, gfp_t flags) { return __vmalloc_array(n, size, flags | __GFP_ZERO); } EXPORT_SYMBOL(__vcalloc); /** * vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ void *vcalloc(size_t n, size_t size) { return __vmalloc_array(n, size, GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vcalloc); /* Neutral page->mapping pointer to address_space or anon_vma or other */ void *page_rmapping(struct page *page) { page = compound_head(page); return __page_rmapping(page); } /* * Return true if this page is mapped into pagetables. * For compound page it returns true if any subpage of compound page is mapped. */ bool page_mapped(struct page *page) { int i; if (likely(!PageCompound(page))) return atomic_read(&page->_mapcount) >= 0; page = compound_head(page); if (atomic_read(compound_mapcount_ptr(page)) >= 0) return true; if (PageHuge(page)) return false; for (i = 0; i < compound_nr(page); i++) { if (atomic_read(&page[i]._mapcount) >= 0) return true; } return false; } EXPORT_SYMBOL(page_mapped); struct anon_vma *page_anon_vma(struct page *page) { unsigned long mapping; page = compound_head(page); mapping = (unsigned long)page->mapping; if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) return NULL; return __page_rmapping(page); } struct address_space *page_mapping(struct page *page) { struct address_space *mapping; page = compound_head(page); /* This happens if someone calls flush_dcache_page on slab page */ if (unlikely(PageSlab(page))) return NULL; if (unlikely(PageSwapCache(page))) { swp_entry_t entry; entry.val = page_private(page); return swap_address_space(entry); } mapping = page->mapping; if ((unsigned long)mapping & PAGE_MAPPING_ANON) return NULL; return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS); } EXPORT_SYMBOL(page_mapping); /* * For file cache pages, return the address_space, otherwise return NULL */ struct address_space *page_mapping_file(struct page *page) { if (unlikely(PageSwapCache(page))) return NULL; return page_mapping(page); } /* Slow path of page_mapcount() for compound pages */ int __page_mapcount(struct page *page) { int ret; ret = atomic_read(&page->_mapcount) + 1; /* * For file THP page->_mapcount contains total number of mapping * of the page: no need to look into compound_mapcount. */ if (!PageAnon(page) && !PageHuge(page)) return ret; page = compound_head(page); ret += atomic_read(compound_mapcount_ptr(page)) + 1; if (PageDoubleMap(page)) ret--; return ret; } EXPORT_SYMBOL_GPL(__page_mapcount); int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; int sysctl_overcommit_ratio __read_mostly = 50; unsigned long sysctl_overcommit_kbytes __read_mostly; int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_kbytes = 0; return ret; } static void sync_overcommit_as(struct work_struct *dummy) { percpu_counter_sync(&vm_committed_as); } int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int new_policy = -1; int ret; /* * The deviation of sync_overcommit_as could be big with loose policy * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply * with the strict "NEVER", and to avoid possible race condtion (even * though user usually won't too frequently do the switching to policy * OVERCOMMIT_NEVER), the switch is done in the following order: * 1. changing the batch * 2. sync percpu count on each CPU * 3. switch the policy */ if (write) { t = *table; t.data = &new_policy; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || new_policy == -1) return ret; mm_compute_batch(new_policy); if (new_policy == OVERCOMMIT_NEVER) schedule_on_each_cpu(sync_overcommit_as); sysctl_overcommit_memory = new_policy; } else { ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } return ret; } int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_ratio = 0; return ret; } /* * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used */ unsigned long vm_commit_limit(void) { unsigned long allowed; if (sysctl_overcommit_kbytes) allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10); else allowed = ((totalram_pages() - hugetlb_total_pages()) * sysctl_overcommit_ratio / 100); allowed += total_swap_pages; return allowed; } /* * Make sure vm_committed_as in one cacheline and not cacheline shared with * other variables. It can be updated by several CPUs frequently. */ struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp; /* * The global memory commitment made in the system can be a metric * that can be used to drive ballooning decisions when Linux is hosted * as a guest. On Hyper-V, the host implements a policy engine for dynamically * balancing memory across competing virtual machines that are hosted. * Several metrics drive this policy engine including the guest reported * memory commitment. * * The time cost of this is very low for small platforms, and for big * platform like a 2S/36C/72T Skylake server, in worst case where * vm_committed_as's spinlock is under severe contention, the time cost * could be about 30~40 microseconds. */ unsigned long vm_memory_committed(void) { return percpu_counter_sum_positive(&vm_committed_as); } EXPORT_SYMBOL_GPL(vm_memory_committed); /* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to * succeed and -ENOMEM implies there is not. * * We currently support three overcommit policies, which are set via the * vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting.rst * * Strict overcommit modes added 2002 Feb 26 by Alan Cox. * Additional code 2002 Jul 20 by Robert Love. * * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise. * * Note this is a helper function intended to be used by LSMs which * wish to use this logic. */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { long allowed; vm_acct_memory(pages); /* * Sometimes we want to use more memory than we have */ if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS) return 0; if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { if (pages > totalram_pages() + total_swap_pages) goto error; return 0; } allowed = vm_commit_limit(); /* * Reserve some for root */ if (!cap_sys_admin) allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); /* * Don't let a single process grow so big a user can't recover */ if (mm) { long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); allowed -= min_t(long, mm->total_vm / 32, reserve); } if (percpu_counter_read_positive(&vm_committed_as) < allowed) return 0; error: vm_unacct_memory(pages); return -ENOMEM; } /** * get_cmdline() - copy the cmdline value to a buffer. * @task: the task whose cmdline value to copy. * @buffer: the buffer to copy to. * @buflen: the length of the buffer. Larger cmdline values are truncated * to this length. * * Return: the size of the cmdline field copied. Note that the copy does * not guarantee an ending NULL byte. */ int get_cmdline(struct task_struct *task, char *buffer, int buflen) { int res = 0; unsigned int len; struct mm_struct *mm = get_task_mm(task); unsigned long arg_start, arg_end, env_start, env_end; if (!mm) goto out; if (!mm->arg_end) goto out_mm; /* Shh! No looking before we're done */ spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); len = arg_end - arg_start; if (len > buflen) len = buflen; res = access_process_vm(task, arg_start, buffer, len, FOLL_FORCE); /* * If the nul at the end of args has been overwritten, then * assume application is using setproctitle(3). */ if (res > 0 && buffer[res-1] != '\0' && len < buflen) { len = strnlen(buffer, res); if (len < res) { res = len; } else { len = env_end - env_start; if (len > buflen - res) len = buflen - res; res += access_process_vm(task, env_start, buffer+res, len, FOLL_FORCE); res = strnlen(buffer, res); } } out_mm: mmput(mm); out: return res; } int __weak memcmp_pages(struct page *page1, struct page *page2) { char *addr1, *addr2; int ret; addr1 = kmap_atomic(page1); addr2 = kmap_atomic(page2); ret = memcmp(addr1, addr2, PAGE_SIZE); kunmap_atomic(addr2); kunmap_atomic(addr1); return ret; } int mmap_file(struct file *file, struct vm_area_struct *vma) { static const struct vm_operations_struct dummy_vm_ops = {}; int err = call_mmap(file, vma); if (likely(!err)) return 0; /* * OK, we tried to call the file hook for mmap(), but an error * arose. The mapping is in an inconsistent state and we most not invoke * any further hooks on it. */ vma->vm_ops = &dummy_vm_ops; return err; } void vma_close(struct vm_area_struct *vma) { static const struct vm_operations_struct dummy_vm_ops = {}; if (vma->vm_ops && vma->vm_ops->close) { vma->vm_ops->close(vma); /* * The mapping is in an inconsistent state, and no further hooks * may be invoked upon it. */ vma->vm_ops = &dummy_vm_ops; } } |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bitops.h> #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/uaccess.h> #include <linux/nospec.h> /* out-of-line parts */ #ifndef INLINE_COPY_FROM_USER unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { /* * Ensure that bad access_ok() speculation will not * lead to nasty side effects *after* the copy is * finished: */ barrier_nospec(); instrument_copy_from_user(to, from, n); res = raw_copy_from_user(to, from, n); } if (unlikely(res)) memset(to + (n - res), 0, res); return res; } EXPORT_SYMBOL(_copy_from_user); #endif #ifndef INLINE_COPY_TO_USER unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) return n; if (likely(access_ok(to, n))) { instrument_copy_to_user(to, from, n); n = raw_copy_to_user(to, from, n); } return n; } EXPORT_SYMBOL(_copy_to_user); #endif /** * check_zeroed_user: check if a userspace buffer only contains zero bytes * @from: Source address, in userspace. * @size: Size of buffer. * * This is effectively shorthand for "memchr_inv(from, 0, size) == NULL" for * userspace addresses (and is more efficient because we don't care where the * first non-zero byte is). * * Returns: * * 0: There were non-zero bytes present in the buffer. * * 1: The buffer was full of zero bytes. * * -EFAULT: access to userspace failed. */ int check_zeroed_user(const void __user *from, size_t size) { unsigned long val; uintptr_t align = (uintptr_t) from % sizeof(unsigned long); if (unlikely(size == 0)) return 1; from -= align; size += align; if (!user_read_access_begin(from, size)) return -EFAULT; unsafe_get_user(val, (unsigned long __user *) from, err_fault); if (align) val &= ~aligned_byte_mask(align); while (size > sizeof(unsigned long)) { if (unlikely(val)) goto done; from += sizeof(unsigned long); size -= sizeof(unsigned long); unsafe_get_user(val, (unsigned long __user *) from, err_fault); } if (size < sizeof(unsigned long)) val &= aligned_byte_mask(size); done: user_read_access_end(); return (val == 0); err_fault: user_read_access_end(); return -EFAULT; } EXPORT_SYMBOL(check_zeroed_user); |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LOCAL_LOCK_H # error "Do not include directly, include linux/local_lock.h" #endif #include <linux/percpu-defs.h> #include <linux/lockdep.h> typedef struct { #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; struct task_struct *owner; #endif } local_lock_t; #ifdef CONFIG_DEBUG_LOCK_ALLOC # define LOCAL_LOCK_DEBUG_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ .lock_type = LD_LOCK_PERCPU, \ }, \ .owner = NULL, static inline void local_lock_acquire(local_lock_t *l) { lock_map_acquire(&l->dep_map); DEBUG_LOCKS_WARN_ON(l->owner); l->owner = current; } static inline void local_lock_release(local_lock_t *l) { DEBUG_LOCKS_WARN_ON(l->owner != current); l->owner = NULL; lock_map_release(&l->dep_map); } static inline void local_lock_debug_init(local_lock_t *l) { l->owner = NULL; } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) static inline void local_lock_acquire(local_lock_t *l) { } static inline void local_lock_release(local_lock_t *l) { } static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } #define __local_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ LD_LOCK_PERCPU); \ local_lock_debug_init(lock); \ } while (0) #define __local_lock(lock) \ do { \ preempt_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irq(lock) \ do { \ local_irq_disable(); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_lock_irqsave(lock, flags) \ do { \ local_irq_save(flags); \ local_lock_acquire(this_cpu_ptr(lock)); \ } while (0) #define __local_unlock(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ preempt_enable(); \ } while (0) #define __local_unlock_irq(lock) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_enable(); \ } while (0) #define __local_unlock_irqrestore(lock, flags) \ do { \ local_lock_release(this_cpu_ptr(lock)); \ local_irq_restore(flags); \ } while (0) |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 | // SPDX-License-Identifier: GPL-2.0-only /* File: fs/xattr.c Extended attribute handling. Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (C) 2001 SGI - Silicon Graphics, Inc <linux-xfs@oss.sgi.com> Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/fs.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/xattr.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/evm.h> #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fsnotify.h> #include <linux/audit.h> #include <linux/vmalloc.h> #include <linux/posix_acl_xattr.h> #include <linux/uaccess.h> static const char * strcmp_prefix(const char *a, const char *a_prefix) { while (*a_prefix && *a == *a_prefix) { a++; a_prefix++; } return *a_prefix ? NULL : a; } /* * In order to implement different sets of xattr operations for each xattr * prefix, a filesystem should create a null-terminated array of struct * xattr_handler (one for each prefix) and hang a pointer to it off of the * s_xattr field of the superblock. */ #define for_each_xattr_handler(handlers, handler) \ if (handlers) \ for ((handler) = *(handlers)++; \ (handler) != NULL; \ (handler) = *(handlers)++) /* * Find the xattr_handler with the matching prefix. */ static const struct xattr_handler * xattr_resolve_name(struct inode *inode, const char **name) { const struct xattr_handler **handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) return ERR_PTR(-EIO); return ERR_PTR(-EOPNOTSUPP); } for_each_xattr_handler(handlers, handler) { const char *n; n = strcmp_prefix(*name, xattr_prefix(handler)); if (n) { if (!handler->prefix ^ !*n) { if (*n) continue; return ERR_PTR(-EINVAL); } *name = n; return handler; } } return ERR_PTR(-EOPNOTSUPP); } /* * Check permissions for extended attribute access. This is a bit complicated * because different namespaces have very different rules. */ static int xattr_permission(struct inode *inode, const char *name, int mask) { /* * We can never set or remove an extended attribute on a read-only * filesystem or on an immutable / append-only inode. */ if (mask & MAY_WRITE) { if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; /* * Updating an xattr will likely cause i_uid and i_gid * to be writen back improperly if their true value is * unknown to the vfs. */ if (HAS_UNMAPPED_ID(inode)) return -EPERM; } /* * No restriction for security.* and system.* from the VFS. Decision * on these is left to the underlying filesystem / security module. */ if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) || !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN)) return 0; /* * The trusted.* namespace can only be accessed by privileged users. */ if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) { if (!capable(CAP_SYS_ADMIN)) return (mask & MAY_WRITE) ? -EPERM : -ENODATA; return 0; } /* * In the user.* namespace, only regular files and directories can have * extended attributes. For sticky directories, only the owner and * privileged users can write attributes. */ if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) { if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return (mask & MAY_WRITE) ? -EPERM : -ENODATA; if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) && (mask & MAY_WRITE) && !inode_owner_or_capable(inode)) return -EPERM; } return inode_permission(inode, mask); } /* * Look for any handler that deals with the specified namespace. */ int xattr_supported_namespace(struct inode *inode, const char *prefix) { const struct xattr_handler **handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; size_t preflen; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) return -EIO; return -EOPNOTSUPP; } preflen = strlen(prefix); for_each_xattr_handler(handlers, handler) { if (!strncmp(xattr_prefix(handler), prefix, preflen)) return 0; } return -EOPNOTSUPP; } EXPORT_SYMBOL(xattr_supported_namespace); int __vfs_setxattr(struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags) { const struct xattr_handler *handler; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; if (size == 0) value = ""; /* empty EA, do not remove */ return handler->set(handler, dentry, inode, name, value, size, flags); } EXPORT_SYMBOL(__vfs_setxattr); /** * __vfs_setxattr_noperm - perform setxattr operation without performing * permission checks. * * @dentry - object to perform setxattr on * @name - xattr name to set * @value - value to set @name to * @size - size of @value * @flags - flags to pass into filesystem operations * * returns the result of the internal setxattr or setsecurity operations. * * This function requires the caller to lock the inode's i_mutex before it * is executed. It also assumes that the caller will make the appropriate * permission checks. */ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; int error = -EAGAIN; int issec = !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); if (issec) inode->i_flags &= ~S_NOSEC; if (inode->i_opflags & IOP_XATTR) { error = __vfs_setxattr(dentry, inode, name, value, size, flags); if (!error) { fsnotify_xattr(dentry); security_inode_post_setxattr(dentry, name, value, size, flags); } } else { if (unlikely(is_bad_inode(inode))) return -EIO; } if (error == -EAGAIN) { error = -EOPNOTSUPP; if (issec) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; error = security_inode_setsecurity(inode, suffix, value, size, flags); if (!error) fsnotify_xattr(dentry); } } return error; } /** * __vfs_setxattr_locked - set an extended attribute while holding the inode * lock * * @dentry: object to perform setxattr on * @name: xattr name to set * @value: value to set @name to * @size: size of @value * @flags: flags to pass into filesystem operations * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int __vfs_setxattr_locked(struct dentry *dentry, const char *name, const void *value, size_t size, int flags, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(inode, name, MAY_WRITE); if (error) return error; error = security_inode_setxattr(dentry, name, value, size, flags); if (error) goto out; error = try_break_deleg(inode, delegated_inode); if (error) goto out; error = __vfs_setxattr_noperm(dentry, name, value, size, flags); out: return error; } EXPORT_SYMBOL_GPL(__vfs_setxattr_locked); int vfs_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; int error; retry_deleg: inode_lock(inode); error = __vfs_setxattr_locked(dentry, name, value, size, flags, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_setxattr); static ssize_t xattr_getsecurity(struct inode *inode, const char *name, void *value, size_t size) { void *buffer = NULL; ssize_t len; if (!value || !size) { len = security_inode_getsecurity(inode, name, &buffer, false); goto out_noalloc; } len = security_inode_getsecurity(inode, name, &buffer, true); if (len < 0) return len; if (size < len) { len = -ERANGE; goto out; } memcpy(value, buffer, len); out: kfree(buffer); out_noalloc: return len; } /* * vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr * * Allocate memory, if not already allocated, or re-allocate correct size, * before retrieving the extended attribute. * * Returns the result of alloc, if failed, or the getxattr operation. */ ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, size_t xattr_size, gfp_t flags) { const struct xattr_handler *handler; struct inode *inode = dentry->d_inode; char *value = *xattr_value; int error; error = xattr_permission(inode, name, MAY_READ); if (error) return error; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->get) return -EOPNOTSUPP; error = handler->get(handler, dentry, inode, name, NULL, 0); if (error < 0) return error; if (!value || (error > xattr_size)) { value = krealloc(*xattr_value, error + 1, flags); if (!value) return -ENOMEM; memset(value, 0, error + 1); } error = handler->get(handler, dentry, inode, name, value, error); *xattr_value = value; return error; } ssize_t __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { const struct xattr_handler *handler; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->get) return -EOPNOTSUPP; return handler->get(handler, dentry, inode, name, value, size); } EXPORT_SYMBOL(__vfs_getxattr); ssize_t vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(inode, name, MAY_READ); if (error) return error; error = security_inode_getxattr(dentry, name); if (error) return error; if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; int ret = xattr_getsecurity(inode, suffix, value, size); /* * Only overwrite the return value if a security module * is actually active. */ if (ret == -EOPNOTSUPP) goto nolsm; return ret; } nolsm: return __vfs_getxattr(dentry, inode, name, value, size); } EXPORT_SYMBOL_GPL(vfs_getxattr); ssize_t vfs_listxattr(struct dentry *dentry, char *list, size_t size) { struct inode *inode = d_inode(dentry); ssize_t error; error = security_inode_listxattr(dentry); if (error) return error; if (inode->i_op->listxattr && (inode->i_opflags & IOP_XATTR)) { error = inode->i_op->listxattr(dentry, list, size); } else { error = security_inode_listsecurity(inode, list, size); if (size && error > size) error = -ERANGE; } return error; } EXPORT_SYMBOL_GPL(vfs_listxattr); int __vfs_removexattr(struct dentry *dentry, const char *name) { struct inode *inode = d_inode(dentry); const struct xattr_handler *handler; handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); if (!handler->set) return -EOPNOTSUPP; return handler->set(handler, dentry, inode, name, NULL, 0, XATTR_REPLACE); } EXPORT_SYMBOL(__vfs_removexattr); /** * __vfs_removexattr_locked - set an extended attribute while holding the inode * lock * * @dentry: object to perform setxattr on * @name: name of xattr to remove * @delegated_inode: on return, will contain an inode pointer that * a delegation was broken on, NULL if none. */ int __vfs_removexattr_locked(struct dentry *dentry, const char *name, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; error = xattr_permission(inode, name, MAY_WRITE); if (error) return error; error = security_inode_removexattr(dentry, name); if (error) goto out; error = try_break_deleg(inode, delegated_inode); if (error) goto out; error = __vfs_removexattr(dentry, name); if (!error) { fsnotify_xattr(dentry); evm_inode_post_removexattr(dentry, name); } out: return error; } EXPORT_SYMBOL_GPL(__vfs_removexattr_locked); int vfs_removexattr(struct dentry *dentry, const char *name) { struct inode *inode = dentry->d_inode; struct inode *delegated_inode = NULL; int error; retry_deleg: inode_lock(inode); error = __vfs_removexattr_locked(dentry, name, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_removexattr); /* * Extended attribute SET operations */ static long setxattr(struct dentry *d, const char __user *name, const void __user *value, size_t size, int flags) { int error; void *kvalue = NULL; char kname[XATTR_NAME_MAX + 1]; if (flags & ~(XATTR_CREATE|XATTR_REPLACE)) return -EINVAL; error = strncpy_from_user(kname, name, sizeof(kname)); if (error == 0 || error == sizeof(kname)) error = -ERANGE; if (error < 0) return error; if (size) { if (size > XATTR_SIZE_MAX) return -E2BIG; kvalue = kvmalloc(size, GFP_KERNEL); if (!kvalue) return -ENOMEM; if (copy_from_user(kvalue, value, size)) { error = -EFAULT; goto out; } if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) posix_acl_fix_xattr_from_user(kvalue, size); else if (strcmp(kname, XATTR_NAME_CAPS) == 0) { error = cap_convert_nscap(d, &kvalue, size); if (error < 0) goto out; size = error; } } error = vfs_setxattr(d, kname, kvalue, size, flags); out: kvfree(kvalue); return error; } static int path_setxattr(const char __user *pathname, const char __user *name, const void __user *value, size_t size, int flags, unsigned int lookup_flags) { struct path path; int error; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = mnt_want_write(path.mnt); if (!error) { error = setxattr(path.dentry, name, value, size, flags); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE5(setxattr, const char __user *, pathname, const char __user *, name, const void __user *, value, size_t, size, int, flags) { return path_setxattr(pathname, name, value, size, flags, LOOKUP_FOLLOW); } SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname, const char __user *, name, const void __user *, value, size_t, size, int, flags) { return path_setxattr(pathname, name, value, size, flags, 0); } SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, const void __user *,value, size_t, size, int, flags) { struct fd f = fdget(fd); int error = -EBADF; if (!f.file) return error; audit_file(f.file); error = mnt_want_write_file(f.file); if (!error) { error = setxattr(f.file->f_path.dentry, name, value, size, flags); mnt_drop_write_file(f.file); } fdput(f); return error; } /* * Extended attribute GET operations */ static ssize_t getxattr(struct dentry *d, const char __user *name, void __user *value, size_t size) { ssize_t error; void *kvalue = NULL; char kname[XATTR_NAME_MAX + 1]; error = strncpy_from_user(kname, name, sizeof(kname)); if (error == 0 || error == sizeof(kname)) error = -ERANGE; if (error < 0) return error; if (size) { if (size > XATTR_SIZE_MAX) size = XATTR_SIZE_MAX; kvalue = kvzalloc(size, GFP_KERNEL); if (!kvalue) return -ENOMEM; } error = vfs_getxattr(d, kname, kvalue, size); if (error > 0) { if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) posix_acl_fix_xattr_to_user(kvalue, error); if (size && copy_to_user(value, kvalue, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { /* The file system tried to returned a value bigger than XATTR_SIZE_MAX bytes. Not possible. */ error = -E2BIG; } kvfree(kvalue); return error; } static ssize_t path_getxattr(const char __user *pathname, const char __user *name, void __user *value, size_t size, unsigned int lookup_flags) { struct path path; ssize_t error; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = getxattr(path.dentry, name, value, size); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE4(getxattr, const char __user *, pathname, const char __user *, name, void __user *, value, size_t, size) { return path_getxattr(pathname, name, value, size, LOOKUP_FOLLOW); } SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname, const char __user *, name, void __user *, value, size_t, size) { return path_getxattr(pathname, name, value, size, 0); } SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size) { struct fd f = fdget(fd); ssize_t error = -EBADF; if (!f.file) return error; audit_file(f.file); error = getxattr(f.file->f_path.dentry, name, value, size); fdput(f); return error; } /* * Extended attribute LIST operations */ static ssize_t listxattr(struct dentry *d, char __user *list, size_t size) { ssize_t error; char *klist = NULL; if (size) { if (size > XATTR_LIST_MAX) size = XATTR_LIST_MAX; klist = kvmalloc(size, GFP_KERNEL); if (!klist) return -ENOMEM; } error = vfs_listxattr(d, klist, size); if (error > 0) { if (size && copy_to_user(list, klist, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_LIST_MAX) { /* The file system tried to returned a list bigger than XATTR_LIST_MAX bytes. Not possible. */ error = -E2BIG; } kvfree(klist); return error; } static ssize_t path_listxattr(const char __user *pathname, char __user *list, size_t size, unsigned int lookup_flags) { struct path path; ssize_t error; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = listxattr(path.dentry, list, size); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list, size_t, size) { return path_listxattr(pathname, list, size, LOOKUP_FOLLOW); } SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list, size_t, size) { return path_listxattr(pathname, list, size, 0); } SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) { struct fd f = fdget(fd); ssize_t error = -EBADF; if (!f.file) return error; audit_file(f.file); error = listxattr(f.file->f_path.dentry, list, size); fdput(f); return error; } /* * Extended attribute REMOVE operations */ static long removexattr(struct dentry *d, const char __user *name) { int error; char kname[XATTR_NAME_MAX + 1]; error = strncpy_from_user(kname, name, sizeof(kname)); if (error == 0 || error == sizeof(kname)) error = -ERANGE; if (error < 0) return error; return vfs_removexattr(d, kname); } static int path_removexattr(const char __user *pathname, const char __user *name, unsigned int lookup_flags) { struct path path; int error; retry: error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path); if (error) return error; error = mnt_want_write(path.mnt); if (!error) { error = removexattr(path.dentry, name); mnt_drop_write(path.mnt); } path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE2(removexattr, const char __user *, pathname, const char __user *, name) { return path_removexattr(pathname, name, LOOKUP_FOLLOW); } SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname, const char __user *, name) { return path_removexattr(pathname, name, 0); } SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) { struct fd f = fdget(fd); int error = -EBADF; if (!f.file) return error; audit_file(f.file); error = mnt_want_write_file(f.file); if (!error) { error = removexattr(f.file->f_path.dentry, name); mnt_drop_write_file(f.file); } fdput(f); return error; } /* * Combine the results of the list() operation from every xattr_handler in the * list. */ ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { const struct xattr_handler *handler, **handlers = dentry->d_sb->s_xattr; unsigned int size = 0; if (!buffer) { for_each_xattr_handler(handlers, handler) { if (!handler->name || (handler->list && !handler->list(dentry))) continue; size += strlen(handler->name) + 1; } } else { char *buf = buffer; size_t len; for_each_xattr_handler(handlers, handler) { if (!handler->name || (handler->list && !handler->list(dentry))) continue; len = strlen(handler->name); if (len + 1 > buffer_size) return -ERANGE; memcpy(buf, handler->name, len + 1); buf += len + 1; buffer_size -= len + 1; } size = buf - buffer; } return size; } EXPORT_SYMBOL(generic_listxattr); /** * xattr_full_name - Compute full attribute name from suffix * * @handler: handler of the xattr_handler operation * @name: name passed to the xattr_handler operation * * The get and set xattr handler operations are called with the remainder of * the attribute name after skipping the handler's prefix: for example, "foo" * is passed to the get operation of a handler with prefix "user." to get * attribute "user.foo". The full name is still "there" in the name though. * * Note: the list xattr handler operation when called from the vfs is passed a * NULL name; some file systems use this operation internally, with varying * semantics. */ const char *xattr_full_name(const struct xattr_handler *handler, const char *name) { size_t prefix_len = strlen(xattr_prefix(handler)); return name - prefix_len; } EXPORT_SYMBOL(xattr_full_name); /* * Allocate new xattr and copy in the value; but leave the name to callers. */ struct simple_xattr *simple_xattr_alloc(const void *value, size_t size) { struct simple_xattr *new_xattr; size_t len; /* wrap around? */ len = sizeof(*new_xattr) + size; if (len < sizeof(*new_xattr)) return NULL; new_xattr = kvmalloc(len, GFP_KERNEL); if (!new_xattr) return NULL; new_xattr->size = size; memcpy(new_xattr->value, value, size); return new_xattr; } /* * xattr GET operation for in-memory/pseudo filesystems */ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size) { struct simple_xattr *xattr; int ret = -ENODATA; spin_lock(&xattrs->lock); list_for_each_entry(xattr, &xattrs->head, list) { if (strcmp(name, xattr->name)) continue; ret = xattr->size; if (buffer) { if (size < xattr->size) ret = -ERANGE; else memcpy(buffer, xattr->value, xattr->size); } break; } spin_unlock(&xattrs->lock); return ret; } /** * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems * @xattrs: target simple_xattr list * @name: name of the extended attribute * @value: value of the xattr. If %NULL, will remove the attribute. * @size: size of the new xattr * @flags: %XATTR_{CREATE|REPLACE} * @removed_size: returns size of the removed xattr, -1 if none removed * * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails * with -EEXIST. If %XATTR_REPLACE is set, the xattr should exist; * otherwise, fails with -ENODATA. * * Returns 0 on success, -errno on failure. */ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags, ssize_t *removed_size) { struct simple_xattr *xattr; struct simple_xattr *new_xattr = NULL; int err = 0; if (removed_size) *removed_size = -1; /* value == NULL means remove */ if (value) { new_xattr = simple_xattr_alloc(value, size); if (!new_xattr) return -ENOMEM; new_xattr->name = kstrdup(name, GFP_KERNEL); if (!new_xattr->name) { kvfree(new_xattr); return -ENOMEM; } } spin_lock(&xattrs->lock); list_for_each_entry(xattr, &xattrs->head, list) { if (!strcmp(name, xattr->name)) { if (flags & XATTR_CREATE) { xattr = new_xattr; err = -EEXIST; } else if (new_xattr) { list_replace(&xattr->list, &new_xattr->list); if (removed_size) *removed_size = xattr->size; } else { list_del(&xattr->list); if (removed_size) *removed_size = xattr->size; } goto out; } } if (flags & XATTR_REPLACE) { xattr = new_xattr; err = -ENODATA; } else { list_add(&new_xattr->list, &xattrs->head); xattr = NULL; } out: spin_unlock(&xattrs->lock); if (xattr) { kfree(xattr->name); kvfree(xattr); } return err; } static bool xattr_is_trusted(const char *name) { return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } static int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name) { size_t len = strlen(name) + 1; if (*buffer) { if (*remaining_size < len) return -ERANGE; memcpy(*buffer, name, len); *buffer += len; } *remaining_size -= len; return 0; } /* * xattr LIST operation for in-memory/pseudo filesystems */ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size) { bool trusted = ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); struct simple_xattr *xattr; ssize_t remaining_size = size; int err = 0; #ifdef CONFIG_FS_POSIX_ACL if (IS_POSIXACL(inode)) { if (inode->i_acl) { err = xattr_list_one(&buffer, &remaining_size, XATTR_NAME_POSIX_ACL_ACCESS); if (err) return err; } if (inode->i_default_acl) { err = xattr_list_one(&buffer, &remaining_size, XATTR_NAME_POSIX_ACL_DEFAULT); if (err) return err; } } #endif spin_lock(&xattrs->lock); list_for_each_entry(xattr, &xattrs->head, list) { /* skip "trusted." attributes for unprivileged callers */ if (!trusted && xattr_is_trusted(xattr->name)) continue; err = xattr_list_one(&buffer, &remaining_size, xattr->name); if (err) break; } spin_unlock(&xattrs->lock); return err ? err : size - remaining_size; } /* * Adds an extended attribute to the list */ void simple_xattr_list_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr) { spin_lock(&xattrs->lock); list_add(&new_xattr->list, &xattrs->head); spin_unlock(&xattrs->lock); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PGTABLE_H #define _LINUX_PGTABLE_H #include <linux/pfn.h> #include <asm/pgtable.h> #ifndef __ASSEMBLY__ #ifdef CONFIG_MMU #include <linux/mm_types.h> #include <linux/bug.h> #include <linux/errno.h> #include <asm-generic/pgtable_uffd.h> #if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \ defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS #error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED #endif /* * On almost all architectures and configurations, 0 can be used as the * upper ceiling to free_pgtables(): on many architectures it has the same * effect as using TASK_SIZE. However, there is one configuration which * must impose a more careful limit, to avoid freeing kernel pgtables. */ #ifndef USER_PGTABLES_CEILING #define USER_PGTABLES_CEILING 0UL #endif /* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * * The pXx_index() functions return the index of the entry in the page * table page which would control the given virtual address * * As these functions may be used by the same code for different levels of * the page table folding, they are always available, regardless of * CONFIG_PGTABLE_LEVELS value. For the folded levels they simply return 0 * because in such cases PTRS_PER_PxD equals 1. */ static inline unsigned long pte_index(unsigned long address) { return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); } #define pte_index pte_index #ifndef pmd_index static inline unsigned long pmd_index(unsigned long address) { return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); } #define pmd_index pmd_index #endif #ifndef pud_index static inline unsigned long pud_index(unsigned long address) { return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); } #define pud_index pud_index #endif #ifndef pgd_index /* Must be a compile-time constant, so implement it as a macro */ #define pgd_index(a) (((a) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1)) #endif #ifndef pte_offset_kernel static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address) { return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address); } #define pte_offset_kernel pte_offset_kernel #endif #if defined(CONFIG_HIGHPTE) #define pte_offset_map(dir, address) \ ((pte_t *)kmap_atomic(pmd_page(*(dir))) + \ pte_index((address))) #define pte_unmap(pte) kunmap_atomic((pte)) #else #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address)) #define pte_unmap(pte) ((void)(pte)) /* NOP */ #endif /* Find an entry in the second-level page table.. */ #ifndef pmd_offset static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { return pud_pgtable(*pud) + pmd_index(address); } #define pmd_offset pmd_offset #endif #ifndef pud_offset static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) { return p4d_pgtable(*p4d) + pud_index(address); } #define pud_offset pud_offset #endif static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) { return (pgd + pgd_index(address)); }; /* * a shortcut to get a pgd_t in a given mm */ #ifndef pgd_offset #define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address)) #endif /* * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ #ifndef pgd_offset_k #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) #endif /* * In many cases it is known that a virtual address is mapped at PMD or PTE * level, so instead of traversing all the page table levels, we can get a * pointer to the PMD entry in user or kernel page table or translate a virtual * address to the pointer in the PTE in the kernel page tables with simple * helpers. */ static inline pmd_t *pmd_off(struct mm_struct *mm, unsigned long va) { return pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, va), va), va), va); } static inline pmd_t *pmd_off_k(unsigned long va) { return pmd_offset(pud_offset(p4d_offset(pgd_offset_k(va), va), va), va); } static inline pte_t *virt_to_kpte(unsigned long vaddr) { pmd_t *pmd = pmd_off_k(vaddr); return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr); } #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #endif #ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); extern int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty); #else static inline int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { BUILD_BUG(); return 0; } static inline int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t pte = *ptep; int r = 1; if (!pte_young(pte)) r = 0; else set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte)); return r; } #endif #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_t pmd = *pmdp; int r = 1; if (!pmd_young(pmd)) r = 0; else set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd)); return r; } #else static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #endif #ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #else /* * Despite relevant to THP only, this API is called from generic rmap code * under PageTransHuge(), hence needs a dummy implementation for !THP */ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t pte = *ptep; pte_clear(mm, address, ptep); return pte; } #endif #ifndef __HAVE_ARCH_PTEP_GET static inline pte_t ptep_get(pte_t *ptep) { return READ_ONCE(*ptep); } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t pmd = *pmdp; pmd_clear(pmdp); return pmd; } #endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */ #ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pud_t *pudp) { pud_t pud = *pudp; pud_clear(pudp); return pud; } #endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL static inline pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, int full) { return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); } #endif #ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL static inline pud_t pudp_huge_get_and_clear_full(struct mm_struct *mm, unsigned long address, pud_t *pudp, int full) { return pudp_huge_get_and_clear(mm, address, pudp); } #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long address, pte_t *ptep, int full) { pte_t pte; pte = ptep_get_and_clear(mm, address, ptep); return pte; } #endif /* * If two threads concurrently fault at the same page, the thread that * won the race updates the PTE and its local TLB/Cache. The other thread * gives up, simply does nothing, and continues; on architectures where * software can update TLB, local TLB can be updated here to avoid next page * fault. This function updates TLB only, do nothing with cache or others. * It is the difference with function update_mmu_cache. */ #ifndef __HAVE_ARCH_UPDATE_MMU_TLB static inline void update_mmu_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { } #define __HAVE_ARCH_UPDATE_MMU_TLB #endif /* * Some architectures may be able to avoid expensive synchronization * primitives when modifications are made to PTE's which are already * not present, or in the process of an address space destruction. */ #ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL static inline void pte_clear_not_present_full(struct mm_struct *mm, unsigned long address, pte_t *ptep, int full) { pte_clear(mm, address, ptep); } #endif #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH extern pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #endif #ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, pud_t *pudp); #endif #ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT struct mm_struct; static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t old_pte = *ptep; set_pte_at(mm, address, ptep, pte_wrprotect(old_pte)); } #endif /* * On some architectures hardware does not set page access bit when accessing * memory page, it is responsibilty of software setting this bit. It brings * out extra page fault penalty to track page access bit. For optimization page * access bit can be set during all page fault flow on these arches. * To be differentiate with macro pte_mkyoung, this macro is used on platforms * where software maintains page access bit. */ #ifndef pte_sw_mkyoung static inline pte_t pte_sw_mkyoung(pte_t pte) { return pte; } #define pte_sw_mkyoung pte_sw_mkyoung #endif #ifndef pte_savedwrite #define pte_savedwrite pte_write #endif #ifndef pte_mk_savedwrite #define pte_mk_savedwrite pte_mkwrite #endif #ifndef pte_clear_savedwrite #define pte_clear_savedwrite pte_wrprotect #endif #ifndef pmd_savedwrite #define pmd_savedwrite pmd_write #endif #ifndef pmd_mk_savedwrite #define pmd_mk_savedwrite pmd_mkwrite #endif #ifndef pmd_clear_savedwrite #define pmd_clear_savedwrite pmd_wrprotect #endif #ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t old_pmd = *pmdp; set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd)); } #else static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long address, pud_t *pudp) { pud_t old_pud = *pudp; set_pud_at(mm, address, pudp, pud_wrprotect(old_pud)); } #else static inline void pudp_set_wrprotect(struct mm_struct *mm, unsigned long address, pud_t *pudp) { BUILD_BUG(); } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ #endif #ifndef pmdp_collapse_flush #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #else static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { BUILD_BUG(); return *pmdp; } #define pmdp_collapse_flush pmdp_collapse_flush #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pgtable); #endif #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * This is an implementation of pmdp_establish() that is only suitable for an * architecture that doesn't have hardware dirty/accessed bits. In this case we * can't race with CPU which sets these bits and non-atomic aproach is fine. */ static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { pmd_t old_pmd = *pmdp; set_pmd_at(vma->vm_mm, address, pmdp, pmd); return old_pmd; } #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif #ifndef __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { return pte_val(pte_a) == pte_val(pte_b); } #endif #ifndef __HAVE_ARCH_PTE_UNUSED /* * Some architectures provide facilities to virtualization guests * so that they can flag allocated pages as unused. This allows the * host to transparently reclaim unused pages. This function returns * whether the pte's page is unused. */ static inline int pte_unused(pte_t pte) { return 0; } #endif #ifndef pte_access_permitted #define pte_access_permitted(pte, write) \ (pte_present(pte) && (!(write) || pte_write(pte))) #endif #ifndef pmd_access_permitted #define pmd_access_permitted(pmd, write) \ (pmd_present(pmd) && (!(write) || pmd_write(pmd))) #endif #ifndef pud_access_permitted #define pud_access_permitted(pud, write) \ (pud_present(pud) && (!(write) || pud_write(pud))) #endif #ifndef p4d_access_permitted #define p4d_access_permitted(p4d, write) \ (p4d_present(p4d) && (!(write) || p4d_write(p4d))) #endif #ifndef pgd_access_permitted #define pgd_access_permitted(pgd, write) \ (pgd_present(pgd) && (!(write) || pgd_write(pgd))) #endif #ifndef __HAVE_ARCH_PMD_SAME static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b) { return pmd_val(pmd_a) == pmd_val(pmd_b); } static inline int pud_same(pud_t pud_a, pud_t pud_b) { return pud_val(pud_a) == pud_val(pud_b); } #endif #ifndef __HAVE_ARCH_P4D_SAME static inline int p4d_same(p4d_t p4d_a, p4d_t p4d_b) { return p4d_val(p4d_a) == p4d_val(p4d_b); } #endif #ifndef __HAVE_ARCH_PGD_SAME static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) { return pgd_val(pgd_a) == pgd_val(pgd_b); } #endif /* * Use set_p*_safe(), and elide TLB flushing, when confident that *no* * TLB flush will be required as a result of the "set". For example, use * in scenarios where it is known ahead of time that the routine is * setting non-present entries, or re-setting an existing entry to the * same value. Otherwise, use the typical "set" helpers and flush the * TLB. */ #define set_pte_safe(ptep, pte) \ ({ \ WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ set_pte(ptep, pte); \ }) #define set_pmd_safe(pmdp, pmd) \ ({ \ WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ set_pmd(pmdp, pmd); \ }) #define set_pud_safe(pudp, pud) \ ({ \ WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ set_pud(pudp, pud); \ }) #define set_p4d_safe(p4dp, p4d) \ ({ \ WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ set_p4d(p4dp, p4d); \ }) #define set_pgd_safe(pgdp, pgd) \ ({ \ WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ set_pgd(pgdp, pgd); \ }) #ifndef __HAVE_ARCH_DO_SWAP_PAGE /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be * restored when the page is swapped back in. SPARC M7 and newer * processors support an ADI (Application Data Integrity) tag for the * page as metadata for the page. arch_do_swap_page() can restore this * metadata when a page is swapped back in. */ static inline void arch_do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t pte, pte_t oldpte) { } #endif #ifndef __HAVE_ARCH_UNMAP_ONE /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be * restored when the page is swapped back in. SPARC M7 and newer * processors support an ADI (Application Data Integrity) tag for the * page as metadata for the page. arch_unmap_one() can save this * metadata on a swap-out of a page. */ static inline int arch_unmap_one(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t orig_pte) { return 0; } #endif /* * Allow architectures to preserve additional metadata associated with * swapped-out pages. The corresponding __HAVE_ARCH_SWAP_* macros and function * prototypes must be defined in the arch-specific asm/pgtable.h file. */ #ifndef __HAVE_ARCH_PREPARE_TO_SWAP static inline int arch_prepare_to_swap(struct page *page) { return 0; } #endif #ifndef __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) { } static inline void arch_swap_invalidate_area(int type) { } #endif #ifndef __HAVE_ARCH_SWAP_RESTORE static inline void arch_swap_restore(swp_entry_t entry, struct page *page) { } #endif #ifndef __HAVE_ARCH_PGD_OFFSET_GATE #define pgd_offset_gate(mm, addr) pgd_offset(mm, addr) #endif #ifndef __HAVE_ARCH_MOVE_PTE #define move_pte(pte, prot, old_addr, new_addr) (pte) #endif #ifndef pte_accessible # define pte_accessible(mm, pte) ((void)(pte), 1) #endif #ifndef flush_tlb_fix_spurious_fault #define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) #endif /* * When walking page tables, get the address of the next boundary, * or the end address of the range if that comes earlier. Although no * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout. */ #define pgd_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #ifndef p4d_addr_end #define p4d_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif #ifndef pud_addr_end #define pud_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif #ifndef pmd_addr_end #define pmd_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \ (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) #endif /* * When walking page tables, we usually want to skip any p?d_none entries; * and any p?d_bad entries - reporting the error before resetting to none. * Do the tests inline, but report and clear the bad entry in mm/memory.c. */ void pgd_clear_bad(pgd_t *); #ifndef __PAGETABLE_P4D_FOLDED void p4d_clear_bad(p4d_t *); #else #define p4d_clear_bad(p4d) do { } while (0) #endif #ifndef __PAGETABLE_PUD_FOLDED void pud_clear_bad(pud_t *); #else #define pud_clear_bad(p4d) do { } while (0) #endif void pmd_clear_bad(pmd_t *); static inline int pgd_none_or_clear_bad(pgd_t *pgd) { if (pgd_none(*pgd)) return 1; if (unlikely(pgd_bad(*pgd))) { pgd_clear_bad(pgd); return 1; } return 0; } static inline int p4d_none_or_clear_bad(p4d_t *p4d) { if (p4d_none(*p4d)) return 1; if (unlikely(p4d_bad(*p4d))) { p4d_clear_bad(p4d); return 1; } return 0; } static inline int pud_none_or_clear_bad(pud_t *pud) { if (pud_none(*pud)) return 1; if (unlikely(pud_bad(*pud))) { pud_clear_bad(pud); return 1; } return 0; } static inline int pmd_none_or_clear_bad(pmd_t *pmd) { if (pmd_none(*pmd)) return 1; if (unlikely(pmd_bad(*pmd))) { pmd_clear_bad(pmd); return 1; } return 0; } static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { /* * Get the current pte state, but zero it out to make it * non-present, preventing the hardware from asynchronously * updating it. */ return ptep_get_and_clear(vma->vm_mm, addr, ptep); } static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte) { /* * The pte is non-present, so there's no hardware state to * preserve. */ set_pte_at(vma->vm_mm, addr, ptep, pte); } #ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION /* * Start a pte protection read-modify-write transaction, which * protects against asynchronous hardware modifications to the pte. * The intention is not to prevent the hardware from making pte * updates, but to prevent any updates it may make from being lost. * * This does not protect against other software modifications of the * pte; the appropriate pte lock must be held over the transation. * * Note that this interface is intended to be batchable, meaning that * ptep_modify_prot_commit may not actually update the pte, but merely * queue the update to be done at some later time. The update must be * actually committed before the pte lock is released, however. */ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return __ptep_modify_prot_start(vma, addr, ptep); } /* * Commit an update to a pte, leaving any hardware-controlled bits in * the PTE unmodified. */ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { __ptep_modify_prot_commit(vma, addr, ptep, pte); } #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */ #endif /* CONFIG_MMU */ /* * No-op macros that just return the current protection value. Defined here * because these macros can be used even if CONFIG_MMU is not defined. */ #ifndef pgprot_nx #define pgprot_nx(prot) (prot) #endif #ifndef pgprot_noncached #define pgprot_noncached(prot) (prot) #endif #ifndef pgprot_writecombine #define pgprot_writecombine pgprot_noncached #endif #ifndef pgprot_writethrough #define pgprot_writethrough pgprot_noncached #endif #ifndef pgprot_device #define pgprot_device pgprot_noncached #endif #ifndef pgprot_mhp #define pgprot_mhp(prot) (prot) #endif #ifdef CONFIG_MMU #ifndef pgprot_modify #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot))) newprot = pgprot_noncached(newprot); if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot))) newprot = pgprot_writecombine(newprot); if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot))) newprot = pgprot_device(newprot); return newprot; } #endif #endif /* CONFIG_MMU */ #ifndef pgprot_encrypted #define pgprot_encrypted(prot) (prot) #endif #ifndef pgprot_decrypted #define pgprot_decrypted(prot) (prot) #endif /* * A facility to provide lazy MMU batching. This allows PTE updates and * page invalidations to be delayed until a call to leave lazy MMU mode * is issued. Some architectures may benefit from doing this, and it is * beneficial for both shadow and direct mode hypervisors, which may batch * the PTE updates which happen during this window. Note that using this * interface requires that read hazards be removed from the code. A read * hazard could result in the direct mode hypervisor case, since the actual * write to the page tables may not yet have taken place, so reads though * a raw PTE pointer after it has been modified are not guaranteed to be * up to date. This mode can only be entered and left under the protection of * the page table locks for all page tables which may be modified. In the UP * case, this is required so that preemption is disabled, and in the SMP case, * it must synchronize the delayed page table writes properly on other CPUs. */ #ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE #define arch_enter_lazy_mmu_mode() do {} while (0) #define arch_leave_lazy_mmu_mode() do {} while (0) #define arch_flush_lazy_mmu_mode() do {} while (0) #endif /* * A facility to provide batching of the reload of page tables and * other process state with the actual context switch code for * paravirtualized guests. By convention, only one of the batched * update (lazy) modes (CPU, MMU) should be active at any given time, * entry should never be nested, and entry and exits should always be * paired. This is for sanity of maintaining and reasoning about the * kernel code. In this case, the exit (end of the context switch) is * in architecture-specific code, and so doesn't need a generic * definition. */ #ifndef __HAVE_ARCH_START_CONTEXT_SWITCH #define arch_start_context_switch(prev) do {} while (0) #endif #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY #ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd; } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return 0; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd; } #endif #else /* !CONFIG_HAVE_ARCH_SOFT_DIRTY */ static inline int pte_soft_dirty(pte_t pte) { return 0; } static inline int pmd_soft_dirty(pmd_t pmd) { return 0; } static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) { return pmd; } static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) { return pmd; } static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { return pte; } static inline int pte_swp_soft_dirty(pte_t pte) { return 0; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return pte; } static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd; } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return 0; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd; } #endif #ifndef __HAVE_PFNMAP_TRACKING /* * Interfaces that can be used by architecture code to keep track of * memory type of pfn mappings specified by the remap_pfn_range, * vmf_insert_pfn. */ /* * track_pfn_remap is called when a _new_ pfn mapping is being established * by remap_pfn_range() for physical range indicated by pfn and size. */ static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size) { return 0; } /* * track_pfn_insert is called when a _new_ single pfn is established * by vmf_insert_pfn(). */ static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn) { } /* * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). */ static inline int track_pfn_copy(struct vm_area_struct *vma) { return 0; } /* * untrack_pfn is called while unmapping a pfnmap for a region. * untrack can be called for a specific region indicated by pfn and size or * can be for the entire vma (in which case pfn, size are zero). */ static inline void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size) { } /* * untrack_pfn_moved is called while mremapping a pfnmap for a new region. */ static inline void untrack_pfn_moved(struct vm_area_struct *vma) { } #else extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long addr, unsigned long size); extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn); extern int track_pfn_copy(struct vm_area_struct *vma); extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size); extern void untrack_pfn_moved(struct vm_area_struct *vma); #endif #ifdef __HAVE_COLOR_ZERO_PAGE static inline int is_zero_pfn(unsigned long pfn) { extern unsigned long zero_pfn; unsigned long offset_from_zero_pfn = pfn - zero_pfn; return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT); } #define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) #else static inline int is_zero_pfn(unsigned long pfn) { extern unsigned long zero_pfn; return pfn == zero_pfn; } static inline unsigned long my_zero_pfn(unsigned long addr) { extern unsigned long zero_pfn; return zero_pfn; } #endif #ifdef CONFIG_MMU #ifndef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_trans_huge(pmd_t pmd) { return 0; } #ifndef pmd_write static inline int pmd_write(pmd_t pmd) { BUG(); return 0; } #endif /* pmd_write */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifndef pud_write static inline int pud_write(pud_t pud) { BUG(); return 0; } #endif /* pud_write */ #if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) static inline int pmd_devmap(pmd_t pmd) { return 0; } static inline int pud_devmap(pud_t pud) { return 0; } static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \ (defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)) static inline int pud_trans_huge(pud_t pud) { return 0; } #endif /* See pmd_none_or_trans_huge_or_clear_bad for discussion. */ static inline int pud_none_or_trans_huge_or_dev_or_clear_bad(pud_t *pud) { pud_t pudval = READ_ONCE(*pud); if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval)) return 1; if (unlikely(pud_bad(pudval))) { pud_clear_bad(pud); return 1; } return 0; } /* See pmd_trans_unstable for discussion. */ static inline int pud_trans_unstable(pud_t *pud) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) return pud_none_or_trans_huge_or_dev_or_clear_bad(pud); #else return 0; #endif } #ifndef pmd_read_atomic static inline pmd_t pmd_read_atomic(pmd_t *pmdp) { /* * Depend on compiler for an atomic pmd read. NOTE: this is * only going to work, if the pmdval_t isn't larger than * an unsigned long. */ return *pmdp; } #endif #ifndef arch_needs_pgtable_deposit #define arch_needs_pgtable_deposit() (false) #endif /* * This function is meant to be used by sites walking pagetables with * the mmap_lock held in read mode to protect against MADV_DONTNEED and * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd * into a null pmd and the transhuge page fault can convert a null pmd * into an hugepmd or into a regular pmd (if the hugepage allocation * fails). While holding the mmap_lock in read mode the pmd becomes * stable and stops changing under us only if it's not null and not a * transhuge pmd. When those races occurs and this function makes a * difference vs the standard pmd_none_or_clear_bad, the result is * undefined so behaving like if the pmd was none is safe (because it * can return none anyway). The compiler level barrier() is critically * important to compute the two checks atomically on the same pmdval. * * For 32bit kernels with a 64bit large pmd_t this automatically takes * care of reading the pmd atomically to avoid SMP race conditions * against pmd_populate() when the mmap_lock is hold for reading by the * caller (a special atomic read not done by "gcc" as in the generic * version above, is also needed when THP is disabled because the page * fault can populate the pmd from under us). */ static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd) { pmd_t pmdval = pmd_read_atomic(pmd); /* * The barrier will stabilize the pmdval in a register or on * the stack so that it will stop changing under the code. * * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE, * pmd_read_atomic is allowed to return a not atomic pmdval * (for example pointing to an hugepage that has never been * mapped in the pmd). The below checks will only care about * the low part of the pmd with 32bit PAE x86 anyway, with the * exception of pmd_none(). So the important thing is that if * the low part of the pmd is found null, the high part will * be also null or the pmd_none() check below would be * confused. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE barrier(); #endif /* * !pmd_present() checks for pmd migration entries * * The complete check uses is_pmd_migration_entry() in linux/swapops.h * But using that requires moving current function and pmd_trans_unstable() * to linux/swapops.h to resovle dependency, which is too much code move. * * !pmd_present() is equivalent to is_pmd_migration_entry() currently, * because !pmd_present() pages can only be under migration not swapped * out. * * pmd_none() is preseved for future condition checks on pmd migration * entries and not confusing with this function name, although it is * redundant with !pmd_present(). */ if (pmd_none(pmdval) || pmd_trans_huge(pmdval) || (IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION) && !pmd_present(pmdval))) return 1; if (unlikely(pmd_bad(pmdval))) { pmd_clear_bad(pmd); return 1; } return 0; } /* * This is a noop if Transparent Hugepage Support is not built into * the kernel. Otherwise it is equivalent to * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in * places that already verified the pmd is not none and they want to * walk ptes while holding the mmap sem in read mode (write mode don't * need this). If THP is not enabled, the pmd can't go away under the * code even if MADV_DONTNEED runs, but if THP is enabled we need to * run a pmd_trans_unstable before walking the ptes after * split_huge_pmd returns (because it may have run when the pmd become * null, but then a page fault can map in a THP and not a regular page). */ static inline int pmd_trans_unstable(pmd_t *pmd) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE return pmd_none_or_trans_huge_or_clear_bad(pmd); #else return 0; #endif } #ifndef CONFIG_NUMA_BALANCING /* * Technically a PTE can be PROTNONE even when not doing NUMA balancing but * the only case the kernel cares is for NUMA balancing and is only ever set * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked * _PAGE_PROTNONE so by default, implement the helper as "always no". It * is the responsibility of the caller to distinguish between PROT_NONE * protections and NUMA hinting fault protections. */ static inline int pte_protnone(pte_t pte) { return 0; } static inline int pmd_protnone(pmd_t pmd) { return 0; } #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_MMU */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP #ifndef __PAGETABLE_P4D_FOLDED int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot); int p4d_clear_huge(p4d_t *p4d); #else static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int p4d_clear_huge(p4d_t *p4d) { return 0; } #endif /* !__PAGETABLE_P4D_FOLDED */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); int pmd_clear_huge(pmd_t *pmd); int p4d_free_pud_page(p4d_t *p4d, unsigned long addr); int pud_free_pmd_page(pud_t *pud, unsigned long addr); int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { return 0; } static inline int p4d_clear_huge(p4d_t *p4d) { return 0; } static inline int pud_clear_huge(pud_t *pud) { return 0; } static inline int pmd_clear_huge(pmd_t *pmd) { return 0; } static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) { return 0; } static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr) { return 0; } static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) { return 0; } #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * ARCHes with special requirements for evicting THP backing TLB entries can * implement this. Otherwise also, it can help optimize normal TLB flush in * THP regime. Stock flush_tlb_range() typically has optimization to nuke the * entire TLB if flush span is greater than a threshold, which will * likely be true for a single huge page. Thus a single THP flush will * invalidate the entire TLB which is not desirable. * e.g. see arch/arc: flush_pmd_tlb_range */ #define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #else #define flush_pmd_tlb_range(vma, addr, end) BUILD_BUG() #define flush_pud_tlb_range(vma, addr, end) BUILD_BUG() #endif #endif struct file; int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot); #ifndef CONFIG_X86_ESPFIX64 static inline void init_espfix_bsp(void) { } #endif extern void __init pgtable_cache_init(void); #ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot) { return true; } static inline bool arch_has_pfn_modify_check(void) { return false; } #endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */ /* * Architecture PAGE_KERNEL_* fallbacks * * Some architectures don't define certain PAGE_KERNEL_* flags. This is either * because they really don't support them, or the port needs to be updated to * reflect the required functionality. Below are a set of relatively safe * fallbacks, as best effort, which we can count on in lieu of the architectures * not defining them on their own yet. */ #ifndef PAGE_KERNEL_RO # define PAGE_KERNEL_RO PAGE_KERNEL #endif #ifndef PAGE_KERNEL_EXEC # define PAGE_KERNEL_EXEC PAGE_KERNEL #endif /* * Page Table Modification bits for pgtbl_mod_mask. * * These are used by the p?d_alloc_track*() set of functions an in the generic * vmalloc/ioremap code to track at which page-table levels entries have been * modified. Based on that the code can better decide when vmalloc and ioremap * mapping changes need to be synchronized to other page-tables in the system. */ #define __PGTBL_PGD_MODIFIED 0 #define __PGTBL_P4D_MODIFIED 1 #define __PGTBL_PUD_MODIFIED 2 #define __PGTBL_PMD_MODIFIED 3 #define __PGTBL_PTE_MODIFIED 4 #define PGTBL_PGD_MODIFIED BIT(__PGTBL_PGD_MODIFIED) #define PGTBL_P4D_MODIFIED BIT(__PGTBL_P4D_MODIFIED) #define PGTBL_PUD_MODIFIED BIT(__PGTBL_PUD_MODIFIED) #define PGTBL_PMD_MODIFIED BIT(__PGTBL_PMD_MODIFIED) #define PGTBL_PTE_MODIFIED BIT(__PGTBL_PTE_MODIFIED) /* Page-Table Modification Mask */ typedef unsigned int pgtbl_mod_mask; #endif /* !__ASSEMBLY__ */ #if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT) #ifdef CONFIG_PHYS_ADDR_T_64BIT /* * ZSMALLOC needs to know the highest PFN on 32-bit architectures * with physical address space extension, but falls back to * BITS_PER_LONG otherwise. */ #error Missing MAX_POSSIBLE_PHYSMEM_BITS definition #else #define MAX_POSSIBLE_PHYSMEM_BITS 32 #endif #endif #ifndef has_transparent_hugepage #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define has_transparent_hugepage() 1 #else #define has_transparent_hugepage() 0 #endif #endif /* * On some architectures it depends on the mm if the p4d/pud or pmd * layer of the page table hierarchy is folded or not. */ #ifndef mm_p4d_folded #define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED) #endif #ifndef mm_pud_folded #define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED) #endif #ifndef mm_pmd_folded #define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) #endif #ifndef p4d_offset_lockless #define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address) #endif #ifndef pud_offset_lockless #define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address) #endif #ifndef pmd_offset_lockless #define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address) #endif /* * p?d_leaf() - true if this entry is a final mapping to a physical address. * This differs from p?d_huge() by the fact that they are always available (if * the architecture supports large pages at the appropriate level) even * if CONFIG_HUGETLB_PAGE is not defined. * Only meaningful when called on a valid entry. */ #ifndef pgd_leaf #define pgd_leaf(x) 0 #endif #ifndef p4d_leaf #define p4d_leaf(x) 0 #endif #ifndef pud_leaf #define pud_leaf(x) 0 #endif #ifndef pmd_leaf #define pmd_leaf(x) 0 #endif #endif /* _LINUX_PGTABLE_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Credentials management - see Documentation/security/credentials.rst * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_CRED_H #define _LINUX_CRED_H #include <linux/capability.h> #include <linux/init.h> #include <linux/key.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/sched.h> #include <linux/sched/user.h> struct cred; struct inode; /* * COW Supplementary groups list */ struct group_info { atomic_t usage; int ngroups; kgid_t gid[0]; } __randomize_layout; /** * get_group_info - Get a reference to a group info structure * @group_info: The group info to reference * * This gets a reference to a set of supplementary groups. * * If the caller is accessing a task's credentials, they must hold the RCU read * lock when reading. */ static inline struct group_info *get_group_info(struct group_info *gi) { atomic_inc(&gi->usage); return gi; } /** * put_group_info - Release a reference to a group info structure * @group_info: The group info to release */ #define put_group_info(group_info) \ do { \ if (atomic_dec_and_test(&(group_info)->usage)) \ groups_free(group_info); \ } while (0) extern struct group_info init_groups; #ifdef CONFIG_MULTIUSER extern struct group_info *groups_alloc(int); extern void groups_free(struct group_info *); extern int in_group_p(kgid_t); extern int in_egroup_p(kgid_t); extern int groups_search(const struct group_info *, kgid_t); extern int set_current_groups(struct group_info *); extern void set_groups(struct cred *, struct group_info *); extern bool may_setgroups(void); extern void groups_sort(struct group_info *); #else static inline void groups_free(struct group_info *group_info) { } static inline int in_group_p(kgid_t grp) { return 1; } static inline int in_egroup_p(kgid_t grp) { return 1; } static inline int groups_search(const struct group_info *group_info, kgid_t grp) { return 1; } #endif /* * The security context of a task * * The parts of the context break down into two categories: * * (1) The objective context of a task. These parts are used when some other * task is attempting to affect this one. * * (2) The subjective context. These details are used when the task is acting * upon another object, be that a file, a task, a key or whatever. * * Note that some members of this structure belong to both categories - the * LSM security pointer for instance. * * A task has two security pointers. task->real_cred points to the objective * context that defines that task's actual details. The objective part of this * context is used whenever that task is acted upon. * * task->cred points to the subjective context that defines the details of how * that task is going to act upon another object. This may be overridden * temporarily to point to another security context, but normally points to the * same context as task->real_cred. */ struct cred { atomic_long_t usage; #ifdef CONFIG_DEBUG_CREDENTIALS atomic_t subscribers; /* number of processes subscribed */ void *put_addr; unsigned magic; #define CRED_MAGIC 0x43736564 #define CRED_MAGIC_DEAD 0x44656144 #endif kuid_t uid; /* real UID of the task */ kgid_t gid; /* real GID of the task */ kuid_t suid; /* saved UID of the task */ kgid_t sgid; /* saved GID of the task */ kuid_t euid; /* effective UID of the task */ kgid_t egid; /* effective GID of the task */ kuid_t fsuid; /* UID for VFS ops */ kgid_t fsgid; /* GID for VFS ops */ unsigned securebits; /* SUID-less security management */ kernel_cap_t cap_inheritable; /* caps our children can inherit */ kernel_cap_t cap_permitted; /* caps we're permitted */ kernel_cap_t cap_effective; /* caps we can actually use */ kernel_cap_t cap_bset; /* capability bounding set */ kernel_cap_t cap_ambient; /* Ambient capability set */ #ifdef CONFIG_KEYS unsigned char jit_keyring; /* default keyring to attach requested * keys to */ struct key *session_keyring; /* keyring inherited over fork */ struct key *process_keyring; /* keyring private to this process */ struct key *thread_keyring; /* keyring private to this thread */ struct key *request_key_auth; /* assumed request_key authority */ #endif #ifdef CONFIG_SECURITY void *security; /* subjective LSM security */ #endif struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ struct group_info *group_info; /* supplementary groups for euid/fsgid */ /* RCU deletion */ union { int non_rcu; /* Can we skip RCU deletion? */ struct rcu_head rcu; /* RCU deletion hook */ }; } __randomize_layout; extern void __put_cred(struct cred *); extern void exit_creds(struct task_struct *); extern int copy_creds(struct task_struct *, unsigned long); extern const struct cred *get_task_cred(struct task_struct *); extern struct cred *cred_alloc_blank(void); extern struct cred *prepare_creds(void); extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern const struct cred *override_creds(const struct cred *); extern void revert_creds(const struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); extern int change_create_files_as(struct cred *, struct inode *); extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); /* * check for validity of credentials */ #ifdef CONFIG_DEBUG_CREDENTIALS extern void __invalid_creds(const struct cred *, const char *, unsigned); extern void __validate_process_creds(struct task_struct *, const char *, unsigned); extern bool creds_are_invalid(const struct cred *cred); static inline void __validate_creds(const struct cred *cred, const char *file, unsigned line) { if (unlikely(creds_are_invalid(cred))) __invalid_creds(cred, file, line); } #define validate_creds(cred) \ do { \ __validate_creds((cred), __FILE__, __LINE__); \ } while(0) #define validate_process_creds() \ do { \ __validate_process_creds(current, __FILE__, __LINE__); \ } while(0) extern void validate_creds_for_do_exit(struct task_struct *); #else static inline void validate_creds(const struct cred *cred) { } static inline void validate_creds_for_do_exit(struct task_struct *tsk) { } static inline void validate_process_creds(void) { } #endif static inline bool cap_ambient_invariant_ok(const struct cred *cred) { return cap_issubset(cred->cap_ambient, cap_intersect(cred->cap_permitted, cred->cap_inheritable)); } /** * get_new_cred - Get a reference on a new set of credentials * @cred: The new credentials to reference * * Get a reference on the specified set of new credentials. The caller must * release the reference. */ static inline struct cred *get_new_cred(struct cred *cred) { atomic_long_inc(&cred->usage); return cred; } /** * get_cred - Get a reference on a set of credentials * @cred: The credentials to reference * * Get a reference on the specified set of credentials. The caller must * release the reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. Although the * pointer is const, this will temporarily discard the const and increment the * usage count. The purpose of this is to attempt to catch at compile time the * accidental alteration of a set of credentials that should be considered * immutable. */ static inline const struct cred *get_cred(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; validate_creds(cred); nonconst_cred->non_rcu = 0; return get_new_cred(nonconst_cred); } static inline const struct cred *get_cred_rcu(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return NULL; if (!atomic_long_inc_not_zero(&nonconst_cred->usage)) return NULL; validate_creds(cred); nonconst_cred->non_rcu = 0; return cred; } /** * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * * Release a reference to a set of credentials, deleting them when the last ref * is released. If %NULL is passed, nothing is done. * * This takes a const pointer to a set of credentials because the credentials * on task_struct are attached by const pointers to prevent accidental * alteration of otherwise immutable credential sets. */ static inline void put_cred(const struct cred *_cred) { struct cred *cred = (struct cred *) _cred; if (cred) { validate_creds(cred); if (atomic_long_dec_and_test(&(cred)->usage)) __put_cred(cred); } } /** * current_cred - Access the current task's subjective credentials * * Access the subjective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_cred() \ rcu_dereference_protected(current->cred, 1) /** * current_real_cred - Access the current task's objective credentials * * Access the objective credentials of the current task. RCU-safe, * since nobody else can modify it. */ #define current_real_cred() \ rcu_dereference_protected(current->real_cred, 1) /** * __task_cred - Access a task's objective credentials * @task: The task to query * * Access the objective credentials of a task. The caller must hold the RCU * readlock. * * The result of this function should not be passed directly to get_cred(); * rather get_task_cred() should be used instead. */ #define __task_cred(task) \ rcu_dereference((task)->real_cred) /** * get_current_cred - Get the current task's subjective credentials * * Get the subjective credentials of the current task, pinning them so that * they can't go away. Accessing the current task's credentials directly is * not permitted. */ #define get_current_cred() \ (get_cred(current_cred())) /** * get_current_user - Get the current task's user_struct * * Get the user record of the current task, pinning it so that it can't go * away. */ #define get_current_user() \ ({ \ struct user_struct *__u; \ const struct cred *__cred; \ __cred = current_cred(); \ __u = get_uid(__cred->user); \ __u; \ }) /** * get_current_groups - Get the current task's supplementary group list * * Get the supplementary group list of the current task, pinning it so that it * can't go away. */ #define get_current_groups() \ ({ \ struct group_info *__groups; \ const struct cred *__cred; \ __cred = current_cred(); \ __groups = get_group_info(__cred->group_info); \ __groups; \ }) #define task_cred_xxx(task, xxx) \ ({ \ __typeof__(((struct cred *)NULL)->xxx) ___val; \ rcu_read_lock(); \ ___val = __task_cred((task))->xxx; \ rcu_read_unlock(); \ ___val; \ }) #define task_uid(task) (task_cred_xxx((task), uid)) #define task_euid(task) (task_cred_xxx((task), euid)) #define current_cred_xxx(xxx) \ ({ \ current_cred()->xxx; \ }) #define current_uid() (current_cred_xxx(uid)) #define current_gid() (current_cred_xxx(gid)) #define current_euid() (current_cred_xxx(euid)) #define current_egid() (current_cred_xxx(egid)) #define current_suid() (current_cred_xxx(suid)) #define current_sgid() (current_cred_xxx(sgid)) #define current_fsuid() (current_cred_xxx(fsuid)) #define current_fsgid() (current_cred_xxx(fsgid)) #define current_cap() (current_cred_xxx(cap_effective)) #define current_user() (current_cred_xxx(user)) extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS #define current_user_ns() (current_cred_xxx(user_ns)) #else static inline struct user_namespace *current_user_ns(void) { return &init_user_ns; } #endif #define current_uid_gid(_uid, _gid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_uid) = __cred->uid; \ *(_gid) = __cred->gid; \ } while(0) #define current_euid_egid(_euid, _egid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_euid) = __cred->euid; \ *(_egid) = __cred->egid; \ } while(0) #define current_fsuid_fsgid(_fsuid, _fsgid) \ do { \ const struct cred *__cred; \ __cred = current_cred(); \ *(_fsuid) = __cred->fsuid; \ *(_fsgid) = __cred->fsgid; \ } while(0) #endif /* _LINUX_CRED_H */ |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMZONE_H #define _LINUX_MMZONE_H #ifndef __ASSEMBLY__ #ifndef __GENERATING_BOUNDS_H #include <linux/spinlock.h> #include <linux/list.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/numa.h> #include <linux/init.h> #include <linux/seqlock.h> #include <linux/nodemask.h> #include <linux/pageblock-flags.h> #include <linux/page-flags-layout.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <asm/page.h> /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_FORCE_MAX_ZONEORDER #define MAX_ORDER 11 #else #define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER #endif #define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed * costly to service. That is between allocation orders which should * coalesce naturally under reasonable reclaim pressure and those which * will not. */ #define PAGE_ALLOC_COSTLY_ORDER 3 enum migratetype { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RECLAIMABLE, MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES, #ifdef CONFIG_CMA /* * MIGRATE_CMA migration type is designed to mimic the way * ZONE_MOVABLE works. Only movable pages can be allocated * from MIGRATE_CMA pageblocks and page allocator never * implicitly change migration type of MIGRATE_CMA pageblock. * * The way to use it is to change migratetype of a range of * pageblocks to MIGRATE_CMA which can be done by * __free_pageblock_cma() function. What is important though * is that a range of pageblocks must be aligned to * MAX_ORDER_NR_PAGES should biggest page be bigger then * a single pageblock. */ MIGRATE_CMA, #endif #ifdef CONFIG_MEMORY_ISOLATION MIGRATE_ISOLATE, /* can't allocate from here */ #endif MIGRATE_TYPES }; /* In mm/page_alloc.c; keep in sync also with show_migration_types() there */ extern const char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) # define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) #else # define is_migrate_cma(migratetype) false # define is_migrate_cma_page(_page) false #endif static inline bool is_migrate_movable(int mt) { return is_migrate_cma(mt) || mt == MIGRATE_MOVABLE; } #define for_each_migratetype_order(order, type) \ for (order = 0; order < MAX_ORDER; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; #define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1) #define get_pageblock_migratetype(page) \ get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK) struct free_area { struct list_head free_list[MIGRATE_TYPES]; unsigned long nr_free; }; static inline struct page *get_page_from_free_area(struct free_area *area, int migratetype) { return list_first_entry_or_null(&area->free_list[migratetype], struct page, lru); } static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } struct pglist_data; /* * zone->lock and the zone lru_lock are two of the hottest locks in the kernel. * So add a wild amount of padding here to ensure that they fall into separate * cachelines. There are very few zone structures in the machine, so space * consumption is not a concern here. */ #if defined(CONFIG_SMP) struct zone_padding { char x[0]; } ____cacheline_internodealigned_in_smp; #define ZONE_PADDING(name) struct zone_padding name; #else #define ZONE_PADDING(name) #endif #ifdef CONFIG_NUMA enum numa_stat_item { NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ NUMA_FOREIGN, /* was intended here, hit elsewhere */ NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ NR_VM_NUMA_STAT_ITEMS }; #else #define NR_VM_NUMA_STAT_ITEMS 0 #endif enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */ NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE, NR_ZONE_ACTIVE_ANON, NR_ZONE_INACTIVE_FILE, NR_ZONE_ACTIVE_FILE, NR_ZONE_UNEVICTABLE, NR_ZONE_WRITE_PENDING, /* Count of dirty, writeback and unstable pages */ NR_MLOCK, /* mlock()ed pages found and moved off LRU */ NR_PAGETABLE, /* used for pagetables */ /* Second 128 byte cacheline */ NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ #endif NR_FREE_CMA_PAGES, NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { NR_LRU_BASE, NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ NR_ACTIVE_ANON, /* " " " " " */ NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ NR_SLAB_RECLAIMABLE_B, NR_SLAB_UNRECLAIMABLE_B, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_ANON = WORKINGSET_REFAULT_BASE, WORKINGSET_REFAULT_FILE, WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_ANON = WORKINGSET_ACTIVATE_BASE, WORKINGSET_ACTIVATE_FILE, WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_ANON = WORKINGSET_RESTORE_BASE, WORKINGSET_RESTORE_FILE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_SHMEM_THPS, NR_SHMEM_PMDMAPPED, NR_FILE_THPS, NR_FILE_PMDMAPPED, NR_ANON_THPS, NR_VMSCAN_WRITE, NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ NR_KERNEL_STACK_KB, /* measured in KiB */ #if IS_ENABLED(CONFIG_SHADOW_CALL_STACK) NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_VM_NODE_STAT_ITEMS }; /* * Returns true if the value is measured in bytes (most vmstat values are * measured in pages). This defines the API part, the internal representation * might be different. */ static __always_inline bool vmstat_item_in_bytes(int idx) { /* * Global and per-node slab counters track slab pages. * It's expected that changes are multiples of PAGE_SIZE. * Internally values are stored in pages. * * Per-memcg and per-lruvec counters track memory, consumed * by individual slab objects. These counters are actually * byte-precise. */ return (idx == NR_SLAB_RECLAIMABLE_B || idx == NR_SLAB_UNRECLAIMABLE_B); } /* * We do arithmetic on the LRU lists in various places in the code, * so it is important to keep the active lists LRU_ACTIVE higher in * the array than the corresponding inactive lists, and to keep * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists. * * This has to be kept in sync with the statistics in zone_stat_item * above and the descriptions in vmstat_text in mm/vmstat.c */ #define LRU_BASE 0 #define LRU_ACTIVE 1 #define LRU_FILE 2 enum lru_list { LRU_INACTIVE_ANON = LRU_BASE, LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE, LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE, LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE, LRU_UNEVICTABLE, NR_LRU_LISTS }; #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) static inline bool is_file_lru(enum lru_list lru) { return (lru == LRU_INACTIVE_FILE || lru == LRU_ACTIVE_FILE); } static inline bool is_active_lru(enum lru_list lru) { return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE); } #define ANON_AND_FILE 2 enum lruvec_flags { LRUVEC_CONGESTED, /* lruvec has many dirty pages * backed by a congested BDI */ }; struct lruvec { struct list_head lists[NR_LRU_LISTS]; /* * These track the cost of reclaiming one LRU - file or anon - * over the other. As the observed cost of reclaiming one LRU * increases, the reclaim scan balance tips toward the other. */ unsigned long anon_cost; unsigned long file_cost; /* Non-resident age, driven by LRU movement */ atomic_long_t nonresident_age; /* Refaults at the time of last reclaim cycle */ unsigned long refaults[ANON_AND_FILE]; /* Various lruvec state flags (enum lruvec_flags) */ unsigned long flags; #ifdef CONFIG_MEMCG struct pglist_data *pgdat; #endif }; /* Isolate unmapped pages */ #define ISOLATE_UNMAPPED ((__force isolate_mode_t)0x2) /* Isolate for asynchronous migration */ #define ISOLATE_ASYNC_MIGRATE ((__force isolate_mode_t)0x4) /* Isolate unevictable pages */ #define ISOLATE_UNEVICTABLE ((__force isolate_mode_t)0x8) /* LRU Isolation modes. */ typedef unsigned __bitwise isolate_mode_t; enum zone_watermarks { WMARK_MIN, WMARK_LOW, WMARK_HIGH, NR_WMARK }; #define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) struct per_cpu_pages { int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int batch; /* chunk size for buddy add/remove */ /* Lists of pages, one per migrate type stored on the pcp-lists */ struct list_head lists[MIGRATE_PCPTYPES]; }; struct per_cpu_pageset { struct per_cpu_pages pcp; #ifdef CONFIG_NUMA s8 expire; u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; #endif #ifdef CONFIG_SMP s8 stat_threshold; s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; #endif }; struct per_cpu_nodestat { s8 stat_threshold; s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS]; }; #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { /* * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able * to DMA to all of the addressable memory (ZONE_NORMAL). * On architectures where this area covers the whole 32 bit address * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller * DMA addressing constraints. This distinction is important as a 32bit * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit * platforms may need both zones as they support peripherals with * different DMA addressing limitations. */ #ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 ZONE_DMA32, #endif /* * Normal addressable memory is in ZONE_NORMAL. DMA operations can be * performed on pages in ZONE_NORMAL if the DMA devices support * transfers to all addressable memory. */ ZONE_NORMAL, #ifdef CONFIG_HIGHMEM /* * A memory area that is only addressable by the kernel through * mapping portions into its own address space. This is for example * used by i386 to allow the kernel to address the memory beyond * 900MB. The kernel will set up special mappings (page * table entries on i386) for each page that the kernel needs to * access. */ ZONE_HIGHMEM, #endif /* * ZONE_MOVABLE is similar to ZONE_NORMAL, except that it contains * movable pages with few exceptional cases described below. Main use * cases for ZONE_MOVABLE are to make memory offlining/unplug more * likely to succeed, and to locally limit unmovable allocations - e.g., * to increase the number of THP/huge pages. Notable special cases are: * * 1. Pinned pages: (long-term) pinning of movable pages might * essentially turn such pages unmovable. Memory offlining might * retry a long time. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. * 3. Memory holes: kernelcore/movablecore setups might create very rare * situations where ZONE_MOVABLE contains memory holes after boot, * for example, if we have sections that are only partially * populated. Memory offlining and allocations fail early. * 4. PG_hwpoison pages: while poisoned pages can be skipped during * memory offlining, such pages cannot be allocated. * 5. Unmovable PG_offline pages: in paravirtualized environments, * hotplugged memory blocks might only partially be managed by the * buddy (e.g., via XEN-balloon, Hyper-V balloon, virtio-mem). The * parts not manged by the buddy are unmovable PG_offline pages. In * some cases (virtio-mem), such pages can be skipped during * memory offlining, however, cannot be moved/allocated. These * techniques might use alloc_contig_range() to hide previously * exposed pages from the buddy again (e.g., to implement some sort * of memory unplug in virtio-mem). * * In general, no unmovable allocations that degrade memory offlining * should end up in ZONE_MOVABLE. Allocators (like alloc_contig_range()) * have to expect that migrating pages in ZONE_MOVABLE can fail (even * if has_unmovable_pages() states that there are no unmovable pages, * there can be false negatives). */ ZONE_MOVABLE, #ifdef CONFIG_ZONE_DEVICE ZONE_DEVICE, #endif __MAX_NR_ZONES }; #ifndef __GENERATING_BOUNDS_H #define ASYNC_AND_SYNC 2 struct zone { /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long _watermark[NR_WMARK]; unsigned long watermark_boost; unsigned long nr_reserved_highatomic; /* * We don't know if the memory that we're going to allocate will be * freeable or/and it will be released eventually, so to avoid totally * wasting several GB of ram we must reserve some of the lower zone * memory (otherwise we risk to run OOM on the lower zones despite * there being tons of freeable ram on the higher zones). This array is * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl * changes. */ long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NEED_MULTIPLE_NODES int node; #endif struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; #ifndef CONFIG_SPARSEMEM /* * Flags for a pageblock_nr_pages block. See pageblock-flags.h. * In SPARSEMEM, this map is stored in struct mem_section */ unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; /* * spanned_pages is the total pages spanned by the zone, including * holes, which is calculated as: * spanned_pages = zone_end_pfn - zone_start_pfn; * * present_pages is physical pages existing within the zone, which * is calculated as: * present_pages = spanned_pages - absent_pages(pages in holes); * * managed_pages is present pages managed by the buddy system, which * is calculated as (reserved_pages includes pages allocated by the * bootmem allocator): * managed_pages = present_pages - reserved_pages; * * So present_pages may be used by memory hotplug or memory power * management logic to figure out unmanaged pages by checking * (present_pages - managed_pages). And managed_pages should be used * by page allocator and vm scanner to calculate all kinds of watermarks * and thresholds. * * Locking rules: * * zone_start_pfn and spanned_pages are protected by span_seqlock. * It is a seqlock because it has to be read outside of zone->lock, * and it is done in the main allocator path. But, it is written * quite infrequently. * * The span_seq lock is declared along with zone->lock because it is * frequently read in proximity to zone->lock. It's good to * give them a chance of being in the same cacheline. * * Write access to present_pages at runtime should be protected by * mem_hotplug_begin/end(). Any reader who can't tolerant drift of * present_pages should get_online_mems() to get a stable value. */ atomic_long_t managed_pages; unsigned long spanned_pages; unsigned long present_pages; const char *name; #ifdef CONFIG_MEMORY_ISOLATION /* * Number of isolated pageblock. It is used to solve incorrect * freepage counting problem due to racy retrieving migratetype * of pageblock. Protected by zone->lock. */ unsigned long nr_isolate_pageblock; #endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; #endif int initialized; /* Write-intensive fields used from the page allocator */ ZONE_PADDING(_pad1_) /* free areas of different sizes */ struct free_area free_area[MAX_ORDER]; /* zone flags, see below */ unsigned long flags; /* Primarily protects free_area */ spinlock_t lock; /* Write-intensive fields used by compaction and vmstats. */ ZONE_PADDING(_pad2_) /* * When free pages are below this point, additional steps are taken * when reading the number of free pages to avoid per-cpu counter * drift allowing watermarks to be breached */ unsigned long percpu_drift_mark; #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* pfn where compaction free scanner should start */ unsigned long compact_cached_free_pfn; /* pfn where compaction migration scanner should start */ unsigned long compact_cached_migrate_pfn[ASYNC_AND_SYNC]; unsigned long compact_init_migrate_pfn; unsigned long compact_init_free_pfn; #endif #ifdef CONFIG_COMPACTION /* * On compaction failure, 1<<compact_defer_shift compactions * are skipped before trying again. The number attempted since * last failure is tracked with compact_considered. * compact_order_failed is the minimum compaction failed order. */ unsigned int compact_considered; unsigned int compact_defer_shift; int compact_order_failed; #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* Set to true when the PG_migrate_skip bits should be cleared */ bool compact_blockskip_flush; #endif bool contiguous; ZONE_PADDING(_pad3_) /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { PGDAT_DIRTY, /* reclaim scanning has recently found * many dirty file pages at the tail * of the LRU. */ PGDAT_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ PGDAT_RECLAIM_LOCKED, /* prevents concurrent reclaim */ }; enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ }; static inline unsigned long zone_managed_pages(struct zone *zone) { return (unsigned long)atomic_long_read(&zone->managed_pages); } static inline unsigned long zone_end_pfn(const struct zone *zone) { return zone->zone_start_pfn + zone->spanned_pages; } static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) { return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone); } static inline bool zone_is_initialized(struct zone *zone) { return zone->initialized; } static inline bool zone_is_empty(struct zone *zone) { return zone->spanned_pages == 0; } /* * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty * intersection with the given zone */ static inline bool zone_intersects(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { if (zone_is_empty(zone)) return false; if (start_pfn >= zone_end_pfn(zone) || start_pfn + nr_pages <= zone->zone_start_pfn) return false; return true; } /* * The "priority" of VM scanning is how much of the queues we will scan in one * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the * queues ("queue_length >> 12") during an aging round. */ #define DEF_PRIORITY 12 /* Maximum number of zones on a zonelist */ #define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES) enum { ZONELIST_FALLBACK, /* zonelist with fallback */ #ifdef CONFIG_NUMA /* * The NUMA zonelists are doubled because we need zonelists that * restrict the allocations to a single node for __GFP_THISNODE. */ ZONELIST_NOFALLBACK, /* zonelist without fallback (__GFP_THISNODE) */ #endif MAX_ZONELISTS }; /* * This struct contains information about a zone in a zonelist. It is stored * here to avoid dereferences into large structures and lookups of tables */ struct zoneref { struct zone *zone; /* Pointer to actual zone */ int zone_idx; /* zone_idx(zoneref->zone) */ }; /* * One allocation request operates on a zonelist. A zonelist * is a list of zones, the first one is the 'goal' of the * allocation, the other zones are fallback zones, in decreasing * priority. * * To speed the reading of the zonelist, the zonerefs contain the zone index * of the entry being read. Helper functions to access information given * a struct zoneref are * * zonelist_zone() - Return the struct zone * for an entry in _zonerefs * zonelist_zone_idx() - Return the index of the zone for an entry * zonelist_node_idx() - Return the index of the node for an entry */ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; #ifndef CONFIG_DISCONTIGMEM /* The array of struct pages - for discontigmem use pgdat->lmem_map */ extern struct page *mem_map; #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { spinlock_t split_queue_lock; struct list_head split_queue; unsigned long split_queue_len; }; #endif /* * On NUMA machines, each NUMA node would have a pg_data_t to describe * it's memory layout. On UMA machines there is a single pglist_data which * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. */ typedef struct pglist_data { /* * node_zones contains just the zones for THIS node. Not all of the * zones may be populated, but it is the full list. It is referenced by * this node's node_zonelists as well as other node's node_zonelists. */ struct zone node_zones[MAX_NR_ZONES]; /* * node_zonelists contains references to all zones in all nodes. * Generally the first zones will be references to this node's * node_zones. */ struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; /* number of populated zones in this node */ #ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION struct page_ext *node_page_ext; #endif #endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, * node_present_pages, node_spanned_pages or nr_zones to stay constant. * Also synchronizes pgdat->first_deferred_pfn during deferred page * init. * * pgdat_resize_lock() and pgdat_resize_unlock() are provided to * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG * or CONFIG_DEFERRED_STRUCT_PAGE_INIT. * * Nests above zone->lock and zone->span_seqlock */ spinlock_t node_size_lock; #endif unsigned long node_start_pfn; unsigned long node_present_pages; /* total number of physical pages */ unsigned long node_spanned_pages; /* total size of physical page range, including holes */ int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ int kswapd_order; enum zone_type kswapd_highest_zoneidx; int kswapd_failures; /* Number of 'reclaimed == 0' runs */ #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; #endif /* * This is a per-node reserve of pages that are not available * to userspace allocations. */ unsigned long totalreserve_pages; #ifdef CONFIG_NUMA /* * node reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; unsigned long min_slab_pages; #endif /* CONFIG_NUMA */ /* Write-intensive fields used by page reclaim */ ZONE_PADDING(_pad1_) spinlock_t lru_lock; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /* * If memory initialisation on large machines is deferred then this * is the first PFN that needs to be initialised. */ unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif /* Fields commonly accessed by the page reclaim scanner */ /* * NOTE: THIS IS UNUSED IF MEMCG IS ENABLED. * * Use mem_cgroup_lruvec() to look up lruvecs. */ struct lruvec __lruvec; unsigned long flags; ZONE_PADDING(_pad2_) /* Per-node vmstats */ struct per_cpu_nodestat __percpu *per_cpu_nodestats; atomic_long_t vm_stat[NR_VM_NODE_STAT_ITEMS]; } pg_data_t; #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) #ifdef CONFIG_FLAT_NODE_MEM_MAP #define pgdat_page_nr(pgdat, pagenr) ((pgdat)->node_mem_map + (pagenr)) #else #define pgdat_page_nr(pgdat, pagenr) pfn_to_page((pgdat)->node_start_pfn + (pagenr)) #endif #define nid_page_nr(nid, pagenr) pgdat_page_nr(NODE_DATA(nid),(pagenr)) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat) { return pgdat->node_start_pfn + pgdat->node_spanned_pages; } static inline bool pgdat_is_empty(pg_data_t *pgdat) { return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; } #include <linux/memory_hotplug.h> void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order, enum zone_type highest_zoneidx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags, long free_pages); bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx); /* * Memory initialization context, use to differentiate memory added by * the platform statically or via memory hotplug interface. */ enum meminit_context { MEMINIT_EARLY, MEMINIT_HOTPLUG, }; extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); extern void lruvec_init(struct lruvec *lruvec); static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG return lruvec->pgdat; #else return container_of(lruvec, struct pglist_data, __lruvec); #endif } extern unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx); #ifdef CONFIG_HAVE_MEMORYLESS_NODES int local_memory_node(int node_id); #else static inline int local_memory_node(int node_id) { return node_id; }; #endif /* * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc. */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) /* * Returns true if a zone has pages managed by the buddy allocator. * All the reclaim decisions have to use this function rather than * populated_zone(). If the whole zone is reserved then we can easily * end up with populated_zone() && !managed_zone(). */ static inline bool managed_zone(struct zone *zone) { return zone_managed_pages(zone); } /* Returns true if a zone has memory */ static inline bool populated_zone(struct zone *zone) { return zone->present_pages; } #ifdef CONFIG_NEED_MULTIPLE_NODES static inline int zone_to_nid(struct zone *zone) { return zone->node; } static inline void zone_set_nid(struct zone *zone, int nid) { zone->node = nid; } #else static inline int zone_to_nid(struct zone *zone) { return 0; } static inline void zone_set_nid(struct zone *zone, int nid) {} #endif extern int movable_zone; #ifdef CONFIG_HIGHMEM static inline int zone_movable_is_highmem(void) { #ifdef CONFIG_NEED_MULTIPLE_NODES return movable_zone == ZONE_HIGHMEM; #else return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM; #endif } #endif static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || (idx == ZONE_MOVABLE && zone_movable_is_highmem())); #else return 0; #endif } #ifdef CONFIG_ZONE_DMA bool has_managed_dma(void); #else static inline bool has_managed_dma(void) { return false; } #endif /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone - pointer to struct zone variable */ static inline int is_highmem(struct zone *zone) { #ifdef CONFIG_HIGHMEM return is_highmem_idx(zone_idx(zone)); #else return 0; #endif } /* These two functions are used to setup the per zone pages min values */ struct ctl_table; int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int numa_zonelist_order_handler(struct ctl_table *, int, void *, size_t *, loff_t *); extern int percpu_pagelist_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 #ifndef CONFIG_NEED_MULTIPLE_NODES extern struct pglist_data contig_page_data; #define NODE_DATA(nid) (&contig_page_data) #define NODE_MEM_MAP(nid) mem_map #else /* CONFIG_NEED_MULTIPLE_NODES */ #include <asm/mmzone.h> #endif /* !CONFIG_NEED_MULTIPLE_NODES */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); extern struct zone *next_zone(struct zone *zone); /** * for_each_online_pgdat - helper macro to iterate over all online nodes * @pgdat - pointer to a pg_data_t variable */ #define for_each_online_pgdat(pgdat) \ for (pgdat = first_online_pgdat(); \ pgdat; \ pgdat = next_online_pgdat(pgdat)) /** * for_each_zone - helper macro to iterate over all memory zones * @zone - pointer to struct zone variable * * The user only needs to declare the zone variable, for_each_zone * fills it in. */ #define for_each_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) #define for_each_populated_zone(zone) \ for (zone = (first_online_pgdat())->node_zones; \ zone; \ zone = next_zone(zone)) \ if (!populated_zone(zone)) \ ; /* do nothing */ \ else static inline struct zone *zonelist_zone(struct zoneref *zoneref) { return zoneref->zone; } static inline int zonelist_zone_idx(struct zoneref *zoneref) { return zoneref->zone_idx; } static inline int zonelist_node_idx(struct zoneref *zoneref) { return zone_to_nid(zoneref->zone); } struct zoneref *__next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes); /** * next_zones_zonelist - Returns the next zone at or below highest_zoneidx within the allowed nodemask using a cursor within a zonelist as a starting point * @z - The cursor used as a starting point for the search * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the * search. The zoneref returned is a cursor that represents the current zone * being examined. It should be advanced by one before calling * next_zones_zonelist again. */ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, nodemask_t *nodes) { if (likely(!nodes && zonelist_zone_idx(z) <= highest_zoneidx)) return z; return __next_zones_zonelist(z, highest_zoneidx, nodes); } /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist * @zonelist - The zonelist to search for a suitable zone * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with * @return - Zoneref pointer for the first suitable zone found (see below) * * This function returns the first zone at or below a given zone index that is * within the allowed nodemask. The zoneref returned is a cursor that can be * used to iterate the zonelist with next_zones_zonelist by advancing it by * one before calling. * * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is * never NULL). This may happen either genuinely, or due to concurrent nodemask * update due to cpuset modification. */ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, enum zone_type highest_zoneidx, nodemask_t *nodes) { return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes); } /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask * @zone - The current zone in the iterator * @z - The current pointer within zonelist->_zonerefs being iterated * @zlist - The zonelist being iterated * @highidx - The zone index of the highest zone to return * @nodemask - Nodemask allowed by the allocator * * This iterator iterates though all zones at or below a given zone index and * within a given nodemask */ #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask), zone = zonelist_zone(z); \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \ for (zone = z->zone; \ zone; \ z = next_zones_zonelist(++z, highidx, nodemask), \ zone = zonelist_zone(z)) /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index * @zone - The current zone in the iterator * @z - The current pointer within zonelist->zones being iterated * @zlist - The zonelist being iterated * @highidx - The zone index of the highest zone to return * * This iterator iterates though all zones at or below a given zone index. */ #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) /* Whether the 'nodes' are all movable nodes */ static inline bool movable_only_nodes(nodemask_t *nodes) { struct zonelist *zonelist; struct zoneref *z; int nid; if (nodes_empty(*nodes)) return false; /* * We can chose arbitrary node from the nodemask to get a * zonelist as they are interlinked. We just need to find * at least one zone that can satisfy kernel allocations. */ nid = first_node(*nodes); zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); return (!z->zone) ? true : false; } #ifdef CONFIG_SPARSEMEM #include <asm/sparsemem.h> #endif #ifdef CONFIG_FLATMEM #define pfn_to_nid(pfn) (0) #endif #ifdef CONFIG_SPARSEMEM /* * SECTION_SHIFT #bits space required to store a section # * * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ #define PA_SECTION_SHIFT (SECTION_SIZE_BITS) #define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT) #define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT) #define PAGES_PER_SECTION (1UL << PFN_SECTION_SHIFT) #define PAGE_SECTION_MASK (~(PAGES_PER_SECTION-1)) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) #if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif static inline unsigned long pfn_to_section_nr(unsigned long pfn) { return pfn >> PFN_SECTION_SHIFT; } static inline unsigned long section_nr_to_pfn(unsigned long sec) { return sec << PFN_SECTION_SHIFT; } #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) #define SUBSECTION_SHIFT 21 #define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT) #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) #define PAGE_SUBSECTION_MASK (~(PAGES_PER_SUBSECTION-1)) #if SUBSECTION_SHIFT > SECTION_SIZE_BITS #error Subsection size exceeds section size #else #define SUBSECTIONS_PER_SECTION (1UL << (SECTION_SIZE_BITS - SUBSECTION_SHIFT)) #endif #define SUBSECTION_ALIGN_UP(pfn) ALIGN((pfn), PAGES_PER_SUBSECTION) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK) struct mem_section_usage { struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif /* See declaration of similar field in struct zone */ unsigned long pageblock_flags[0]; }; void subsection_map_init(unsigned long pfn, unsigned long nr_pages); struct page; struct page_ext; struct mem_section { /* * This is, logically, a pointer to an array of struct * pages. However, it is stored with some other magic. * (see sparse.c::sparse_init_one_section()) * * Additionally during early boot we encode node id of * the location of the section here to guide allocation. * (see sparse.c::memory_present()) * * Making it a UL at least makes someone do a cast * before using it wrong. */ unsigned long section_mem_map; struct mem_section_usage *usage; #ifdef CONFIG_PAGE_EXTENSION /* * If SPARSEMEM, pgdat doesn't have page_ext pointer. We use * section. (see page_ext.h about this.) */ struct page_ext *page_ext; unsigned long pad; #endif /* * WARNING: mem_section must be a power-of-2 in size for the * calculation and use of SECTION_ROOT_MASK to make sense. */ }; #ifdef CONFIG_SPARSEMEM_EXTREME #define SECTIONS_PER_ROOT (PAGE_SIZE / sizeof (struct mem_section)) #else #define SECTIONS_PER_ROOT 1 #endif #define SECTION_NR_TO_ROOT(sec) ((sec) / SECTIONS_PER_ROOT) #define NR_SECTION_ROOTS DIV_ROUND_UP(NR_MEM_SECTIONS, SECTIONS_PER_ROOT) #define SECTION_ROOT_MASK (SECTIONS_PER_ROOT - 1) #ifdef CONFIG_SPARSEMEM_EXTREME extern struct mem_section **mem_section; #else extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]; #endif static inline unsigned long *section_to_usemap(struct mem_section *ms) { return ms->usage->pageblock_flags; } static inline struct mem_section *__nr_to_section(unsigned long nr) { unsigned long root = SECTION_NR_TO_ROOT(nr); if (unlikely(root >= NR_SECTION_ROOTS)) return NULL; #ifdef CONFIG_SPARSEMEM_EXTREME if (!mem_section || !mem_section[root]) return NULL; #endif return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern unsigned long __section_nr(struct mem_section *ms); extern size_t mem_section_usage_size(void); /* * We use the lower bits of the mem_map pointer to store * a little bit of information. The pointer is calculated * as mem_map - section_nr_to_pfn(pnum). The result is * aligned to the minimum alignment of the two values: * 1. All mem_map arrays are page-aligned. * 2. section_nr_to_pfn() always clears PFN_SECTION_SHIFT * lowest bits. PFN_SECTION_SHIFT is arch-specific * (equal SECTION_SIZE_BITS - PAGE_SHIFT), and the * worst combination is powerpc with 256k pages, * which results in PFN_SECTION_SHIFT equal 6. * To sum it up, at least 6 bits are available. */ #define SECTION_MARKED_PRESENT (1UL<<0) #define SECTION_HAS_MEM_MAP (1UL<<1) #define SECTION_IS_ONLINE (1UL<<2) #define SECTION_IS_EARLY (1UL<<3) #define SECTION_MAP_LAST_BIT (1UL<<4) #define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1)) #define SECTION_NID_SHIFT 3 static inline struct page *__section_mem_map_addr(struct mem_section *section) { unsigned long map = section->section_mem_map; map &= SECTION_MAP_MASK; return (struct page *)map; } static inline int present_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_MARKED_PRESENT)); } static inline int present_section_nr(unsigned long nr) { return present_section(__nr_to_section(nr)); } static inline int valid_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP)); } static inline int early_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_EARLY)); } static inline int valid_section_nr(unsigned long nr) { return valid_section(__nr_to_section(nr)); } static inline int online_section(struct mem_section *section) { return (section && (section->section_mem_map & SECTION_IS_ONLINE)); } static inline int online_section_nr(unsigned long nr) { return online_section(__nr_to_section(nr)); } #ifdef CONFIG_MEMORY_HOTPLUG void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_HOTREMOVE void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn); #endif #endif static inline struct mem_section *__pfn_to_section(unsigned long pfn) { return __nr_to_section(pfn_to_section_nr(pfn)); } extern unsigned long __highest_present_section_nr; static inline int subsection_map_index(unsigned long pfn) { return (pfn & ~(PAGE_SECTION_MASK)) / PAGES_PER_SUBSECTION; } #ifdef CONFIG_SPARSEMEM_VMEMMAP static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); struct mem_section_usage *usage = READ_ONCE(ms->usage); return usage ? test_bit(idx, usage->subsection_map) : 0; } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { return 1; } #endif #ifndef CONFIG_HAVE_ARCH_PFN_VALID static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; int ret; if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); rcu_read_lock(); if (!valid_section(ms)) { rcu_read_unlock(); return 0; } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ ret = early_section(ms) || pfn_section_valid(ms, pfn); rcu_read_unlock(); return ret; } #endif static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) { while (++section_nr <= __highest_present_section_nr) { if (present_section_nr(section_nr)) return section_nr; } return -1; } /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate * this restriction. */ #ifdef CONFIG_NUMA #define pfn_to_nid(pfn) \ ({ \ unsigned long __pfn_to_nid_pfn = (pfn); \ page_to_nid(pfn_to_page(__pfn_to_nid_pfn)); \ }) #else #define pfn_to_nid(pfn) (0) #endif void sparse_init(void); #else #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) #define pfn_in_present_section pfn_valid #define subsection_map_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ /* * During memory init memblocks map pfns to nids. The search is expensive and * this caches recent lookups. The implementation of __early_pfn_to_nid * may treat start/end as pfns or sections. */ struct mminit_pfnnid_cache { unsigned long last_start; unsigned long last_end; int last_nid; }; /* * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we * need to check pfn validity within that MAX_ORDER_NR_PAGES block. * pfn_valid_within() should be used in this case; we optimise this away * when we have no holes within a MAX_ORDER_NR_PAGES block. */ #ifdef CONFIG_HOLES_IN_ZONE #define pfn_valid_within(pfn) pfn_valid(pfn) #else #define pfn_valid_within(pfn) (1) #endif #endif /* !__GENERATING_BOUNDS.H */ #endif /* !__ASSEMBLY__ */ #endif /* _LINUX_MMZONE_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 | // SPDX-License-Identifier: GPL-2.0 /* * This is a maximally equidistributed combined Tausworthe generator * based on code from GNU Scientific Library 1.5 (30 Jun 2004) * * lfsr113 version: * * x_n = (s1_n ^ s2_n ^ s3_n ^ s4_n) * * s1_{n+1} = (((s1_n & 4294967294) << 18) ^ (((s1_n << 6) ^ s1_n) >> 13)) * s2_{n+1} = (((s2_n & 4294967288) << 2) ^ (((s2_n << 2) ^ s2_n) >> 27)) * s3_{n+1} = (((s3_n & 4294967280) << 7) ^ (((s3_n << 13) ^ s3_n) >> 21)) * s4_{n+1} = (((s4_n & 4294967168) << 13) ^ (((s4_n << 3) ^ s4_n) >> 12)) * * The period of this generator is about 2^113 (see erratum paper). * * From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe * Generators", Mathematics of Computation, 65, 213 (1996), 203--213: * http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps * ftp://ftp.iro.umontreal.ca/pub/simulation/lecuyer/papers/tausme.ps * * There is an erratum in the paper "Tables of Maximally Equidistributed * Combined LFSR Generators", Mathematics of Computation, 68, 225 (1999), * 261--269: http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps * * ... the k_j most significant bits of z_j must be non-zero, * for each j. (Note: this restriction also applies to the * computer code given in [4], but was mistakenly not mentioned * in that paper.) * * This affects the seeding procedure by imposing the requirement * s1 > 1, s2 > 7, s3 > 15, s4 > 127. */ #include <linux/types.h> #include <linux/percpu.h> #include <linux/export.h> #include <linux/jiffies.h> #include <linux/random.h> #include <linux/sched.h> #include <linux/bitops.h> #include <linux/slab.h> #include <linux/notifier.h> #include <asm/unaligned.h> /** * prandom_u32_state - seeded pseudo-random number generator. * @state: pointer to state structure holding seeded state. * * This is used for pseudo-randomness with no outside seeding. * For more random results, use prandom_u32(). */ u32 prandom_u32_state(struct rnd_state *state) { #define TAUSWORTHE(s, a, b, c, d) ((s & c) << d) ^ (((s << a) ^ s) >> b) state->s1 = TAUSWORTHE(state->s1, 6U, 13U, 4294967294U, 18U); state->s2 = TAUSWORTHE(state->s2, 2U, 27U, 4294967288U, 2U); state->s3 = TAUSWORTHE(state->s3, 13U, 21U, 4294967280U, 7U); state->s4 = TAUSWORTHE(state->s4, 3U, 12U, 4294967168U, 13U); return (state->s1 ^ state->s2 ^ state->s3 ^ state->s4); } EXPORT_SYMBOL(prandom_u32_state); /** * prandom_bytes_state - get the requested number of pseudo-random bytes * * @state: pointer to state structure holding seeded state. * @buf: where to copy the pseudo-random bytes to * @bytes: the requested number of bytes * * This is used for pseudo-randomness with no outside seeding. * For more random results, use prandom_bytes(). */ void prandom_bytes_state(struct rnd_state *state, void *buf, size_t bytes) { u8 *ptr = buf; while (bytes >= sizeof(u32)) { put_unaligned(prandom_u32_state(state), (u32 *) ptr); ptr += sizeof(u32); bytes -= sizeof(u32); } if (bytes > 0) { u32 rem = prandom_u32_state(state); do { *ptr++ = (u8) rem; bytes--; rem >>= BITS_PER_BYTE; } while (bytes > 0); } } EXPORT_SYMBOL(prandom_bytes_state); static void prandom_warmup(struct rnd_state *state) { /* Calling RNG ten times to satisfy recurrence condition */ prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); } void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state) { int i; for_each_possible_cpu(i) { struct rnd_state *state = per_cpu_ptr(pcpu_state, i); u32 seeds[4]; get_random_bytes(&seeds, sizeof(seeds)); state->s1 = __seed(seeds[0], 2U); state->s2 = __seed(seeds[1], 8U); state->s3 = __seed(seeds[2], 16U); state->s4 = __seed(seeds[3], 128U); prandom_warmup(state); } } EXPORT_SYMBOL(prandom_seed_full_state); #ifdef CONFIG_RANDOM32_SELFTEST static struct prandom_test1 { u32 seed; u32 result; } test1[] = { { 1U, 3484351685U }, { 2U, 2623130059U }, { 3U, 3125133893U }, { 4U, 984847254U }, }; static struct prandom_test2 { u32 seed; u32 iteration; u32 result; } test2[] = { /* Test cases against taus113 from GSL library. */ { 931557656U, 959U, 2975593782U }, { 1339693295U, 876U, 3887776532U }, { 1545556285U, 961U, 1615538833U }, { 601730776U, 723U, 1776162651U }, { 1027516047U, 687U, 511983079U }, { 416526298U, 700U, 916156552U }, { 1395522032U, 652U, 2222063676U }, { 366221443U, 617U, 2992857763U }, { 1539836965U, 714U, 3783265725U }, { 556206671U, 994U, 799626459U }, { 684907218U, 799U, 367789491U }, { 2121230701U, 931U, 2115467001U }, { 1668516451U, 644U, 3620590685U }, { 768046066U, 883U, 2034077390U }, { 1989159136U, 833U, 1195767305U }, { 536585145U, 996U, 3577259204U }, { 1008129373U, 642U, 1478080776U }, { 1740775604U, 939U, 1264980372U }, { 1967883163U, 508U, 10734624U }, { 1923019697U, 730U, 3821419629U }, { 442079932U, 560U, 3440032343U }, { 1961302714U, 845U, 841962572U }, { 2030205964U, 962U, 1325144227U }, { 1160407529U, 507U, 240940858U }, { 635482502U, 779U, 4200489746U }, { 1252788931U, 699U, 867195434U }, { 1961817131U, 719U, 668237657U }, { 1071468216U, 983U, 917876630U }, { 1281848367U, 932U, 1003100039U }, { 582537119U, 780U, 1127273778U }, { 1973672777U, 853U, 1071368872U }, { 1896756996U, 762U, 1127851055U }, { 847917054U, 500U, 1717499075U }, { 1240520510U, 951U, 2849576657U }, { 1685071682U, 567U, 1961810396U }, { 1516232129U, 557U, 3173877U }, { 1208118903U, 612U, 1613145022U }, { 1817269927U, 693U, 4279122573U }, { 1510091701U, 717U, 638191229U }, { 365916850U, 807U, 600424314U }, { 399324359U, 702U, 1803598116U }, { 1318480274U, 779U, 2074237022U }, { 697758115U, 840U, 1483639402U }, { 1696507773U, 840U, 577415447U }, { 2081979121U, 981U, 3041486449U }, { 955646687U, 742U, 3846494357U }, { 1250683506U, 749U, 836419859U }, { 595003102U, 534U, 366794109U }, { 47485338U, 558U, 3521120834U }, { 619433479U, 610U, 3991783875U }, { 704096520U, 518U, 4139493852U }, { 1712224984U, 606U, 2393312003U }, { 1318233152U, 922U, 3880361134U }, { 855572992U, 761U, 1472974787U }, { 64721421U, 703U, 683860550U }, { 678931758U, 840U, 380616043U }, { 692711973U, 778U, 1382361947U }, { 677703619U, 530U, 2826914161U }, { 92393223U, 586U, 1522128471U }, { 1222592920U, 743U, 3466726667U }, { 358288986U, 695U, 1091956998U }, { 1935056945U, 958U, 514864477U }, { 735675993U, 990U, 1294239989U }, { 1560089402U, 897U, 2238551287U }, { 70616361U, 829U, 22483098U }, { 368234700U, 731U, 2913875084U }, { 20221190U, 879U, 1564152970U }, { 539444654U, 682U, 1835141259U }, { 1314987297U, 840U, 1801114136U }, { 2019295544U, 645U, 3286438930U }, { 469023838U, 716U, 1637918202U }, { 1843754496U, 653U, 2562092152U }, { 400672036U, 809U, 4264212785U }, { 404722249U, 965U, 2704116999U }, { 600702209U, 758U, 584979986U }, { 519953954U, 667U, 2574436237U }, { 1658071126U, 694U, 2214569490U }, { 420480037U, 749U, 3430010866U }, { 690103647U, 969U, 3700758083U }, { 1029424799U, 937U, 3787746841U }, { 2012608669U, 506U, 3362628973U }, { 1535432887U, 998U, 42610943U }, { 1330635533U, 857U, 3040806504U }, { 1223800550U, 539U, 3954229517U }, { 1322411537U, 680U, 3223250324U }, { 1877847898U, 945U, 2915147143U }, { 1646356099U, 874U, 965988280U }, { 805687536U, 744U, 4032277920U }, { 1948093210U, 633U, 1346597684U }, { 392609744U, 783U, 1636083295U }, { 690241304U, 770U, 1201031298U }, { 1360302965U, 696U, 1665394461U }, { 1220090946U, 780U, 1316922812U }, { 447092251U, 500U, 3438743375U }, { 1613868791U, 592U, 828546883U }, { 523430951U, 548U, 2552392304U }, { 726692899U, 810U, 1656872867U }, { 1364340021U, 836U, 3710513486U }, { 1986257729U, 931U, 935013962U }, { 407983964U, 921U, 728767059U }, }; static u32 __extract_hwseed(void) { unsigned int val = 0; (void)(arch_get_random_seed_int(&val) || arch_get_random_int(&val)); return val; } static void prandom_seed_early(struct rnd_state *state, u32 seed, bool mix_with_hwseed) { #define LCG(x) ((x) * 69069U) /* super-duper LCG */ #define HWSEED() (mix_with_hwseed ? __extract_hwseed() : 0) state->s1 = __seed(HWSEED() ^ LCG(seed), 2U); state->s2 = __seed(HWSEED() ^ LCG(state->s1), 8U); state->s3 = __seed(HWSEED() ^ LCG(state->s2), 16U); state->s4 = __seed(HWSEED() ^ LCG(state->s3), 128U); } static int __init prandom_state_selftest(void) { int i, j, errors = 0, runs = 0; bool error = false; for (i = 0; i < ARRAY_SIZE(test1); i++) { struct rnd_state state; prandom_seed_early(&state, test1[i].seed, false); prandom_warmup(&state); if (test1[i].result != prandom_u32_state(&state)) error = true; } if (error) pr_warn("prandom: seed boundary self test failed\n"); else pr_info("prandom: seed boundary self test passed\n"); for (i = 0; i < ARRAY_SIZE(test2); i++) { struct rnd_state state; prandom_seed_early(&state, test2[i].seed, false); prandom_warmup(&state); for (j = 0; j < test2[i].iteration - 1; j++) prandom_u32_state(&state); if (test2[i].result != prandom_u32_state(&state)) errors++; runs++; cond_resched(); } if (errors) pr_warn("prandom: %d/%d self tests failed\n", errors, runs); else pr_info("prandom: %d self tests passed\n", runs); return 0; } core_initcall(prandom_state_selftest); #endif /* * The prandom_u32() implementation is now completely separate from the * prandom_state() functions, which are retained (for now) for compatibility. * * Because of (ab)use in the networking code for choosing random TCP/UDP port * numbers, which open DoS possibilities if guessable, we want something * stronger than a standard PRNG. But the performance requirements of * the network code do not allow robust crypto for this application. * * So this is a homebrew Junior Spaceman implementation, based on the * lowest-latency trustworthy crypto primitive available, SipHash. * (The authors of SipHash have not been consulted about this abuse of * their work.) * * Standard SipHash-2-4 uses 2n+4 rounds to hash n words of input to * one word of output. This abbreviated version uses 2 rounds per word * of output. */ struct siprand_state { unsigned long v0; unsigned long v1; unsigned long v2; unsigned long v3; }; static DEFINE_PER_CPU(struct siprand_state, net_rand_state) __latent_entropy; DEFINE_PER_CPU(unsigned long, net_rand_noise); EXPORT_PER_CPU_SYMBOL(net_rand_noise); /* * This is the core CPRNG function. As "pseudorandom", this is not used * for truly valuable things, just intended to be a PITA to guess. * For maximum speed, we do just two SipHash rounds per word. This is * the same rate as 4 rounds per 64 bits that SipHash normally uses, * so hopefully it's reasonably secure. * * There are two changes from the official SipHash finalization: * - We omit some constants XORed with v2 in the SipHash spec as irrelevant; * they are there only to make the output rounds distinct from the input * rounds, and this application has no input rounds. * - Rather than returning v0^v1^v2^v3, return v1+v3. * If you look at the SipHash round, the last operation on v3 is * "v3 ^= v0", so "v0 ^ v3" just undoes that, a waste of time. * Likewise "v1 ^= v2". (The rotate of v2 makes a difference, but * it still cancels out half of the bits in v2 for no benefit.) * Second, since the last combining operation was xor, continue the * pattern of alternating xor/add for a tiny bit of extra non-linearity. */ static inline u32 siprand_u32(struct siprand_state *s) { unsigned long v0 = s->v0, v1 = s->v1, v2 = s->v2, v3 = s->v3; unsigned long n = raw_cpu_read(net_rand_noise); v3 ^= n; PRND_SIPROUND(v0, v1, v2, v3); PRND_SIPROUND(v0, v1, v2, v3); v0 ^= n; s->v0 = v0; s->v1 = v1; s->v2 = v2; s->v3 = v3; return v1 + v3; } /** * prandom_u32 - pseudo random number generator * * A 32 bit pseudo-random number is generated using a fast * algorithm suitable for simulation. This algorithm is NOT * considered safe for cryptographic use. */ u32 prandom_u32(void) { struct siprand_state *state = get_cpu_ptr(&net_rand_state); u32 res = siprand_u32(state); put_cpu_ptr(&net_rand_state); return res; } EXPORT_SYMBOL(prandom_u32); /** * prandom_bytes - get the requested number of pseudo-random bytes * @buf: where to copy the pseudo-random bytes to * @bytes: the requested number of bytes */ void prandom_bytes(void *buf, size_t bytes) { struct siprand_state *state = get_cpu_ptr(&net_rand_state); u8 *ptr = buf; while (bytes >= sizeof(u32)) { put_unaligned(siprand_u32(state), (u32 *)ptr); ptr += sizeof(u32); bytes -= sizeof(u32); } if (bytes > 0) { u32 rem = siprand_u32(state); do { *ptr++ = (u8)rem; rem >>= BITS_PER_BYTE; } while (--bytes > 0); } put_cpu_ptr(&net_rand_state); } EXPORT_SYMBOL(prandom_bytes); /** * prandom_seed - add entropy to pseudo random number generator * @entropy: entropy value * * Add some additional seed material to the prandom pool. * The "entropy" is actually our IP address (the only caller is * the network code), not for unpredictability, but to ensure that * different machines are initialized differently. */ void prandom_seed(u32 entropy) { int i; add_device_randomness(&entropy, sizeof(entropy)); for_each_possible_cpu(i) { struct siprand_state *state = per_cpu_ptr(&net_rand_state, i); unsigned long v0 = state->v0, v1 = state->v1; unsigned long v2 = state->v2, v3 = state->v3; do { v3 ^= entropy; PRND_SIPROUND(v0, v1, v2, v3); PRND_SIPROUND(v0, v1, v2, v3); v0 ^= entropy; } while (unlikely(!v0 || !v1 || !v2 || !v3)); WRITE_ONCE(state->v0, v0); WRITE_ONCE(state->v1, v1); WRITE_ONCE(state->v2, v2); WRITE_ONCE(state->v3, v3); } } EXPORT_SYMBOL(prandom_seed); /* * Generate some initially weak seeding values to allow * the prandom_u32() engine to be started. */ static int __init prandom_init_early(void) { int i; unsigned long v0, v1, v2, v3; if (!arch_get_random_long(&v0)) v0 = jiffies; if (!arch_get_random_long(&v1)) v1 = random_get_entropy(); v2 = v0 ^ PRND_K0; v3 = v1 ^ PRND_K1; for_each_possible_cpu(i) { struct siprand_state *state; v3 ^= i; PRND_SIPROUND(v0, v1, v2, v3); PRND_SIPROUND(v0, v1, v2, v3); v0 ^= i; state = per_cpu_ptr(&net_rand_state, i); state->v0 = v0; state->v1 = v1; state->v2 = v2; state->v3 = v3; } return 0; } core_initcall(prandom_init_early); /* Stronger reseeding when available, and periodically thereafter. */ static void prandom_reseed(struct timer_list *unused); static DEFINE_TIMER(seed_timer, prandom_reseed); static void prandom_reseed(struct timer_list *unused) { unsigned long expires; int i; /* * Reinitialize each CPU's PRNG with 128 bits of key. * No locking on the CPUs, but then somewhat random results are, * well, expected. */ for_each_possible_cpu(i) { struct siprand_state *state; unsigned long v0 = get_random_long(), v2 = v0 ^ PRND_K0; unsigned long v1 = get_random_long(), v3 = v1 ^ PRND_K1; #if BITS_PER_LONG == 32 int j; /* * On 32-bit machines, hash in two extra words to * approximate 128-bit key length. Not that the hash * has that much security, but this prevents a trivial * 64-bit brute force. */ for (j = 0; j < 2; j++) { unsigned long m = get_random_long(); v3 ^= m; PRND_SIPROUND(v0, v1, v2, v3); PRND_SIPROUND(v0, v1, v2, v3); v0 ^= m; } #endif /* * Probably impossible in practice, but there is a * theoretical risk that a race between this reseeding * and the target CPU writing its state back could * create the all-zero SipHash fixed point. * * To ensure that never happens, ensure the state * we write contains no zero words. */ state = per_cpu_ptr(&net_rand_state, i); WRITE_ONCE(state->v0, v0 ? v0 : -1ul); WRITE_ONCE(state->v1, v1 ? v1 : -1ul); WRITE_ONCE(state->v2, v2 ? v2 : -1ul); WRITE_ONCE(state->v3, v3 ? v3 : -1ul); } /* reseed every ~60 seconds, in [40 .. 80) interval with slack */ expires = round_jiffies(jiffies + 40 * HZ + prandom_u32_max(40 * HZ)); mod_timer(&seed_timer, expires); } /* * The random ready callback can be called from almost any interrupt. * To avoid worrying about whether it's safe to delay that interrupt * long enough to seed all CPUs, just schedule an immediate timer event. */ static int prandom_timer_start(struct notifier_block *nb, unsigned long action, void *data) { mod_timer(&seed_timer, jiffies); return 0; } #ifdef CONFIG_RANDOM32_SELFTEST /* Principle: True 32-bit random numbers will all have 16 differing bits on * average. For each 32-bit number, there are 601M numbers differing by 16 * bits, and 89% of the numbers differ by at least 12 bits. Note that more * than 16 differing bits also implies a correlation with inverted bits. Thus * we take 1024 random numbers and compare each of them to the other ones, * counting the deviation of correlated bits to 16. Constants report 32, * counters 32-log2(TEST_SIZE), and pure randoms, around 6 or lower. With the * u32 total, TEST_SIZE may be as large as 4096 samples. */ #define TEST_SIZE 1024 static int __init prandom32_state_selftest(void) { unsigned int x, y, bits, samples; u32 xor, flip; u32 total; u32 *data; data = kmalloc(sizeof(*data) * TEST_SIZE, GFP_KERNEL); if (!data) return 0; for (samples = 0; samples < TEST_SIZE; samples++) data[samples] = prandom_u32(); flip = total = 0; for (x = 0; x < samples; x++) { for (y = 0; y < samples; y++) { if (x == y) continue; xor = data[x] ^ data[y]; flip |= xor; bits = hweight32(xor); total += (bits - 16) * (bits - 16); } } /* We'll return the average deviation as 2*sqrt(corr/samples), which * is also sqrt(4*corr/samples) which provides a better resolution. */ bits = int_sqrt(total / (samples * (samples - 1)) * 4); if (bits > 6) pr_warn("prandom32: self test failed (at least %u bits" " correlated, fixed_mask=%#x fixed_value=%#x\n", bits, ~flip, data[0] & ~flip); else pr_info("prandom32: self test passed (less than %u bits" " correlated)\n", bits+1); kfree(data); return 0; } core_initcall(prandom32_state_selftest); #endif /* CONFIG_RANDOM32_SELFTEST */ /* * Start periodic full reseeding as soon as strong * random numbers are available. */ static int __init prandom_init_late(void) { static struct notifier_block random_ready = { .notifier_call = prandom_timer_start }; int ret = register_random_ready_notifier(&random_ready); if (ret == -EALREADY) { prandom_timer_start(&random_ready, 0, NULL); ret = 0; } return ret; } late_initcall(prandom_init_late); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CGROUP_H #define _LINUX_CGROUP_H /* * cgroup interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/rculist.h> #include <linux/cgroupstats.h> #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/kernfs.h> #include <linux/jump_label.h> #include <linux/types.h> #include <linux/ns_common.h> #include <linux/nsproxy.h> #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/kernel_stat.h> #include <linux/cgroup-defs.h> struct kernel_clone_args; #ifdef CONFIG_CGROUPS /* * All weight knobs on the default hierarhcy should use the following min, * default and max values. The default value is the logarithmic center of * MIN and MAX and allows 100x to be expressed in both directions. */ #define CGROUP_WEIGHT_MIN 1 #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 /* walk only threadgroup leaders */ #define CSS_TASK_ITER_PROCS (1U << 0) /* walk all threaded css_sets in the domain */ #define CSS_TASK_ITER_THREADED (1U << 1) /* internal flags */ #define CSS_TASK_ITER_SKIPPED (1U << 16) /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { struct cgroup_subsys *ss; unsigned int flags; struct list_head *cset_pos; struct list_head *cset_head; struct list_head *tcset_pos; struct list_head *tcset_head; struct list_head *task_pos; struct list_head *cur_tasks_head; struct css_set *cur_cset; struct css_set *cur_dcset; struct task_struct *cur_task; struct list_head iters_node; /* css_set->task_iters */ }; extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; #include <linux/cgroup_subsys.h> #undef SUBSYS #define SUBSYS(_x) \ extern struct static_key_true _x ## _cgrp_subsys_enabled_key; \ extern struct static_key_true _x ## _cgrp_subsys_on_dfl_key; #include <linux/cgroup_subsys.h> #undef SUBSYS /** * cgroup_subsys_enabled - fast test on whether a subsys is enabled * @ss: subsystem in question */ #define cgroup_subsys_enabled(ss) \ static_branch_likely(&ss ## _enabled_key) /** * cgroup_subsys_on_dfl - fast test on whether a subsys is on default hierarchy * @ss: subsystem in question */ #define cgroup_subsys_on_dfl(ss) \ static_branch_likely(&ss ## _on_dfl_key) bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss); struct cgroup *cgroup_get_from_path(const char *path); struct cgroup *cgroup_get_from_fd(int fd); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); void cgroup_file_notify(struct cgroup_file *cfile); int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); void cgroup_fork(struct task_struct *p); extern int cgroup_can_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void cgroup_cancel_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void cgroup_post_fork(struct task_struct *p, struct kernel_clone_args *kargs); void cgroup_exit(struct task_struct *p); void cgroup_release(struct task_struct *p); void cgroup_free(struct task_struct *p); int cgroup_init_early(void); int cgroup_init(void); int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v); /* * Iteration helpers and macros. */ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent); struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos); struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it); struct task_struct *css_task_iter_next(struct css_task_iter *it); void css_task_iter_end(struct css_task_iter *it); /** * css_for_each_child - iterate through children of a css * @pos: the css * to use as the loop cursor * @parent: css whose children to walk * * Walk @parent's children. Must be called under rcu_read_lock(). * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ #define css_for_each_child(pos, parent) \ for ((pos) = css_next_child(NULL, (parent)); (pos); \ (pos) = css_next_child((pos), (parent))) /** * css_for_each_descendant_pre - pre-order walk of a css's descendants * @pos: the css * to use as the loop cursor * @root: css whose descendants to walk * * Walk @root's descendants. @root is included in the iteration and the * first node to be visited. Must be called under rcu_read_lock(). * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * For example, the following guarantees that a descendant can't escape * state updates of its ancestors. * * my_online(@css) * { * Lock @css's parent and @css; * Inherit state from the parent; * Unlock both. * } * * my_update_state(@css) * { * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; * if (@pos == @css) * Update @css's state; * else * Verify @pos is alive and inherit state from its parent; * Unlock @pos; * } * } * * As long as the inheriting step, including checking the parent state, is * enclosed inside @pos locking, double-locking the parent isn't necessary * while inheriting. The state update to the parent is guaranteed to be * visible by walking order and, as long as inheriting operations to the * same @pos are atomic to each other, multiple updates racing each other * still result in the correct state. It's guaranateed that at least one * inheritance happens for any css after the latest update to its parent. * * If checking parent's state requires locking the parent, each inheriting * iteration should lock and unlock both @pos->parent and @pos. * * Alternatively, a subsystem may choose to use a single global lock to * synchronize ->css_online() and ->css_offline() against tree-walking * operations. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ #define css_for_each_descendant_pre(pos, css) \ for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ (pos) = css_next_descendant_pre((pos), (css))) /** * css_for_each_descendant_post - post-order walk of a css's descendants * @pos: the css * to use as the loop cursor * @css: css whose descendants to walk * * Similar to css_for_each_descendant_pre() but performs post-order * traversal instead. @root is included in the iteration and the last * node to be visited. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * Note that the walk visibility guarantee example described in pre-order * walk doesn't apply the same to post-order walks. */ #define css_for_each_descendant_post(pos, css) \ for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ (pos) = css_next_descendant_post((pos), (css))) /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor * @dst_css: the destination css * @tset: taskset to iterate * * @tset may contain multiple tasks and they may belong to multiple * processes. * * On the v2 hierarchy, there may be tasks from multiple processes and they * may not share the source or destination csses. * * On traditional hierarchies, when there are multiple tasks in @tset, if a * task of a process is in @tset, all tasks of the process are in @tset. * Also, all are guaranteed to share the same source and destination csses. * * Iteration is not in any specific order. */ #define cgroup_taskset_for_each(task, dst_css, tset) \ for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ (task); \ (task) = cgroup_taskset_next((tset), &(dst_css))) /** * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor * @dst_css: the destination css * @tset: taskset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. */ #define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ (leader); \ (leader) = cgroup_taskset_next((tset), &(dst_css))) \ if ((leader) != (leader)->group_leader) \ ; \ else /* * Inline functions. */ static inline u64 cgroup_id(struct cgroup *cgrp) { return cgrp->kn->id; } /** * css_get - obtain a reference on the specified css * @css: target css * * The caller must already have a reference. */ static inline void css_get(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_NO_REF)) percpu_ref_get(&css->refcnt); } /** * css_get_many - obtain references on the specified css * @css: target css * @n: number of references to get * * The caller must already have a reference. */ static inline void css_get_many(struct cgroup_subsys_state *css, unsigned int n) { if (!(css->flags & CSS_NO_REF)) percpu_ref_get_many(&css->refcnt, n); } /** * css_tryget - try to obtain a reference on the specified css * @css: target css * * Obtain a reference on @css unless it already has reached zero and is * being released. This function doesn't care whether @css is on or * offline. The caller naturally needs to ensure that @css is accessible * but doesn't have to be holding a reference on it - IOW, RCU protected * access is good enough for this function. Returns %true if a reference * count was successfully obtained; %false otherwise. */ static inline bool css_tryget(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_NO_REF)) return percpu_ref_tryget(&css->refcnt); return true; } /** * css_tryget_online - try to obtain a reference on the specified css if online * @css: target css * * Obtain a reference on @css if it's online. The caller naturally needs * to ensure that @css is accessible but doesn't have to be holding a * reference on it - IOW, RCU protected access is good enough for this * function. Returns %true if a reference count was successfully obtained; * %false otherwise. */ static inline bool css_tryget_online(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_NO_REF)) return percpu_ref_tryget_live(&css->refcnt); return true; } /** * css_is_dying - test whether the specified css is dying * @css: target css * * Test whether @css is in the process of offlining or already offline. In * most cases, ->css_online() and ->css_offline() callbacks should be * enough; however, the actual offline operations are RCU delayed and this * test returns %true also when @css is scheduled to be offlined. * * This is useful, for example, when the use case requires synchronous * behavior with respect to cgroup removal. cgroup removal schedules css * offlining but the css can seem alive while the operation is being * delayed. If the delay affects user visible semantics, this test can be * used to resolve the situation. */ static inline bool css_is_dying(struct cgroup_subsys_state *css) { return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt); } /** * css_put - put a css reference * @css: target css * * Put a reference obtained via css_get() and css_tryget_online(). */ static inline void css_put(struct cgroup_subsys_state *css) { if (!(css->flags & CSS_NO_REF)) percpu_ref_put(&css->refcnt); } /** * css_put_many - put css references * @css: target css * @n: number of references to put * * Put references obtained via css_get() and css_tryget_online(). */ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n) { if (!(css->flags & CSS_NO_REF)) percpu_ref_put_many(&css->refcnt, n); } static inline void cgroup_get(struct cgroup *cgrp) { css_get(&cgrp->self); } static inline bool cgroup_tryget(struct cgroup *cgrp) { return css_tryget(&cgrp->self); } static inline void cgroup_put(struct cgroup *cgrp) { css_put(&cgrp->self); } /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for * @__c: extra condition expression to be passed to rcu_dereference_check() * * A task's css_set is RCU protected, initialized and exited while holding * task_lock(), and can only be modified while holding both cgroup_mutex * and task_lock() while the task is alive. This macro verifies that the * caller is inside proper critical section and returns @task's css_set. * * The caller can also specify additional allowed conditions via @__c, such * as locks used during the cgroup_subsys::attach() methods. */ #ifdef CONFIG_PROVE_RCU extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ rcu_read_lock_sched_held() || \ lockdep_is_held(&cgroup_mutex) || \ lockdep_is_held(&css_set_lock) || \ ((task)->flags & PF_EXITING) || (__c)) #else #define task_css_set_check(task, __c) \ rcu_dereference((task)->cgroups) #endif /** * task_css_check - obtain css for (task, subsys) w/ extra access conds * @task: the target task * @subsys_id: the target subsystem ID * @__c: extra condition expression to be passed to rcu_dereference_check() * * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The * synchronization rules are the same as task_css_set_check(). */ #define task_css_check(task, subsys_id, __c) \ task_css_set_check((task), (__c))->subsys[(subsys_id)] /** * task_css_set - obtain a task's css_set * @task: the task to obtain css_set for * * See task_css_set_check(). */ static inline struct css_set *task_css_set(struct task_struct *task) { return task_css_set_check(task, false); } /** * task_css - obtain css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * * See task_css_check(). */ static inline struct cgroup_subsys_state *task_css(struct task_struct *task, int subsys_id) { return task_css_check(task, subsys_id, false); } /** * task_get_css - find and get the css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * * Find the css for the (@task, @subsys_id) combination, increment a * reference on and return it. This function is guaranteed to return a * valid css. The returned css may already have been offlined. */ static inline struct cgroup_subsys_state * task_get_css(struct task_struct *task, int subsys_id) { struct cgroup_subsys_state *css; rcu_read_lock(); while (true) { css = task_css(task, subsys_id); /* * Can't use css_tryget_online() here. A task which has * PF_EXITING set may stay associated with an offline css. * If such task calls this function, css_tryget_online() * will keep failing. */ if (likely(css_tryget(css))) break; cpu_relax(); } rcu_read_unlock(); return css; } /** * task_css_is_root - test whether a task belongs to the root css * @task: the target task * @subsys_id: the target subsystem ID * * Test whether @task belongs to the root css on the specified subsystem. * May be invoked in any context. */ static inline bool task_css_is_root(struct task_struct *task, int subsys_id) { return task_css_check(task, subsys_id, true) == init_css_set.subsys[subsys_id]; } static inline struct cgroup *task_cgroup(struct task_struct *task, int subsys_id) { return task_css(task, subsys_id)->cgroup; } static inline struct cgroup *task_dfl_cgroup(struct task_struct *task) { return task_css_set(task)->dfl_cgrp; } static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { struct cgroup_subsys_state *parent_css = cgrp->self.parent; if (parent_css) return container_of(parent_css, struct cgroup, self); return NULL; } /** * cgroup_is_descendant - test ancestry * @cgrp: the cgroup to be tested * @ancestor: possible ancestor of @cgrp * * Test whether @cgrp is a descendant of @ancestor. It also returns %true * if @cgrp == @ancestor. This function is safe to call as long as @cgrp * and @ancestor are accessible. */ static inline bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor) { if (cgrp->root != ancestor->root || cgrp->level < ancestor->level) return false; return cgrp->ancestor_ids[ancestor->level] == cgroup_id(ancestor); } /** * cgroup_ancestor - find ancestor of cgroup * @cgrp: cgroup to find ancestor of * @ancestor_level: level of ancestor to find starting from root * * Find ancestor of cgroup at specified level starting from root if it exists * and return pointer to it. Return NULL if @cgrp doesn't have ancestor at * @ancestor_level. * * This function is safe to call as long as @cgrp is accessible. */ static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, int ancestor_level) { if (cgrp->level < ancestor_level) return NULL; while (cgrp && cgrp->level > ancestor_level) cgrp = cgroup_parent(cgrp); return cgrp; } /** * task_under_cgroup_hierarchy - test task's membership of cgroup ancestry * @task: the task to be tested * @ancestor: possible ancestor of @task's cgroup * * Tests whether @task's default cgroup hierarchy is a descendant of @ancestor. * It follows all the same rules as cgroup_is_descendant, and only applies * to the default hierarchy. */ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { struct css_set *cset = task_css_set(task); return cgroup_is_descendant(cset->dfl_cgrp, ancestor); } /* no synchronization, the result can only be used as a hint */ static inline bool cgroup_is_populated(struct cgroup *cgrp) { return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children + cgrp->nr_populated_threaded_children; } /* returns ino associated with a cgroup */ static inline ino_t cgroup_ino(struct cgroup *cgrp) { return kernfs_ino(cgrp->kn); } /* cft/css accessors for cftype->write() operation */ static inline struct cftype *of_cft(struct kernfs_open_file *of) { return of->kn->priv; } struct cgroup_subsys_state *of_css(struct kernfs_open_file *of); /* cft/css accessors for cftype->seq_*() operations */ static inline struct cftype *seq_cft(struct seq_file *seq) { return of_cft(seq->private); } static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq) { return of_css(seq->private); } /* * Name / path handling functions. All are thin wrappers around the kernfs * counterparts and can be called under any context. */ static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen) { return kernfs_name(cgrp->kn, buf, buflen); } static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen) { return kernfs_path(cgrp->kn, buf, buflen); } static inline void pr_cont_cgroup_name(struct cgroup *cgrp) { pr_cont_kernfs_name(cgrp->kn); } static inline void pr_cont_cgroup_path(struct cgroup *cgrp) { pr_cont_kernfs_path(cgrp->kn); } static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) { return &cgrp->psi; } static inline void cgroup_init_kthreadd(void) { /* * kthreadd is inherited by all kthreads, keep it in the root so * that the new kthreads are guaranteed to stay in the root until * initialization is finished. */ current->no_cgroup_migration = 1; } static inline void cgroup_kthread_ready(void) { /* * This kthread finished initialization. The creator should have * set PF_NO_SETAFFINITY if this kthread should stay in the root. */ current->no_cgroup_migration = 0; } void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; struct cgroup; static inline u64 cgroup_id(struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) { return 0; } static inline int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { return -EINVAL; } static inline void cgroup_fork(struct task_struct *p) {} static inline int cgroup_can_fork(struct task_struct *p, struct kernel_clone_args *kargs) { return 0; } static inline void cgroup_cancel_fork(struct task_struct *p, struct kernel_clone_args *kargs) {} static inline void cgroup_post_fork(struct task_struct *p, struct kernel_clone_args *kargs) {} static inline void cgroup_exit(struct task_struct *p) {} static inline void cgroup_release(struct task_struct *p) {} static inline void cgroup_free(struct task_struct *p) {} static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { return NULL; } static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) { return NULL; } static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { return true; } static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) {} #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS /* * cgroup scalable recursive statistics. */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp); void cgroup_rstat_flush_hold(struct cgroup *cgrp); void cgroup_rstat_flush_release(void); /* * Basic resource stats. */ #ifdef CONFIG_CGROUP_CPUACCT void cpuacct_charge(struct task_struct *tsk, u64 cputime); void cpuacct_account_field(struct task_struct *tsk, int index, u64 val); #else static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} static inline void cpuacct_account_field(struct task_struct *tsk, int index, u64 val) {} #endif void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec); void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec); static inline void cgroup_account_cputime(struct task_struct *task, u64 delta_exec) { struct cgroup *cgrp; cpuacct_charge(task, delta_exec); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime(cgrp, delta_exec); } static inline void cgroup_account_cputime_field(struct task_struct *task, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup *cgrp; cpuacct_account_field(task, index, delta_exec); rcu_read_lock(); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime_field(cgrp, index, delta_exec); rcu_read_unlock(); } #else /* CONFIG_CGROUPS */ static inline void cgroup_account_cputime(struct task_struct *task, u64 delta_exec) {} static inline void cgroup_account_cputime_field(struct task_struct *task, enum cpu_usage_stat index, u64 delta_exec) {} #endif /* CONFIG_CGROUPS */ /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA void cgroup_sk_alloc(struct sock_cgroup_data *skcd); void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) { return skcd->cgroup; } #else /* CONFIG_CGROUP_DATA */ static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ struct cgroup_namespace { refcount_t count; struct ns_common ns; struct user_namespace *user_ns; struct ucounts *ucounts; struct css_set *root_cset; }; extern struct cgroup_namespace init_cgroup_ns; #ifdef CONFIG_CGROUPS void free_cgroup_ns(struct cgroup_namespace *ns); struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns); int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns); #else /* !CONFIG_CGROUPS */ static inline void free_cgroup_ns(struct cgroup_namespace *ns) { } static inline struct cgroup_namespace * copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns) { return old_ns; } #endif /* !CONFIG_CGROUPS */ static inline void get_cgroup_ns(struct cgroup_namespace *ns) { if (ns) refcount_inc(&ns->count); } static inline void put_cgroup_ns(struct cgroup_namespace *ns) { if (ns && refcount_dec_and_test(&ns->count)) free_cgroup_ns(ns); } #ifdef CONFIG_CGROUPS void cgroup_enter_frozen(void); void cgroup_leave_frozen(bool always_leave); void cgroup_update_frozen(struct cgroup *cgrp); void cgroup_freeze(struct cgroup *cgrp, bool freeze); void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src, struct cgroup *dst); static inline bool cgroup_task_freeze(struct task_struct *task) { bool ret; if (task->flags & PF_KTHREAD) return false; rcu_read_lock(); ret = test_bit(CGRP_FREEZE, &task_dfl_cgroup(task)->flags); rcu_read_unlock(); return ret; } static inline bool cgroup_task_frozen(struct task_struct *task) { return task->frozen; } #else /* !CONFIG_CGROUPS */ static inline void cgroup_enter_frozen(void) { } static inline void cgroup_leave_frozen(bool always_leave) { } static inline bool cgroup_task_freeze(struct task_struct *task) { return false; } static inline bool cgroup_task_frozen(struct task_struct *task) { return false; } #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUP_BPF static inline void cgroup_bpf_get(struct cgroup *cgrp) { percpu_ref_get(&cgrp->bpf.refcnt); } static inline void cgroup_bpf_put(struct cgroup *cgrp) { percpu_ref_put(&cgrp->bpf.refcnt); } #else /* CONFIG_CGROUP_BPF */ static inline void cgroup_bpf_get(struct cgroup *cgrp) {} static inline void cgroup_bpf_put(struct cgroup *cgrp) {} #endif /* CONFIG_CGROUP_BPF */ #endif /* _LINUX_CGROUP_H */ |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This header provides generic wrappers for memory access instrumentation that * the compiler cannot emit for: KASAN, KCSAN. */ #ifndef _LINUX_INSTRUMENTED_H #define _LINUX_INSTRUMENTED_H #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> #include <linux/types.h> /** * instrument_read - instrument regular read access * * Instrument a regular read access. The instrumentation should be inserted * before the actual read happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_read(v, size); } /** * instrument_write - instrument regular write access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_write(v, size); } /** * instrument_read_write - instrument regular read-write access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_read_write(v, size); } /** * instrument_atomic_read - instrument atomic read access * * Instrument an atomic read access. The instrumentation should be inserted * before the actual read happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_atomic_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_atomic_read(v, size); } /** * instrument_atomic_write - instrument atomic write access * * Instrument an atomic write access. The instrumentation should be inserted * before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_atomic_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_write(v, size); } /** * instrument_atomic_read_write - instrument atomic read-write access * * Instrument an atomic read-write access. The instrumentation should be * inserted before the actual write happens. * * @ptr address of access * @size size of access */ static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_read_write(v, size); } /** * instrument_copy_to_user - instrument reads of copy_to_user * * Instrument reads from kernel memory, that are due to copy_to_user (and * variants). The instrumentation must be inserted before the accesses. * * @to destination address * @from source address * @n number of bytes to copy */ static __always_inline void instrument_copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); kcsan_check_read(from, n); } /** * instrument_copy_from_user - instrument writes of copy_from_user * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. * * @to destination address * @from source address * @n number of bytes to copy */ static __always_inline void instrument_copy_from_user(const void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); kcsan_check_write(to, n); } #endif /* _LINUX_INSTRUMENTED_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/read_write.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/slab.h> #include <linux/stat.h> #include <linux/sched/xacct.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> #include "internal.h" #include <linux/uaccess.h> #include <asm/unistd.h> const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, .mmap = generic_file_readonly_mmap, .splice_read = generic_file_splice_read, }; EXPORT_SYMBOL(generic_ro_fops); static inline bool unsigned_offsets(struct file *file) { return file->f_mode & FMODE_UNSIGNED_OFFSET; } /** * vfs_setpos - update the file offset for lseek * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * * This is a low-level filesystem helper for updating the file offset to * the value specified by @offset if the given offset is valid and it is * not equal to the current file offset. * * Return the specified offset on success and -EINVAL on invalid offset. */ loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) { if (offset < 0 && !unsigned_offsets(file)) return -EINVAL; if (offset > maxsize) return -EINVAL; if (offset != file->f_pos) { file->f_pos = offset; file->f_version = 0; } return offset; } EXPORT_SYMBOL(vfs_setpos); /** * generic_file_llseek_size - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: max size of this file in file system * @eof: offset used for SEEK_END position * * This is a variant of generic_file_llseek that allows passing in a custom * maximum file size and a custom EOF position, for e.g. hashed directories * * Synchronization: * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes. * read/writes behave like SEEK_SET against seeks. */ loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof) { switch (whence) { case SEEK_END: offset += eof; break; case SEEK_CUR: /* * Here we special-case the lseek(fd, 0, SEEK_CUR) * position-querying operation. Avoid rewriting the "same" * f_pos value back to the file because a concurrent read(), * write() or lseek() might have altered it */ if (offset == 0) return file->f_pos; /* * f_lock protects against read/modify/write race with other * SEEK_CURs. Note that parallel writes and reads behave * like SEEK_SET. */ spin_lock(&file->f_lock); offset = vfs_setpos(file, file->f_pos + offset, maxsize); spin_unlock(&file->f_lock); return offset; case SEEK_DATA: /* * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ if ((unsigned long long)offset >= eof) return -ENXIO; break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ if ((unsigned long long)offset >= eof) return -ENXIO; offset = eof; break; } return vfs_setpos(file, offset, maxsize); } EXPORT_SYMBOL(generic_file_llseek_size); /** * generic_file_llseek - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is a generic implemenation of ->llseek useable for all normal local * filesystems. It just updates the file offset to the value specified by * @offset and @whence. */ loff_t generic_file_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; return generic_file_llseek_size(file, offset, whence, inode->i_sb->s_maxbytes, i_size_read(inode)); } EXPORT_SYMBOL(generic_file_llseek); /** * fixed_size_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: size of the file * */ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: case SEEK_END: return generic_file_llseek_size(file, offset, whence, size, size); default: return -EINVAL; } } EXPORT_SYMBOL(fixed_size_llseek); /** * no_seek_end_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * */ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, OFFSET_MAX, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek); /** * no_seek_end_llseek_size - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: maximal offset allowed * */ loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, size, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek_size); /** * noop_llseek - No Operation Performed llseek implementation * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is an implementation of ->llseek useable for the rare special case when * userspace expects the seek to succeed but the (device) file is actually not * able to perform the seek. In this case you use noop_llseek() instead of * falling back to the default implementation of ->llseek. */ loff_t noop_llseek(struct file *file, loff_t offset, int whence) { return file->f_pos; } EXPORT_SYMBOL(noop_llseek); loff_t no_llseek(struct file *file, loff_t offset, int whence) { return -ESPIPE; } EXPORT_SYMBOL(no_llseek); loff_t default_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file_inode(file); loff_t retval; inode_lock(inode); switch (whence) { case SEEK_END: offset += i_size_read(inode); break; case SEEK_CUR: if (offset == 0) { retval = file->f_pos; goto out; } offset += file->f_pos; break; case SEEK_DATA: /* * In the generic case the entire file is data, so as * long as offset isn't at the end of the file then the * offset is data. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so * as long as offset isn't i_size or larger, return * i_size. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } offset = inode->i_size; break; } retval = -EINVAL; if (offset >= 0 || unsigned_offsets(file)) { if (offset != file->f_pos) { file->f_pos = offset; file->f_version = 0; } retval = offset; } out: inode_unlock(inode); return retval; } EXPORT_SYMBOL(default_llseek); loff_t vfs_llseek(struct file *file, loff_t offset, int whence) { loff_t (*fn)(struct file *, loff_t, int); fn = no_llseek; if (file->f_mode & FMODE_LSEEK) { if (file->f_op->llseek) fn = file->f_op->llseek; } return fn(file, offset, whence); } EXPORT_SYMBOL(vfs_llseek); static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; struct fd f = fdget_pos(fd); if (!f.file) return -EBADF; retval = -EINVAL; if (whence <= SEEK_MAX) { loff_t res = vfs_llseek(f.file, offset, whence); retval = res; if (res != (loff_t)retval) retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */ } fdput_pos(f); return retval; } SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #endif #if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) || \ defined(__ARCH_WANT_SYS_LLSEEK) SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, unsigned long, offset_low, loff_t __user *, result, unsigned int, whence) { int retval; struct fd f = fdget_pos(fd); loff_t offset; if (!f.file) return -EBADF; retval = -EINVAL; if (whence > SEEK_MAX) goto out_putf; offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low, whence); retval = (int)offset; if (offset >= 0) { retval = -EFAULT; if (!copy_to_user(result, &offset, sizeof(offset))) retval = 0; } out_putf: fdput_pos(f); return retval; } #endif int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { struct inode *inode; int retval = -EINVAL; inode = file_inode(file); if (unlikely((ssize_t) count < 0)) return retval; /* * ranged mandatory locking does not apply to streams - it makes sense * only for files where position has a meaning. */ if (ppos) { loff_t pos = *ppos; if (unlikely(pos < 0)) { if (!unsigned_offsets(file)) return retval; if (count >= -pos) /* both values are in 0..LLONG_MAX */ return -EOVERFLOW; } else if (unlikely((loff_t) (pos + count) < 0)) { if (!unsigned_offsets(file)) return retval; } if (unlikely(inode->i_flctx && mandatory_lock(inode))) { retval = locks_mandatory_area(inode, file, pos, pos + count - 1, read_write == READ ? F_RDLCK : F_WRLCK); if (retval < 0) return retval; } } return security_file_permission(file, read_write == READ ? MAY_READ : MAY_WRITE); } static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct iovec iov = { .iov_base = buf, .iov_len = len }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_init(&iter, READ, &iov, 1, len); ret = call_read_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } static int warn_unsupported(struct file *file, const char *op) { pr_warn_ratelimited( "kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n", op, file, current->pid, current->comm); return -EINVAL; } ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ))) return -EINVAL; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; /* * Also fail if ->read_iter and ->read are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->read_iter || file->f_op->read)) return warn_unsupported(file, "read"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; iov_iter_kvec(&iter, READ, &iov, 1, iov.iov_len); ret = file->f_op->read_iter(&kiocb, &iter); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; return __kernel_read(file, buf, count, pos); } EXPORT_SYMBOL(kernel_read); ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; if (file->f_op->read) ret = file->f_op->read(file, buf, count, pos); else if (file->f_op->read_iter) ret = new_sync_read(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_init(&iter, WRITE, &iov, 1, len); ret = call_write_iter(filp, &kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ret > 0 && ppos) *ppos = kiocb.ki_pos; return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = (void *)buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; /* * Also fail if ->write_iter and ->write are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->write_iter || file->f_op->write)) return warn_unsupported(file, "write"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len); ret = file->f_op->write_iter(&kiocb, &iter); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); return ret; } /* * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()", * but autofs is one of the few internal kernel users that actually * wants this _and_ can be built as a module. So we need to export * this symbol for autofs, even though it really isn't appropriate * for any other kernel modules. */ EXPORT_SYMBOL_GPL(__kernel_write); ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; file_start_write(file); ret = __kernel_write(file, buf, count, pos); file_end_write(file); return ret; } EXPORT_SYMBOL(kernel_write); ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; file_start_write(file); if (file->f_op->write) ret = file->f_op->write(file, buf, count, pos); else if (file->f_op->write_iter) ret = new_sync_write(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); file_end_write(file); return ret; } /* file_ppos returns &file->f_pos or NULL if file is stream */ static inline loff_t *file_ppos(struct file *file) { return file->f_mode & FMODE_STREAM ? NULL : &file->f_pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_read(f.file, buf, count, ppos); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } return ret; } SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) { return ksys_read(fd, buf, count); } ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_write(f.file, buf, count, ppos); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } return ret; } SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, size_t, count) { return ksys_write(fd, buf, count); } ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) ret = vfs_read(f.file, buf, count, &pos); fdput(f); } return ret; } SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, size_t, count, loff_t, pos) { return ksys_pread64(fd, buf, count, pos); } ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) ret = vfs_write(f.file, buf, count, &pos); fdput(f); } return ret; } SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, loff_t, pos) { return ksys_pwrite64(fd, buf, count, pos); } static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); ret = kiocb_set_rw_flags(&kiocb, flags); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); if (type == READ) ret = call_read_iter(filp, &kiocb, iter); else ret = call_write_iter(filp, &kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { ssize_t ret = 0; if (flags & ~RWF_HIPRI) return -EOPNOTSUPP; while (iov_iter_count(iter)) { struct iovec iovec = iov_iter_iovec(iter); ssize_t nr; if (type == READ) { nr = filp->f_op->read(filp, iovec.iov_base, iovec.iov_len, ppos); } else { nr = filp->f_op->write(filp, iovec.iov_base, iovec.iov_len, ppos); } if (nr < 0) { if (!ret) ret = nr; break; } ret += nr; if (nr != iovec.iov_len) break; iov_iter_advance(iter, nr); } return ret; } static ssize_t do_iter_read(struct file *file, struct iov_iter *iter, loff_t *pos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, pos, tot_len); if (ret < 0) return ret; if (file->f_op->read_iter) ret = do_iter_readv_writev(file, iter, pos, READ, flags); else ret = do_loop_readv_writev(file, iter, pos, READ, flags); out: if (ret >= 0) fsnotify_access(file); return ret; } ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; ret = call_read_iter(file, iocb, iter); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_read); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { if (!file->f_op->read_iter) return -EINVAL; return do_iter_read(file, iter, ppos, flags); } EXPORT_SYMBOL(vfs_iter_read); static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, loff_t *pos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, pos, tot_len); if (ret < 0) return ret; if (file->f_op->write_iter) ret = do_iter_readv_writev(file, iter, pos, WRITE, flags); else ret = do_loop_readv_writev(file, iter, pos, WRITE, flags); if (ret > 0) fsnotify_modify(file); return ret; } ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->write_iter) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; ret = call_write_iter(file, iocb, iter); if (ret > 0) fsnotify_modify(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_write); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { if (!file->f_op->write_iter) return -EINVAL; return do_iter_write(file, iter, ppos, flags); } EXPORT_SYMBOL(vfs_iter_write); static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t ret; ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret >= 0) { ret = do_iter_read(file, &iter, pos, flags); kfree(iov); } return ret; } static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t ret; ret = import_iovec(WRITE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret >= 0) { file_start_write(file); ret = do_iter_write(file, &iter, pos, flags); file_end_write(file); kfree(iov); } return ret; } static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_readv(f.file, vec, vlen, ppos, flags); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_writev(f.file, vec, vlen, ppos, flags); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) { #define HALF_LONG_BITS (BITS_PER_LONG / 2) return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; } static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) ret = vfs_readv(f.file, vec, vlen, &pos, flags); fdput(f); } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) ret = vfs_writev(f.file, vec, vlen, &pos, flags); fdput(f); } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_readv(fd, vec, vlen, 0); } SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_writev(fd, vec, vlen, 0); } SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_preadv(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_pwritev(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } /* * Various compat syscalls. Note that they all pretend to take a native * iovec - import_iovec will properly treat those as compat_iovecs based on * in_compat_syscall(). */ #ifdef CONFIG_COMPAT #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_preadv(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_preadv(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_pwritev(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_pwritev(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif /* CONFIG_COMPAT */ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, loff_t max) { struct fd in, out; struct inode *in_inode, *out_inode; loff_t pos; loff_t out_pos; ssize_t retval; int fl; /* * Get input file, and verify that it is ok.. */ retval = -EBADF; in = fdget(in_fd); if (!in.file) goto out; if (!(in.file->f_mode & FMODE_READ)) goto fput_in; retval = -ESPIPE; if (!ppos) { pos = in.file->f_pos; } else { pos = *ppos; if (!(in.file->f_mode & FMODE_PREAD)) goto fput_in; } retval = rw_verify_area(READ, in.file, &pos, count); if (retval < 0) goto fput_in; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; /* * Get output file, and verify that it is ok.. */ retval = -EBADF; out = fdget(out_fd); if (!out.file) goto fput_in; if (!(out.file->f_mode & FMODE_WRITE)) goto fput_out; in_inode = file_inode(in.file); out_inode = file_inode(out.file); out_pos = out.file->f_pos; retval = rw_verify_area(WRITE, out.file, &out_pos, count); if (retval < 0) goto fput_out; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); if (unlikely(pos + count > max)) { retval = -EOVERFLOW; if (pos >= max) goto fput_out; count = max - pos; } fl = 0; #if 0 /* * We need to debate whether we can enable this or not. The * man page documents EAGAIN return for the output at least, * and the application is arguably buggy if it doesn't expect * EAGAIN on a non-blocking file descriptor. */ if (in.file->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif file_start_write(out.file); retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); file_end_write(out.file); if (retval > 0) { add_rchar(current, retval); add_wchar(current, retval); fsnotify_access(in.file); fsnotify_modify(out.file); out.file->f_pos = out_pos; if (ppos) *ppos = pos; else in.file->f_pos = pos; } inc_syscr(current); inc_syscw(current); if (pos > max) retval = -EOVERFLOW; fput_out: fdput(out); fput_in: fdput(in); out: return retval; } SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, compat_off_t __user *, offset, compat_size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, compat_loff_t __user *, offset, compat_size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #endif /** * generic_copy_file_range - copy data between two files * @file_in: file structure to read from * @pos_in: file offset to read from * @file_out: file structure to write data to * @pos_out: file offset to write data to * @len: amount of data to copy * @flags: copy flags * * This is a generic filesystem helper to copy data from one file to another. * It has no constraints on the source or destination file owners - the files * can belong to different superblocks and different filesystem types. Short * copies are allowed. * * This should be called from the @file_out filesystem, as per the * ->copy_file_range() method. * * Returns the number of bytes copied or a negative error indicating the * failure. */ ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { return do_splice_direct(file_in, &pos_in, file_out, &pos_out, len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); } EXPORT_SYMBOL(generic_copy_file_range); /* * Performs necessary checks before doing a file copy * * Can adjust amount of bytes to copy via @req_count argument. * Returns appropriate error code that caller should return or * zero in case the copy should be allowed. */ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t *req_count, unsigned int flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); uint64_t count = *req_count; loff_t size_in; int ret; ret = generic_file_rw_checks(file_in, file_out); if (ret) return ret; /* * We allow some filesystems to handle cross sb copy, but passing * a file of the wrong filesystem type to filesystem driver can result * in an attempt to dereference the wrong type of ->private_data, so * avoid doing that until we really have a good reason. * * nfs and cifs define several different file_system_type structures * and several different sets of file_operations, but they all end up * using the same ->copy_file_range() function pointer. */ if (flags & COPY_FILE_SPLICE) { /* cross sb splice is allowed */ } else if (file_out->f_op->copy_file_range) { if (file_in->f_op->copy_file_range != file_out->f_op->copy_file_range) return -EXDEV; } else if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) { return -EXDEV; } /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Ensure offsets don't wrap. */ if (pos_in + count < pos_in || pos_out + count < pos_out) return -EOVERFLOW; /* Shorten the copy to EOF */ size_in = i_size_read(inode_in); if (pos_in >= size_in) count = 0; else count = min(count, size_in - (uint64_t)pos_in); ret = generic_write_check_limits(file_out, pos_out, &count); if (ret) return ret; /* Don't allow overlapped copying within the same file. */ if (inode_in == inode_out && pos_out + count > pos_in && pos_out < pos_in + count) return -EINVAL; *req_count = count; return 0; } /* * copy_file_range() differs from regular file read and write in that it * specifically allows return partial success. When it does so is up to * the copy_file_range method. */ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { ssize_t ret; bool splice = flags & COPY_FILE_SPLICE; if (flags & ~COPY_FILE_SPLICE) return -EINVAL; ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, flags); if (unlikely(ret)) return ret; ret = rw_verify_area(READ, file_in, &pos_in, len); if (unlikely(ret)) return ret; ret = rw_verify_area(WRITE, file_out, &pos_out, len); if (unlikely(ret)) return ret; if (len == 0) return 0; file_start_write(file_out); /* * Cloning is supported by more file systems, so we implement copy on * same sb using clone, but for filesystems where both clone and copy * are supported (e.g. nfs,cifs), we only call the copy method. */ if (!splice && file_out->f_op->copy_file_range) { ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); goto done; } if (!splice && file_in->f_op->remap_file_range && file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) { ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, min_t(loff_t, MAX_RW_COUNT, len), REMAP_FILE_CAN_SHORTEN); if (ret > 0) goto done; } /* * We can get here for same sb copy of filesystems that do not implement * ->copy_file_range() in case filesystem does not support clone or in * case filesystem supports clone but rejected the clone request (e.g. * because it was not block aligned). * * In both cases, fall back to kernel copy so we are able to maintain a * consistent story about which filesystems support copy_file_range() * and which filesystems do not, that will allow userspace tools to * make consistent desicions w.r.t using copy_file_range(). * * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE. */ ret = generic_copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); done: if (ret > 0) { fsnotify_access(file_in); add_rchar(current, ret); fsnotify_modify(file_out); add_wchar(current, ret); } inc_syscr(current); inc_syscw(current); file_end_write(file_out); return ret; } EXPORT_SYMBOL(vfs_copy_file_range); SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) { loff_t pos_in; loff_t pos_out; struct fd f_in; struct fd f_out; ssize_t ret = -EBADF; f_in = fdget(fd_in); if (!f_in.file) goto out2; f_out = fdget(fd_out); if (!f_out.file) goto out1; ret = -EFAULT; if (off_in) { if (copy_from_user(&pos_in, off_in, sizeof(loff_t))) goto out; } else { pos_in = f_in.file->f_pos; } if (off_out) { if (copy_from_user(&pos_out, off_out, sizeof(loff_t))) goto out; } else { pos_out = f_out.file->f_pos; } ret = -EINVAL; if (flags != 0) goto out; ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len, flags); if (ret > 0) { pos_in += ret; pos_out += ret; if (off_in) { if (copy_to_user(off_in, &pos_in, sizeof(loff_t))) ret = -EFAULT; } else { f_in.file->f_pos = pos_in; } if (off_out) { if (copy_to_user(off_out, &pos_out, sizeof(loff_t))) ret = -EFAULT; } else { f_out.file->f_pos = pos_out; } } out: fdput(f_out); out1: fdput(f_in); out2: return ret; } /* * Don't operate on ranges the page cache doesn't support, and don't exceed the * LFS limits. If pos is under the limit it becomes a short access. If it * exceeds the limit we return -EFBIG. */ int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count) { struct inode *inode = file->f_mapping->host; loff_t max_size = inode->i_sb->s_maxbytes; loff_t limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY) { if (pos >= limit) { send_sig(SIGXFSZ, current, 0); return -EFBIG; } *count = min(*count, limit - pos); } if (!(file->f_flags & O_LARGEFILE)) max_size = MAX_NON_LFS; if (unlikely(pos >= max_size)) return -EFBIG; *count = min(*count, max_size - pos); return 0; } /* * Performs necessary checks before doing a write * * Can adjust writing position or amount of bytes to write. * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */ ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; loff_t count; int ret; if (IS_SWAPFILE(inode)) return -ETXTBSY; if (!iov_iter_count(from)) return 0; /* FIXME: this is for backwards compatibility with 2.4 */ if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) return -EINVAL; count = iov_iter_count(from); ret = generic_write_check_limits(file, iocb->ki_pos, &count); if (ret) return ret; iov_iter_truncate(from, count); return iov_iter_count(from); } EXPORT_SYMBOL(generic_write_checks); /* * Performs common checks before doing a file copy/clone * from @file_in to @file_out. */ int generic_file_rw_checks(struct file *file_in, struct file *file_out) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); /* Don't copy dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || (file_out->f_flags & O_APPEND)) return -EBADF; return 0; } |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 | // SPDX-License-Identifier: GPL-2.0-or-later /* bit search implementation * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * Copyright (C) 2008 IBM Corporation * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au> * (Inspired by David Howell's find_next_bit implementation) * * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease * size and improve performance, 2015. */ #include <linux/bitops.h> #include <linux/bitmap.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/minmax.h> #if !defined(find_next_bit) || !defined(find_next_zero_bit) || \ !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) || \ !defined(find_next_and_bit) /* * This is a common helper function for find_next_bit, find_next_zero_bit, and * find_next_and_bit. The differences are: * - The "invert" argument, which is XORed with each fetched word before * searching it for one bits. * - The optional "addr2", which is anded with "addr1" if present. */ static unsigned long _find_next_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start, unsigned long invert, unsigned long le) { unsigned long tmp, mask; if (unlikely(start >= nbits)) return nbits; tmp = addr1[start / BITS_PER_LONG]; if (addr2) tmp &= addr2[start / BITS_PER_LONG]; tmp ^= invert; /* Handle 1st word. */ mask = BITMAP_FIRST_WORD_MASK(start); if (le) mask = swab(mask); tmp &= mask; start = round_down(start, BITS_PER_LONG); while (!tmp) { start += BITS_PER_LONG; if (start >= nbits) return nbits; tmp = addr1[start / BITS_PER_LONG]; if (addr2) tmp &= addr2[start / BITS_PER_LONG]; tmp ^= invert; } if (le) tmp = swab(tmp); return min(start + __ffs(tmp), nbits); } #endif #ifndef find_next_bit /* * Find the next set bit in a memory region. */ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, 0UL, 0); } EXPORT_SYMBOL(find_next_bit); #endif #ifndef find_next_zero_bit unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); } EXPORT_SYMBOL(find_next_zero_bit); #endif #if !defined(find_next_and_bit) unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); } EXPORT_SYMBOL(find_next_and_bit); #endif #ifndef find_first_bit /* * Find the first set bit in a memory region. */ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; for (idx = 0; idx * BITS_PER_LONG < size; idx++) { if (addr[idx]) return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); } return size; } EXPORT_SYMBOL(find_first_bit); #endif #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region. */ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; for (idx = 0; idx * BITS_PER_LONG < size; idx++) { if (addr[idx] != ~0UL) return min(idx * BITS_PER_LONG + ffz(addr[idx]), size); } return size; } EXPORT_SYMBOL(find_first_zero_bit); #endif #ifndef find_last_bit unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (size) { unsigned long val = BITMAP_LAST_WORD_MASK(size); unsigned long idx = (size-1) / BITS_PER_LONG; do { val &= addr[idx]; if (val) return idx * BITS_PER_LONG + __fls(val); val = ~0ul; } while (idx--); } return size; } EXPORT_SYMBOL(find_last_bit); #endif #ifdef __BIG_ENDIAN #ifndef find_next_zero_bit_le unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); } EXPORT_SYMBOL(find_next_zero_bit_le); #endif #ifndef find_next_bit_le unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, NULL, size, offset, 0UL, 1); } EXPORT_SYMBOL(find_next_bit_le); #endif #endif /* __BIG_ENDIAN */ unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr, unsigned long size, unsigned long offset) { offset = find_next_bit(addr, size, offset); if (offset == size) return size; offset = round_down(offset, 8); *clump = bitmap_get_value8(addr, offset); return offset; } EXPORT_SYMBOL(find_next_clump8); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * RCU-based infrastructure for lightweight reader-writer locking * * Copyright (c) 2015, Red Hat, Inc. * * Author: Oleg Nesterov <oleg@redhat.com> */ #ifndef _LINUX_RCU_SYNC_H_ #define _LINUX_RCU_SYNC_H_ #include <linux/wait.h> #include <linux/rcupdate.h> /* Structure to mediate between updaters and fastpath-using readers. */ struct rcu_sync { int gp_state; int gp_count; wait_queue_head_t gp_wait; struct rcu_head cb_head; }; /** * rcu_sync_is_idle() - Are readers permitted to use their fastpaths? * @rsp: Pointer to rcu_sync structure to use for synchronization * * Returns true if readers are permitted to use their fastpaths. Must be * invoked within some flavor of RCU read-side critical section. */ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) { RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), "suspicious rcu_sync_is_idle() usage"); return !READ_ONCE(rsp->gp_state); /* GP_IDLE */ } extern void rcu_sync_init(struct rcu_sync *); extern void rcu_sync_enter_start(struct rcu_sync *); extern void rcu_sync_enter(struct rcu_sync *); extern void rcu_sync_exit(struct rcu_sync *); extern void rcu_sync_dtor(struct rcu_sync *); #define __RCU_SYNC_INITIALIZER(name) { \ .gp_state = 0, \ .gp_count = 0, \ .gp_wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.gp_wait), \ } #define DEFINE_RCU_SYNC(name) \ struct rcu_sync name = __RCU_SYNC_INITIALIZER(name) #endif /* _LINUX_RCU_SYNC_H_ */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Security plug functions * * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> * Copyright (C) 2001-2002 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2016 Mellanox Technologies */ #define pr_fmt(fmt) "LSM: " fmt #include <linux/bpf.h> #include <linux/capability.h> #include <linux/dcache.h> #include <linux/export.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/lsm_hooks.h> #include <linux/integrity.h> #include <linux/ima.h> #include <linux/evm.h> #include <linux/fsnotify.h> #include <linux/mman.h> #include <linux/mount.h> #include <linux/personality.h> #include <linux/backing-dev.h> #include <linux/string.h> #include <linux/msg.h> #include <net/flow.h> #define MAX_LSM_EVM_XATTR 2 /* How many LSMs were built into the kernel? */ #define LSM_COUNT (__end_lsm_info - __start_lsm_info) /* * These are descriptions of the reasons that can be passed to the * security_locked_down() LSM hook. Placing this array here allows * all security modules to use the same descriptions for auditing * purposes. */ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = { [LOCKDOWN_NONE] = "none", [LOCKDOWN_MODULE_SIGNATURE] = "unsigned module loading", [LOCKDOWN_DEV_MEM] = "/dev/mem,kmem,port", [LOCKDOWN_EFI_TEST] = "/dev/efi_test access", [LOCKDOWN_KEXEC] = "kexec of unsigned images", [LOCKDOWN_HIBERNATION] = "hibernation", [LOCKDOWN_PCI_ACCESS] = "direct PCI access", [LOCKDOWN_IOPORT] = "raw io port access", [LOCKDOWN_MSR] = "raw MSR access", [LOCKDOWN_ACPI_TABLES] = "modifying ACPI tables", [LOCKDOWN_PCMCIA_CIS] = "direct PCMCIA CIS storage", [LOCKDOWN_TIOCSSERIAL] = "reconfiguration of serial port IO", [LOCKDOWN_MODULE_PARAMETERS] = "unsafe module parameters", [LOCKDOWN_MMIOTRACE] = "unsafe mmio", [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", [LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", [LOCKDOWN_BPF_READ] = "use of bpf to read kernel RAM", [LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", [LOCKDOWN_CONFIDENTIALITY_MAX] = "confidentiality", }; struct security_hook_heads security_hook_heads __lsm_ro_after_init; static BLOCKING_NOTIFIER_HEAD(blocking_lsm_notifier_chain); static struct kmem_cache *lsm_file_cache; static struct kmem_cache *lsm_inode_cache; char *lsm_names; static struct lsm_blob_sizes blob_sizes __lsm_ro_after_init; /* Boot-time LSM user choice */ static __initdata const char *chosen_lsm_order; static __initdata const char *chosen_major_lsm; static __initconst const char * const builtin_lsm_order = CONFIG_LSM; /* Ordered list of LSMs to initialize. */ static __initdata struct lsm_info **ordered_lsms; static __initdata struct lsm_info *exclusive; static __initdata bool debug; #define init_debug(...) \ do { \ if (debug) \ pr_info(__VA_ARGS__); \ } while (0) static bool __init is_enabled(struct lsm_info *lsm) { if (!lsm->enabled) return false; return *lsm->enabled; } /* Mark an LSM's enabled flag. */ static int lsm_enabled_true __initdata = 1; static int lsm_enabled_false __initdata = 0; static void __init set_enabled(struct lsm_info *lsm, bool enabled) { /* * When an LSM hasn't configured an enable variable, we can use * a hard-coded location for storing the default enabled state. */ if (!lsm->enabled) { if (enabled) lsm->enabled = &lsm_enabled_true; else lsm->enabled = &lsm_enabled_false; } else if (lsm->enabled == &lsm_enabled_true) { if (!enabled) lsm->enabled = &lsm_enabled_false; } else if (lsm->enabled == &lsm_enabled_false) { if (enabled) lsm->enabled = &lsm_enabled_true; } else { *lsm->enabled = enabled; } } /* Is an LSM already listed in the ordered LSMs list? */ static bool __init exists_ordered_lsm(struct lsm_info *lsm) { struct lsm_info **check; for (check = ordered_lsms; *check; check++) if (*check == lsm) return true; return false; } /* Append an LSM to the list of ordered LSMs to initialize. */ static int last_lsm __initdata; static void __init append_ordered_lsm(struct lsm_info *lsm, const char *from) { /* Ignore duplicate selections. */ if (exists_ordered_lsm(lsm)) return; if (WARN(last_lsm == LSM_COUNT, "%s: out of LSM slots!?\n", from)) return; /* Enable this LSM, if it is not already set. */ if (!lsm->enabled) lsm->enabled = &lsm_enabled_true; ordered_lsms[last_lsm++] = lsm; init_debug("%s ordering: %s (%sabled)\n", from, lsm->name, is_enabled(lsm) ? "en" : "dis"); } /* Is an LSM allowed to be initialized? */ static bool __init lsm_allowed(struct lsm_info *lsm) { /* Skip if the LSM is disabled. */ if (!is_enabled(lsm)) return false; /* Not allowed if another exclusive LSM already initialized. */ if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && exclusive) { init_debug("exclusive disabled: %s\n", lsm->name); return false; } return true; } static void __init lsm_set_blob_size(int *need, int *lbs) { int offset; if (*need > 0) { offset = *lbs; *lbs += *need; *need = offset; } } static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) { if (!needed) return; lsm_set_blob_size(&needed->lbs_cred, &blob_sizes.lbs_cred); lsm_set_blob_size(&needed->lbs_file, &blob_sizes.lbs_file); /* * The inode blob gets an rcu_head in addition to * what the modules might need. */ if (needed->lbs_inode && blob_sizes.lbs_inode == 0) blob_sizes.lbs_inode = sizeof(struct rcu_head); lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode); lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc); lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg); lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task); } /* Prepare LSM for initialization. */ static void __init prepare_lsm(struct lsm_info *lsm) { int enabled = lsm_allowed(lsm); /* Record enablement (to handle any following exclusive LSMs). */ set_enabled(lsm, enabled); /* If enabled, do pre-initialization work. */ if (enabled) { if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && !exclusive) { exclusive = lsm; init_debug("exclusive chosen: %s\n", lsm->name); } lsm_set_blob_sizes(lsm->blobs); } } /* Initialize a given LSM, if it is enabled. */ static void __init initialize_lsm(struct lsm_info *lsm) { if (is_enabled(lsm)) { int ret; init_debug("initializing %s\n", lsm->name); ret = lsm->init(); WARN(ret, "%s failed to initialize: %d\n", lsm->name, ret); } } /* Populate ordered LSMs list from comma-separated LSM name list. */ static void __init ordered_lsm_parse(const char *order, const char *origin) { struct lsm_info *lsm; char *sep, *name, *next; /* LSM_ORDER_FIRST is always first. */ for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (lsm->order == LSM_ORDER_FIRST) append_ordered_lsm(lsm, "first"); } /* Process "security=", if given. */ if (chosen_major_lsm) { struct lsm_info *major; /* * To match the original "security=" behavior, this * explicitly does NOT fallback to another Legacy Major * if the selected one was separately disabled: disable * all non-matching Legacy Major LSMs. */ for (major = __start_lsm_info; major < __end_lsm_info; major++) { if ((major->flags & LSM_FLAG_LEGACY_MAJOR) && strcmp(major->name, chosen_major_lsm) != 0) { set_enabled(major, false); init_debug("security=%s disabled: %s\n", chosen_major_lsm, major->name); } } } sep = kstrdup(order, GFP_KERNEL); next = sep; /* Walk the list, looking for matching LSMs. */ while ((name = strsep(&next, ",")) != NULL) { bool found = false; for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (lsm->order == LSM_ORDER_MUTABLE && strcmp(lsm->name, name) == 0) { append_ordered_lsm(lsm, origin); found = true; } } if (!found) init_debug("%s ignored: %s\n", origin, name); } /* Process "security=", if given. */ if (chosen_major_lsm) { for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (exists_ordered_lsm(lsm)) continue; if (strcmp(lsm->name, chosen_major_lsm) == 0) append_ordered_lsm(lsm, "security="); } } /* Disable all LSMs not in the ordered list. */ for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (exists_ordered_lsm(lsm)) continue; set_enabled(lsm, false); init_debug("%s disabled: %s\n", origin, lsm->name); } kfree(sep); } static void __init lsm_early_cred(struct cred *cred); static void __init lsm_early_task(struct task_struct *task); static int lsm_append(const char *new, char **result); static void __init ordered_lsm_init(void) { struct lsm_info **lsm; ordered_lsms = kcalloc(LSM_COUNT + 1, sizeof(*ordered_lsms), GFP_KERNEL); if (chosen_lsm_order) { if (chosen_major_lsm) { pr_info("security= is ignored because it is superseded by lsm=\n"); chosen_major_lsm = NULL; } ordered_lsm_parse(chosen_lsm_order, "cmdline"); } else ordered_lsm_parse(builtin_lsm_order, "builtin"); for (lsm = ordered_lsms; *lsm; lsm++) prepare_lsm(*lsm); init_debug("cred blob size = %d\n", blob_sizes.lbs_cred); init_debug("file blob size = %d\n", blob_sizes.lbs_file); init_debug("inode blob size = %d\n", blob_sizes.lbs_inode); init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc); init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg); init_debug("task blob size = %d\n", blob_sizes.lbs_task); /* * Create any kmem_caches needed for blobs */ if (blob_sizes.lbs_file) lsm_file_cache = kmem_cache_create("lsm_file_cache", blob_sizes.lbs_file, 0, SLAB_PANIC, NULL); if (blob_sizes.lbs_inode) lsm_inode_cache = kmem_cache_create("lsm_inode_cache", blob_sizes.lbs_inode, 0, SLAB_PANIC, NULL); lsm_early_cred((struct cred *) current->cred); lsm_early_task(current); for (lsm = ordered_lsms; *lsm; lsm++) initialize_lsm(*lsm); kfree(ordered_lsms); } int __init early_security_init(void) { int i; struct hlist_head *list = (struct hlist_head *) &security_hook_heads; struct lsm_info *lsm; for (i = 0; i < sizeof(security_hook_heads) / sizeof(struct hlist_head); i++) INIT_HLIST_HEAD(&list[i]); for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) { if (!lsm->enabled) lsm->enabled = &lsm_enabled_true; prepare_lsm(lsm); initialize_lsm(lsm); } return 0; } /** * security_init - initializes the security framework * * This should be called early in the kernel initialization sequence. */ int __init security_init(void) { struct lsm_info *lsm; pr_info("Security Framework initializing\n"); /* * Append the names of the early LSM modules now that kmalloc() is * available */ for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) { if (lsm->enabled) lsm_append(lsm->name, &lsm_names); } /* Load LSMs in specified order. */ ordered_lsm_init(); return 0; } /* Save user chosen LSM */ static int __init choose_major_lsm(char *str) { chosen_major_lsm = str; return 1; } __setup("security=", choose_major_lsm); /* Explicitly choose LSM initialization order. */ static int __init choose_lsm_order(char *str) { chosen_lsm_order = str; return 1; } __setup("lsm=", choose_lsm_order); /* Enable LSM order debugging. */ static int __init enable_debug(char *str) { debug = true; return 1; } __setup("lsm.debug", enable_debug); static bool match_last_lsm(const char *list, const char *lsm) { const char *last; if (WARN_ON(!list || !lsm)) return false; last = strrchr(list, ','); if (last) /* Pass the comma, strcmp() will check for '\0' */ last++; else last = list; return !strcmp(last, lsm); } static int lsm_append(const char *new, char **result) { char *cp; if (*result == NULL) { *result = kstrdup(new, GFP_KERNEL); if (*result == NULL) return -ENOMEM; } else { /* Check if it is the last registered name */ if (match_last_lsm(*result, new)) return 0; cp = kasprintf(GFP_KERNEL, "%s,%s", *result, new); if (cp == NULL) return -ENOMEM; kfree(*result); *result = cp; } return 0; } /** * security_add_hooks - Add a modules hooks to the hook lists. * @hooks: the hooks to add * @count: the number of hooks to add * @lsm: the name of the security module * * Each LSM has to register its hooks with the infrastructure. */ void __init security_add_hooks(struct security_hook_list *hooks, int count, char *lsm) { int i; for (i = 0; i < count; i++) { hooks[i].lsm = lsm; hlist_add_tail_rcu(&hooks[i].list, hooks[i].head); } /* * Don't try to append during early_security_init(), we'll come back * and fix this up afterwards. */ if (slab_is_available()) { if (lsm_append(lsm, &lsm_names) < 0) panic("%s - Cannot get early memory.\n", __func__); } } int call_blocking_lsm_notifier(enum lsm_event event, void *data) { return blocking_notifier_call_chain(&blocking_lsm_notifier_chain, event, data); } EXPORT_SYMBOL(call_blocking_lsm_notifier); int register_blocking_lsm_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&blocking_lsm_notifier_chain, nb); } EXPORT_SYMBOL(register_blocking_lsm_notifier); int unregister_blocking_lsm_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&blocking_lsm_notifier_chain, nb); } EXPORT_SYMBOL(unregister_blocking_lsm_notifier); /** * lsm_cred_alloc - allocate a composite cred blob * @cred: the cred that needs a blob * @gfp: allocation type * * Allocate the cred blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_cred_alloc(struct cred *cred, gfp_t gfp) { if (blob_sizes.lbs_cred == 0) { cred->security = NULL; return 0; } cred->security = kzalloc(blob_sizes.lbs_cred, gfp); if (cred->security == NULL) return -ENOMEM; return 0; } /** * lsm_early_cred - during initialization allocate a composite cred blob * @cred: the cred that needs a blob * * Allocate the cred blob for all the modules */ static void __init lsm_early_cred(struct cred *cred) { int rc = lsm_cred_alloc(cred, GFP_KERNEL); if (rc) panic("%s: Early cred alloc failed.\n", __func__); } /** * lsm_file_alloc - allocate a composite file blob * @file: the file that needs a blob * * Allocate the file blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_file_alloc(struct file *file) { if (!lsm_file_cache) { file->f_security = NULL; return 0; } file->f_security = kmem_cache_zalloc(lsm_file_cache, GFP_KERNEL); if (file->f_security == NULL) return -ENOMEM; return 0; } /** * lsm_inode_alloc - allocate a composite inode blob * @inode: the inode that needs a blob * * Allocate the inode blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ int lsm_inode_alloc(struct inode *inode) { if (!lsm_inode_cache) { inode->i_security = NULL; return 0; } inode->i_security = kmem_cache_zalloc(lsm_inode_cache, GFP_NOFS); if (inode->i_security == NULL) return -ENOMEM; return 0; } /** * lsm_task_alloc - allocate a composite task blob * @task: the task that needs a blob * * Allocate the task blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_task_alloc(struct task_struct *task) { if (blob_sizes.lbs_task == 0) { task->security = NULL; return 0; } task->security = kzalloc(blob_sizes.lbs_task, GFP_KERNEL); if (task->security == NULL) return -ENOMEM; return 0; } /** * lsm_ipc_alloc - allocate a composite ipc blob * @kip: the ipc that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_ipc_alloc(struct kern_ipc_perm *kip) { if (blob_sizes.lbs_ipc == 0) { kip->security = NULL; return 0; } kip->security = kzalloc(blob_sizes.lbs_ipc, GFP_KERNEL); if (kip->security == NULL) return -ENOMEM; return 0; } /** * lsm_msg_msg_alloc - allocate a composite msg_msg blob * @mp: the msg_msg that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_msg_msg_alloc(struct msg_msg *mp) { if (blob_sizes.lbs_msg_msg == 0) { mp->security = NULL; return 0; } mp->security = kzalloc(blob_sizes.lbs_msg_msg, GFP_KERNEL); if (mp->security == NULL) return -ENOMEM; return 0; } /** * lsm_early_task - during initialization allocate a composite task blob * @task: the task that needs a blob * * Allocate the task blob for all the modules */ static void __init lsm_early_task(struct task_struct *task) { int rc = lsm_task_alloc(task); if (rc) panic("%s: Early task alloc failed.\n", __func__); } /* * The default value of the LSM hook is defined in linux/lsm_hook_defs.h and * can be accessed with: * * LSM_RET_DEFAULT(<hook_name>) * * The macros below define static constants for the default value of each * LSM hook. */ #define LSM_RET_DEFAULT(NAME) (NAME##_default) #define DECLARE_LSM_RET_DEFAULT_void(DEFAULT, NAME) #define DECLARE_LSM_RET_DEFAULT_int(DEFAULT, NAME) \ static const int LSM_RET_DEFAULT(NAME) = (DEFAULT); #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ DECLARE_LSM_RET_DEFAULT_##RET(DEFAULT, NAME) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK /* * Hook list operation macros. * * call_void_hook: * This is a hook that does not return a value. * * call_int_hook: * This is a hook that returns a value. */ #define call_void_hook(FUNC, ...) \ do { \ struct security_hook_list *P; \ \ hlist_for_each_entry(P, &security_hook_heads.FUNC, list) \ P->hook.FUNC(__VA_ARGS__); \ } while (0) #define call_int_hook(FUNC, IRC, ...) ({ \ int RC = IRC; \ do { \ struct security_hook_list *P; \ \ hlist_for_each_entry(P, &security_hook_heads.FUNC, list) { \ RC = P->hook.FUNC(__VA_ARGS__); \ if (RC != 0) \ break; \ } \ } while (0); \ RC; \ }) /* Security operations */ int security_binder_set_context_mgr(const struct cred *mgr) { return call_int_hook(binder_set_context_mgr, 0, mgr); } int security_binder_transaction(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transaction, 0, from, to); } int security_binder_transfer_binder(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transfer_binder, 0, from, to); } int security_binder_transfer_file(const struct cred *from, const struct cred *to, struct file *file) { return call_int_hook(binder_transfer_file, 0, from, to, file); } int security_ptrace_access_check(struct task_struct *child, unsigned int mode) { return call_int_hook(ptrace_access_check, 0, child, mode); } int security_ptrace_traceme(struct task_struct *parent) { return call_int_hook(ptrace_traceme, 0, parent); } int security_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return call_int_hook(capget, 0, target, effective, inheritable, permitted); } int security_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return call_int_hook(capset, 0, new, old, effective, inheritable, permitted); } int security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return call_int_hook(capable, 0, cred, ns, cap, opts); } int security_quotactl(int cmds, int type, int id, struct super_block *sb) { return call_int_hook(quotactl, 0, cmds, type, id, sb); } int security_quota_on(struct dentry *dentry) { return call_int_hook(quota_on, 0, dentry); } int security_syslog(int type) { return call_int_hook(syslog, 0, type); } int security_settime64(const struct timespec64 *ts, const struct timezone *tz) { return call_int_hook(settime, 0, ts, tz); } int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { struct security_hook_list *hp; int cap_sys_admin = 1; int rc; /* * The module will respond with a positive value if * it thinks the __vm_enough_memory() call should be * made with the cap_sys_admin set. If all of the modules * agree that it should be set it will. If any module * thinks it should not be set it won't. */ hlist_for_each_entry(hp, &security_hook_heads.vm_enough_memory, list) { rc = hp->hook.vm_enough_memory(mm, pages); if (rc <= 0) { cap_sys_admin = 0; break; } } return __vm_enough_memory(mm, pages, cap_sys_admin); } int security_bprm_creds_for_exec(struct linux_binprm *bprm) { return call_int_hook(bprm_creds_for_exec, 0, bprm); } int security_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file) { return call_int_hook(bprm_creds_from_file, 0, bprm, file); } int security_bprm_check(struct linux_binprm *bprm) { int ret; ret = call_int_hook(bprm_check_security, 0, bprm); if (ret) return ret; return ima_bprm_check(bprm); } void security_bprm_committing_creds(struct linux_binprm *bprm) { call_void_hook(bprm_committing_creds, bprm); } void security_bprm_committed_creds(struct linux_binprm *bprm) { call_void_hook(bprm_committed_creds, bprm); } int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { return call_int_hook(fs_context_dup, 0, fc, src_fc); } int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct security_hook_list *hp; int trc; int rc = -ENOPARAM; hlist_for_each_entry(hp, &security_hook_heads.fs_context_parse_param, list) { trc = hp->hook.fs_context_parse_param(fc, param); if (trc == 0) rc = 0; else if (trc != -ENOPARAM) return trc; } return rc; } int security_sb_alloc(struct super_block *sb) { return call_int_hook(sb_alloc_security, 0, sb); } void security_sb_free(struct super_block *sb) { call_void_hook(sb_free_security, sb); } void security_free_mnt_opts(void **mnt_opts) { if (!*mnt_opts) return; call_void_hook(sb_free_mnt_opts, *mnt_opts); *mnt_opts = NULL; } EXPORT_SYMBOL(security_free_mnt_opts); int security_sb_eat_lsm_opts(char *options, void **mnt_opts) { return call_int_hook(sb_eat_lsm_opts, 0, options, mnt_opts); } EXPORT_SYMBOL(security_sb_eat_lsm_opts); int security_sb_remount(struct super_block *sb, void *mnt_opts) { return call_int_hook(sb_remount, 0, sb, mnt_opts); } EXPORT_SYMBOL(security_sb_remount); int security_sb_kern_mount(struct super_block *sb) { return call_int_hook(sb_kern_mount, 0, sb); } int security_sb_show_options(struct seq_file *m, struct super_block *sb) { return call_int_hook(sb_show_options, 0, m, sb); } int security_sb_statfs(struct dentry *dentry) { return call_int_hook(sb_statfs, 0, dentry); } int security_sb_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { return call_int_hook(sb_mount, 0, dev_name, path, type, flags, data); } int security_sb_umount(struct vfsmount *mnt, int flags) { return call_int_hook(sb_umount, 0, mnt, flags); } int security_sb_pivotroot(const struct path *old_path, const struct path *new_path) { return call_int_hook(sb_pivotroot, 0, old_path, new_path); } int security_sb_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { return call_int_hook(sb_set_mnt_opts, mnt_opts ? -EOPNOTSUPP : 0, sb, mnt_opts, kern_flags, set_kern_flags); } EXPORT_SYMBOL(security_sb_set_mnt_opts); int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { return call_int_hook(sb_clone_mnt_opts, 0, oldsb, newsb, kern_flags, set_kern_flags); } EXPORT_SYMBOL(security_sb_clone_mnt_opts); int security_add_mnt_opt(const char *option, const char *val, int len, void **mnt_opts) { return call_int_hook(sb_add_mnt_opt, -EINVAL, option, val, len, mnt_opts); } EXPORT_SYMBOL(security_add_mnt_opt); int security_move_mount(const struct path *from_path, const struct path *to_path) { return call_int_hook(move_mount, 0, from_path, to_path); } int security_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { return call_int_hook(path_notify, 0, path, mask, obj_type); } int security_inode_alloc(struct inode *inode) { int rc = lsm_inode_alloc(inode); if (unlikely(rc)) return rc; rc = call_int_hook(inode_alloc_security, 0, inode); if (unlikely(rc)) security_inode_free(inode); return rc; } static void inode_free_by_rcu(struct rcu_head *head) { /* * The rcu head is at the start of the inode blob */ kmem_cache_free(lsm_inode_cache, head); } void security_inode_free(struct inode *inode) { integrity_inode_free(inode); call_void_hook(inode_free_security, inode); /* * The inode may still be referenced in a path walk and * a call to security_inode_permission() can be made * after inode_free_security() is called. Ideally, the VFS * wouldn't do this, but fixing that is a much harder * job. For now, simply free the i_security via RCU, and * leave the current inode->i_security pointer intact. * The inode will be freed after the RCU grace period too. */ if (inode->i_security) call_rcu((struct rcu_head *)inode->i_security, inode_free_by_rcu); } int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, void **ctx, u32 *ctxlen) { return call_int_hook(dentry_init_security, -EOPNOTSUPP, dentry, mode, name, ctx, ctxlen); } EXPORT_SYMBOL(security_dentry_init_security); int security_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) { return call_int_hook(dentry_create_files_as, 0, dentry, mode, name, old, new); } EXPORT_SYMBOL(security_dentry_create_files_as); int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const initxattrs initxattrs, void *fs_data) { struct xattr new_xattrs[MAX_LSM_EVM_XATTR + 1]; struct xattr *lsm_xattr, *evm_xattr, *xattr; int ret; if (unlikely(IS_PRIVATE(inode))) return 0; if (!initxattrs) return call_int_hook(inode_init_security, -EOPNOTSUPP, inode, dir, qstr, NULL, NULL, NULL); memset(new_xattrs, 0, sizeof(new_xattrs)); lsm_xattr = new_xattrs; ret = call_int_hook(inode_init_security, -EOPNOTSUPP, inode, dir, qstr, &lsm_xattr->name, &lsm_xattr->value, &lsm_xattr->value_len); if (ret) goto out; evm_xattr = lsm_xattr + 1; ret = evm_inode_init_security(inode, lsm_xattr, evm_xattr); if (ret) goto out; ret = initxattrs(inode, new_xattrs, fs_data); out: for (xattr = new_xattrs; xattr->value != NULL; xattr++) kfree(xattr->value); return (ret == -EOPNOTSUPP) ? 0 : ret; } EXPORT_SYMBOL(security_inode_init_security); int security_old_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const char **name, void **value, size_t *len) { if (unlikely(IS_PRIVATE(inode))) return -EOPNOTSUPP; return call_int_hook(inode_init_security, -EOPNOTSUPP, inode, dir, qstr, name, value, len); } EXPORT_SYMBOL(security_old_inode_init_security); #ifdef CONFIG_SECURITY_PATH int security_path_mknod(const struct path *dir, struct dentry *dentry, umode_t mode, unsigned int dev) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mknod, 0, dir, dentry, mode, dev); } EXPORT_SYMBOL(security_path_mknod); int security_path_mkdir(const struct path *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mkdir, 0, dir, dentry, mode); } EXPORT_SYMBOL(security_path_mkdir); int security_path_rmdir(const struct path *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_rmdir, 0, dir, dentry); } int security_path_unlink(const struct path *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_unlink, 0, dir, dentry); } EXPORT_SYMBOL(security_path_unlink); int security_path_symlink(const struct path *dir, struct dentry *dentry, const char *old_name) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_symlink, 0, dir, dentry, old_name); } int security_path_link(struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)))) return 0; return call_int_hook(path_link, 0, old_dentry, new_dir, new_dentry); } int security_path_rename(const struct path *old_dir, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry, unsigned int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) || (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; if (flags & RENAME_EXCHANGE) { int err = call_int_hook(path_rename, 0, new_dir, new_dentry, old_dir, old_dentry); if (err) return err; } return call_int_hook(path_rename, 0, old_dir, old_dentry, new_dir, new_dentry); } EXPORT_SYMBOL(security_path_rename); int security_path_truncate(const struct path *path) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_truncate, 0, path); } int security_path_chmod(const struct path *path, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_chmod, 0, path, mode); } int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(path_chown, 0, path, uid, gid); } int security_path_chroot(const struct path *path) { return call_int_hook(path_chroot, 0, path); } #endif int security_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_create, 0, dir, dentry, mode); } EXPORT_SYMBOL_GPL(security_inode_create); int security_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)))) return 0; return call_int_hook(inode_link, 0, old_dentry, dir, new_dentry); } int security_inode_unlink(struct inode *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_unlink, 0, dir, dentry); } int security_inode_symlink(struct inode *dir, struct dentry *dentry, const char *old_name) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_symlink, 0, dir, dentry, old_name); } int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_mkdir, 0, dir, dentry, mode); } EXPORT_SYMBOL_GPL(security_inode_mkdir); int security_inode_rmdir(struct inode *dir, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_rmdir, 0, dir, dentry); } int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { if (unlikely(IS_PRIVATE(dir))) return 0; return call_int_hook(inode_mknod, 0, dir, dentry, mode, dev); } int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) || (d_is_positive(new_dentry) && IS_PRIVATE(d_backing_inode(new_dentry))))) return 0; if (flags & RENAME_EXCHANGE) { int err = call_int_hook(inode_rename, 0, new_dir, new_dentry, old_dir, old_dentry); if (err) return err; } return call_int_hook(inode_rename, 0, old_dir, old_dentry, new_dir, new_dentry); } int security_inode_readlink(struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_readlink, 0, dentry); } int security_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_follow_link, 0, dentry, inode, rcu); } int security_inode_permission(struct inode *inode, int mask) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_permission, 0, inode, mask); } int security_inode_setattr(struct dentry *dentry, struct iattr *attr) { int ret; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; ret = call_int_hook(inode_setattr, 0, dentry, attr); if (ret) return ret; return evm_inode_setattr(dentry, attr); } EXPORT_SYMBOL_GPL(security_inode_setattr); int security_inode_getattr(const struct path *path) { if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry)))) return 0; return call_int_hook(inode_getattr, 0, path); } int security_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { int ret; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; /* * SELinux and Smack integrate the cap call, * so assume that all LSMs supplying this call do so. */ ret = call_int_hook(inode_setxattr, 1, dentry, name, value, size, flags); if (ret == 1) ret = cap_inode_setxattr(dentry, name, value, size, flags); if (ret) return ret; ret = ima_inode_setxattr(dentry, name, value, size); if (ret) return ret; return evm_inode_setxattr(dentry, name, value, size); } void security_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(inode_post_setxattr, dentry, name, value, size, flags); evm_inode_post_setxattr(dentry, name, value, size); } int security_inode_getxattr(struct dentry *dentry, const char *name) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_getxattr, 0, dentry, name); } int security_inode_listxattr(struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; return call_int_hook(inode_listxattr, 0, dentry); } int security_inode_removexattr(struct dentry *dentry, const char *name) { int ret; if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; /* * SELinux and Smack integrate the cap call, * so assume that all LSMs supplying this call do so. */ ret = call_int_hook(inode_removexattr, 1, dentry, name); if (ret == 1) ret = cap_inode_removexattr(dentry, name); if (ret) return ret; ret = ima_inode_removexattr(dentry, name); if (ret) return ret; return evm_inode_removexattr(dentry, name); } int security_inode_need_killpriv(struct dentry *dentry) { return call_int_hook(inode_need_killpriv, 0, dentry); } int security_inode_killpriv(struct dentry *dentry) { return call_int_hook(inode_killpriv, 0, dentry); } int security_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) { struct security_hook_list *hp; int rc; if (unlikely(IS_PRIVATE(inode))) return LSM_RET_DEFAULT(inode_getsecurity); /* * Only one module will provide an attribute with a given name. */ hlist_for_each_entry(hp, &security_hook_heads.inode_getsecurity, list) { rc = hp->hook.inode_getsecurity(inode, name, buffer, alloc); if (rc != LSM_RET_DEFAULT(inode_getsecurity)) return rc; } return LSM_RET_DEFAULT(inode_getsecurity); } int security_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct security_hook_list *hp; int rc; if (unlikely(IS_PRIVATE(inode))) return LSM_RET_DEFAULT(inode_setsecurity); /* * Only one module will provide an attribute with a given name. */ hlist_for_each_entry(hp, &security_hook_heads.inode_setsecurity, list) { rc = hp->hook.inode_setsecurity(inode, name, value, size, flags); if (rc != LSM_RET_DEFAULT(inode_setsecurity)) return rc; } return LSM_RET_DEFAULT(inode_setsecurity); } int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { if (unlikely(IS_PRIVATE(inode))) return 0; return call_int_hook(inode_listsecurity, 0, inode, buffer, buffer_size); } EXPORT_SYMBOL(security_inode_listsecurity); void security_inode_getsecid(struct inode *inode, u32 *secid) { call_void_hook(inode_getsecid, inode, secid); } int security_inode_copy_up(struct dentry *src, struct cred **new) { return call_int_hook(inode_copy_up, 0, src, new); } EXPORT_SYMBOL(security_inode_copy_up); int security_inode_copy_up_xattr(const char *name) { struct security_hook_list *hp; int rc; /* * The implementation can return 0 (accept the xattr), 1 (discard the * xattr), -EOPNOTSUPP if it does not know anything about the xattr or * any other error code incase of an error. */ hlist_for_each_entry(hp, &security_hook_heads.inode_copy_up_xattr, list) { rc = hp->hook.inode_copy_up_xattr(name); if (rc != LSM_RET_DEFAULT(inode_copy_up_xattr)) return rc; } return LSM_RET_DEFAULT(inode_copy_up_xattr); } EXPORT_SYMBOL(security_inode_copy_up_xattr); int security_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { return call_int_hook(kernfs_init_security, 0, kn_dir, kn); } int security_file_permission(struct file *file, int mask) { int ret; ret = call_int_hook(file_permission, 0, file, mask); if (ret) return ret; return fsnotify_perm(file, mask); } int security_file_alloc(struct file *file) { int rc = lsm_file_alloc(file); if (rc) return rc; rc = call_int_hook(file_alloc_security, 0, file); if (unlikely(rc)) security_file_free(file); return rc; } void security_file_free(struct file *file) { void *blob; call_void_hook(file_free_security, file); blob = file->f_security; if (blob) { file->f_security = NULL; kmem_cache_free(lsm_file_cache, blob); } } int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_ioctl, 0, file, cmd, arg); } EXPORT_SYMBOL_GPL(security_file_ioctl); /** * security_file_ioctl_compat() - Check if an ioctl is allowed in compat mode * @file: associated file * @cmd: ioctl cmd * @arg: ioctl arguments * * Compat version of security_file_ioctl() that correctly handles 32-bit * processes running on 64-bit kernels. * * Return: Returns 0 if permission is granted. */ int security_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_ioctl_compat, 0, file, cmd, arg); } EXPORT_SYMBOL_GPL(security_file_ioctl_compat); static inline unsigned long mmap_prot(struct file *file, unsigned long prot) { /* * Does we have PROT_READ and does the application expect * it to imply PROT_EXEC? If not, nothing to talk about... */ if ((prot & (PROT_READ | PROT_EXEC)) != PROT_READ) return prot; if (!(current->personality & READ_IMPLIES_EXEC)) return prot; /* * if that's an anonymous mapping, let it. */ if (!file) return prot | PROT_EXEC; /* * ditto if it's not on noexec mount, except that on !MMU we need * NOMMU_MAP_EXEC (== VM_MAYEXEC) in this case */ if (!path_noexec(&file->f_path)) { #ifndef CONFIG_MMU if (file->f_op->mmap_capabilities) { unsigned caps = file->f_op->mmap_capabilities(file); if (!(caps & NOMMU_MAP_EXEC)) return prot; } #endif return prot | PROT_EXEC; } /* anything on noexec mount won't get PROT_EXEC */ return prot; } int security_mmap_file(struct file *file, unsigned long prot, unsigned long flags) { unsigned long prot_adj = mmap_prot(file, prot); int ret; ret = call_int_hook(mmap_file, 0, file, prot, prot_adj, flags); if (ret) return ret; return ima_file_mmap(file, prot, prot_adj, flags); } int security_mmap_addr(unsigned long addr) { return call_int_hook(mmap_addr, 0, addr); } int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { int ret; ret = call_int_hook(file_mprotect, 0, vma, reqprot, prot); if (ret) return ret; return ima_file_mprotect(vma, prot); } int security_file_lock(struct file *file, unsigned int cmd) { return call_int_hook(file_lock, 0, file, cmd); } int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { return call_int_hook(file_fcntl, 0, file, cmd, arg); } void security_file_set_fowner(struct file *file) { call_void_hook(file_set_fowner, file); } int security_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int sig) { return call_int_hook(file_send_sigiotask, 0, tsk, fown, sig); } int security_file_receive(struct file *file) { return call_int_hook(file_receive, 0, file); } int security_file_open(struct file *file) { int ret; ret = call_int_hook(file_open, 0, file); if (ret) return ret; return fsnotify_perm(file, MAY_OPEN); } int security_task_alloc(struct task_struct *task, unsigned long clone_flags) { int rc = lsm_task_alloc(task); if (rc) return rc; rc = call_int_hook(task_alloc, 0, task, clone_flags); if (unlikely(rc)) security_task_free(task); return rc; } void security_task_free(struct task_struct *task) { call_void_hook(task_free, task); kfree(task->security); task->security = NULL; } int security_cred_alloc_blank(struct cred *cred, gfp_t gfp) { int rc = lsm_cred_alloc(cred, gfp); if (rc) return rc; rc = call_int_hook(cred_alloc_blank, 0, cred, gfp); if (unlikely(rc)) security_cred_free(cred); return rc; } void security_cred_free(struct cred *cred) { /* * There is a failure case in prepare_creds() that * may result in a call here with ->security being NULL. */ if (unlikely(cred->security == NULL)) return; call_void_hook(cred_free, cred); kfree(cred->security); cred->security = NULL; } int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp) { int rc = lsm_cred_alloc(new, gfp); if (rc) return rc; rc = call_int_hook(cred_prepare, 0, new, old, gfp); if (unlikely(rc)) security_cred_free(new); return rc; } void security_transfer_creds(struct cred *new, const struct cred *old) { call_void_hook(cred_transfer, new, old); } void security_cred_getsecid(const struct cred *c, u32 *secid) { *secid = 0; call_void_hook(cred_getsecid, c, secid); } EXPORT_SYMBOL(security_cred_getsecid); int security_kernel_act_as(struct cred *new, u32 secid) { return call_int_hook(kernel_act_as, 0, new, secid); } int security_kernel_create_files_as(struct cred *new, struct inode *inode) { return call_int_hook(kernel_create_files_as, 0, new, inode); } int security_kernel_module_request(char *kmod_name) { int ret; ret = call_int_hook(kernel_module_request, 0, kmod_name); if (ret) return ret; return integrity_kernel_module_request(kmod_name); } int security_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { int ret; ret = call_int_hook(kernel_read_file, 0, file, id, contents); if (ret) return ret; return ima_read_file(file, id, contents); } EXPORT_SYMBOL_GPL(security_kernel_read_file); int security_kernel_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id id) { int ret; ret = call_int_hook(kernel_post_read_file, 0, file, buf, size, id); if (ret) return ret; return ima_post_read_file(file, buf, size, id); } EXPORT_SYMBOL_GPL(security_kernel_post_read_file); int security_kernel_load_data(enum kernel_load_data_id id, bool contents) { int ret; ret = call_int_hook(kernel_load_data, 0, id, contents); if (ret) return ret; return ima_load_data(id, contents); } EXPORT_SYMBOL_GPL(security_kernel_load_data); int security_kernel_post_load_data(char *buf, loff_t size, enum kernel_load_data_id id, char *description) { int ret; ret = call_int_hook(kernel_post_load_data, 0, buf, size, id, description); if (ret) return ret; return ima_post_load_data(buf, size, id, description); } EXPORT_SYMBOL_GPL(security_kernel_post_load_data); int security_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { return call_int_hook(task_fix_setuid, 0, new, old, flags); } int security_task_fix_setgid(struct cred *new, const struct cred *old, int flags) { return call_int_hook(task_fix_setgid, 0, new, old, flags); } int security_task_setpgid(struct task_struct *p, pid_t pgid) { return call_int_hook(task_setpgid, 0, p, pgid); } int security_task_getpgid(struct task_struct *p) { return call_int_hook(task_getpgid, 0, p); } int security_task_getsid(struct task_struct *p) { return call_int_hook(task_getsid, 0, p); } void security_task_getsecid(struct task_struct *p, u32 *secid) { *secid = 0; call_void_hook(task_getsecid, p, secid); } EXPORT_SYMBOL(security_task_getsecid); int security_task_setnice(struct task_struct *p, int nice) { return call_int_hook(task_setnice, 0, p, nice); } int security_task_setioprio(struct task_struct *p, int ioprio) { return call_int_hook(task_setioprio, 0, p, ioprio); } int security_task_getioprio(struct task_struct *p) { return call_int_hook(task_getioprio, 0, p); } int security_task_prlimit(const struct cred *cred, const struct cred *tcred, unsigned int flags) { return call_int_hook(task_prlimit, 0, cred, tcred, flags); } int security_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) { return call_int_hook(task_setrlimit, 0, p, resource, new_rlim); } int security_task_setscheduler(struct task_struct *p) { return call_int_hook(task_setscheduler, 0, p); } int security_task_getscheduler(struct task_struct *p) { return call_int_hook(task_getscheduler, 0, p); } int security_task_movememory(struct task_struct *p) { return call_int_hook(task_movememory, 0, p); } int security_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { return call_int_hook(task_kill, 0, p, info, sig, cred); } int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { int thisrc; int rc = LSM_RET_DEFAULT(task_prctl); struct security_hook_list *hp; hlist_for_each_entry(hp, &security_hook_heads.task_prctl, list) { thisrc = hp->hook.task_prctl(option, arg2, arg3, arg4, arg5); if (thisrc != LSM_RET_DEFAULT(task_prctl)) { rc = thisrc; if (thisrc != 0) break; } } return rc; } void security_task_to_inode(struct task_struct *p, struct inode *inode) { call_void_hook(task_to_inode, p, inode); } int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { return call_int_hook(ipc_permission, 0, ipcp, flag); } void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) { *secid = 0; call_void_hook(ipc_getsecid, ipcp, secid); } int security_msg_msg_alloc(struct msg_msg *msg) { int rc = lsm_msg_msg_alloc(msg); if (unlikely(rc)) return rc; rc = call_int_hook(msg_msg_alloc_security, 0, msg); if (unlikely(rc)) security_msg_msg_free(msg); return rc; } void security_msg_msg_free(struct msg_msg *msg) { call_void_hook(msg_msg_free_security, msg); kfree(msg->security); msg->security = NULL; } int security_msg_queue_alloc(struct kern_ipc_perm *msq) { int rc = lsm_ipc_alloc(msq); if (unlikely(rc)) return rc; rc = call_int_hook(msg_queue_alloc_security, 0, msq); if (unlikely(rc)) security_msg_queue_free(msq); return rc; } void security_msg_queue_free(struct kern_ipc_perm *msq) { call_void_hook(msg_queue_free_security, msq); kfree(msq->security); msq->security = NULL; } int security_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) { return call_int_hook(msg_queue_associate, 0, msq, msqflg); } int security_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd) { return call_int_hook(msg_queue_msgctl, 0, msq, cmd); } int security_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg) { return call_int_hook(msg_queue_msgsnd, 0, msq, msg, msqflg); } int security_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { return call_int_hook(msg_queue_msgrcv, 0, msq, msg, target, type, mode); } int security_shm_alloc(struct kern_ipc_perm *shp) { int rc = lsm_ipc_alloc(shp); if (unlikely(rc)) return rc; rc = call_int_hook(shm_alloc_security, 0, shp); if (unlikely(rc)) security_shm_free(shp); return rc; } void security_shm_free(struct kern_ipc_perm *shp) { call_void_hook(shm_free_security, shp); kfree(shp->security); shp->security = NULL; } int security_shm_associate(struct kern_ipc_perm *shp, int shmflg) { return call_int_hook(shm_associate, 0, shp, shmflg); } int security_shm_shmctl(struct kern_ipc_perm *shp, int cmd) { return call_int_hook(shm_shmctl, 0, shp, cmd); } int security_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmflg) { return call_int_hook(shm_shmat, 0, shp, shmaddr, shmflg); } int security_sem_alloc(struct kern_ipc_perm *sma) { int rc = lsm_ipc_alloc(sma); if (unlikely(rc)) return rc; rc = call_int_hook(sem_alloc_security, 0, sma); if (unlikely(rc)) security_sem_free(sma); return rc; } void security_sem_free(struct kern_ipc_perm *sma) { call_void_hook(sem_free_security, sma); kfree(sma->security); sma->security = NULL; } int security_sem_associate(struct kern_ipc_perm *sma, int semflg) { return call_int_hook(sem_associate, 0, sma, semflg); } int security_sem_semctl(struct kern_ipc_perm *sma, int cmd) { return call_int_hook(sem_semctl, 0, sma, cmd); } int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter) { return call_int_hook(sem_semop, 0, sma, sops, nsops, alter); } void security_d_instantiate(struct dentry *dentry, struct inode *inode) { if (unlikely(inode && IS_PRIVATE(inode))) return; call_void_hook(d_instantiate, dentry, inode); } EXPORT_SYMBOL(security_d_instantiate); int security_getprocattr(struct task_struct *p, const char *lsm, char *name, char **value) { struct security_hook_list *hp; hlist_for_each_entry(hp, &security_hook_heads.getprocattr, list) { if (lsm != NULL && strcmp(lsm, hp->lsm)) continue; return hp->hook.getprocattr(p, name, value); } return LSM_RET_DEFAULT(getprocattr); } int security_setprocattr(const char *lsm, const char *name, void *value, size_t size) { struct security_hook_list *hp; hlist_for_each_entry(hp, &security_hook_heads.setprocattr, list) { if (lsm != NULL && strcmp(lsm, hp->lsm)) continue; return hp->hook.setprocattr(name, value, size); } return LSM_RET_DEFAULT(setprocattr); } int security_netlink_send(struct sock *sk, struct sk_buff *skb) { return call_int_hook(netlink_send, 0, sk, skb); } int security_ismaclabel(const char *name) { return call_int_hook(ismaclabel, 0, name); } EXPORT_SYMBOL(security_ismaclabel); int security_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) { struct security_hook_list *hp; int rc; /* * Currently, only one LSM can implement secid_to_secctx (i.e this * LSM hook is not "stackable"). */ hlist_for_each_entry(hp, &security_hook_heads.secid_to_secctx, list) { rc = hp->hook.secid_to_secctx(secid, secdata, seclen); if (rc != LSM_RET_DEFAULT(secid_to_secctx)) return rc; } return LSM_RET_DEFAULT(secid_to_secctx); } EXPORT_SYMBOL(security_secid_to_secctx); int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { *secid = 0; return call_int_hook(secctx_to_secid, 0, secdata, seclen, secid); } EXPORT_SYMBOL(security_secctx_to_secid); void security_release_secctx(char *secdata, u32 seclen) { call_void_hook(release_secctx, secdata, seclen); } EXPORT_SYMBOL(security_release_secctx); void security_inode_invalidate_secctx(struct inode *inode) { call_void_hook(inode_invalidate_secctx, inode); } EXPORT_SYMBOL(security_inode_invalidate_secctx); int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { return call_int_hook(inode_notifysecctx, 0, inode, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_notifysecctx); int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { return call_int_hook(inode_setsecctx, 0, dentry, ctx, ctxlen); } EXPORT_SYMBOL(security_inode_setsecctx); int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { struct security_hook_list *hp; int rc; /* * Only one module will provide a security context. */ hlist_for_each_entry(hp, &security_hook_heads.inode_getsecctx, list) { rc = hp->hook.inode_getsecctx(inode, ctx, ctxlen); if (rc != LSM_RET_DEFAULT(inode_getsecctx)) return rc; } return LSM_RET_DEFAULT(inode_getsecctx); } EXPORT_SYMBOL(security_inode_getsecctx); #ifdef CONFIG_WATCH_QUEUE int security_post_notification(const struct cred *w_cred, const struct cred *cred, struct watch_notification *n) { return call_int_hook(post_notification, 0, w_cred, cred, n); } #endif /* CONFIG_WATCH_QUEUE */ #ifdef CONFIG_KEY_NOTIFICATIONS int security_watch_key(struct key *key) { return call_int_hook(watch_key, 0, key); } #endif #ifdef CONFIG_SECURITY_NETWORK int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { return call_int_hook(unix_stream_connect, 0, sock, other, newsk); } EXPORT_SYMBOL(security_unix_stream_connect); int security_unix_may_send(struct socket *sock, struct socket *other) { return call_int_hook(unix_may_send, 0, sock, other); } EXPORT_SYMBOL(security_unix_may_send); int security_socket_create(int family, int type, int protocol, int kern) { return call_int_hook(socket_create, 0, family, type, protocol, kern); } int security_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { return call_int_hook(socket_post_create, 0, sock, family, type, protocol, kern); } int security_socket_socketpair(struct socket *socka, struct socket *sockb) { return call_int_hook(socket_socketpair, 0, socka, sockb); } EXPORT_SYMBOL(security_socket_socketpair); int security_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { return call_int_hook(socket_bind, 0, sock, address, addrlen); } int security_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { return call_int_hook(socket_connect, 0, sock, address, addrlen); } int security_socket_listen(struct socket *sock, int backlog) { return call_int_hook(socket_listen, 0, sock, backlog); } int security_socket_accept(struct socket *sock, struct socket *newsock) { return call_int_hook(socket_accept, 0, sock, newsock); } int security_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return call_int_hook(socket_sendmsg, 0, sock, msg, size); } int security_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return call_int_hook(socket_recvmsg, 0, sock, msg, size, flags); } int security_socket_getsockname(struct socket *sock) { return call_int_hook(socket_getsockname, 0, sock); } int security_socket_getpeername(struct socket *sock) { return call_int_hook(socket_getpeername, 0, sock); } int security_socket_getsockopt(struct socket *sock, int level, int optname) { return call_int_hook(socket_getsockopt, 0, sock, level, optname); } int security_socket_setsockopt(struct socket *sock, int level, int optname) { return call_int_hook(socket_setsockopt, 0, sock, level, optname); } int security_socket_shutdown(struct socket *sock, int how) { return call_int_hook(socket_shutdown, 0, sock, how); } int security_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { return call_int_hook(socket_sock_rcv_skb, 0, sk, skb); } EXPORT_SYMBOL(security_sock_rcv_skb); int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { struct security_hook_list *hp; int rc; /* * Only one module will provide a security context. */ hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_stream, list) { rc = hp->hook.socket_getpeersec_stream(sock, optval, optlen, len); if (rc != LSM_RET_DEFAULT(socket_getpeersec_stream)) return rc; } return LSM_RET_DEFAULT(socket_getpeersec_stream); } int security_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { struct security_hook_list *hp; int rc; /* * Only one module will provide a security context. */ hlist_for_each_entry(hp, &security_hook_heads.socket_getpeersec_dgram, list) { rc = hp->hook.socket_getpeersec_dgram(sock, skb, secid); if (rc != LSM_RET_DEFAULT(socket_getpeersec_dgram)) return rc; } return LSM_RET_DEFAULT(socket_getpeersec_dgram); } EXPORT_SYMBOL(security_socket_getpeersec_dgram); int security_sk_alloc(struct sock *sk, int family, gfp_t priority) { return call_int_hook(sk_alloc_security, 0, sk, family, priority); } void security_sk_free(struct sock *sk) { call_void_hook(sk_free_security, sk); } void security_sk_clone(const struct sock *sk, struct sock *newsk) { call_void_hook(sk_clone_security, sk, newsk); } EXPORT_SYMBOL(security_sk_clone); void security_sk_classify_flow(struct sock *sk, struct flowi_common *flic) { call_void_hook(sk_getsecid, sk, &flic->flowic_secid); } EXPORT_SYMBOL(security_sk_classify_flow); void security_req_classify_flow(const struct request_sock *req, struct flowi_common *flic) { call_void_hook(req_classify_flow, req, flic); } EXPORT_SYMBOL(security_req_classify_flow); void security_sock_graft(struct sock *sk, struct socket *parent) { call_void_hook(sock_graft, sk, parent); } EXPORT_SYMBOL(security_sock_graft); int security_inet_conn_request(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { return call_int_hook(inet_conn_request, 0, sk, skb, req); } EXPORT_SYMBOL(security_inet_conn_request); void security_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { call_void_hook(inet_csk_clone, newsk, req); } void security_inet_conn_established(struct sock *sk, struct sk_buff *skb) { call_void_hook(inet_conn_established, sk, skb); } EXPORT_SYMBOL(security_inet_conn_established); int security_secmark_relabel_packet(u32 secid) { return call_int_hook(secmark_relabel_packet, 0, secid); } EXPORT_SYMBOL(security_secmark_relabel_packet); void security_secmark_refcount_inc(void) { call_void_hook(secmark_refcount_inc); } EXPORT_SYMBOL(security_secmark_refcount_inc); void security_secmark_refcount_dec(void) { call_void_hook(secmark_refcount_dec); } EXPORT_SYMBOL(security_secmark_refcount_dec); int security_tun_dev_alloc_security(void **security) { return call_int_hook(tun_dev_alloc_security, 0, security); } EXPORT_SYMBOL(security_tun_dev_alloc_security); void security_tun_dev_free_security(void *security) { call_void_hook(tun_dev_free_security, security); } EXPORT_SYMBOL(security_tun_dev_free_security); int security_tun_dev_create(void) { return call_int_hook(tun_dev_create, 0); } EXPORT_SYMBOL(security_tun_dev_create); int security_tun_dev_attach_queue(void *security) { return call_int_hook(tun_dev_attach_queue, 0, security); } EXPORT_SYMBOL(security_tun_dev_attach_queue); int security_tun_dev_attach(struct sock *sk, void *security) { return call_int_hook(tun_dev_attach, 0, sk, security); } EXPORT_SYMBOL(security_tun_dev_attach); int security_tun_dev_open(void *security) { return call_int_hook(tun_dev_open, 0, security); } EXPORT_SYMBOL(security_tun_dev_open); int security_sctp_assoc_request(struct sctp_endpoint *ep, struct sk_buff *skb) { return call_int_hook(sctp_assoc_request, 0, ep, skb); } EXPORT_SYMBOL(security_sctp_assoc_request); int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen) { return call_int_hook(sctp_bind_connect, 0, sk, optname, address, addrlen); } EXPORT_SYMBOL(security_sctp_bind_connect); void security_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, struct sock *newsk) { call_void_hook(sctp_sk_clone, ep, sk, newsk); } EXPORT_SYMBOL(security_sctp_sk_clone); #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND int security_ib_pkey_access(void *sec, u64 subnet_prefix, u16 pkey) { return call_int_hook(ib_pkey_access, 0, sec, subnet_prefix, pkey); } EXPORT_SYMBOL(security_ib_pkey_access); int security_ib_endport_manage_subnet(void *sec, const char *dev_name, u8 port_num) { return call_int_hook(ib_endport_manage_subnet, 0, sec, dev_name, port_num); } EXPORT_SYMBOL(security_ib_endport_manage_subnet); int security_ib_alloc_security(void **sec) { return call_int_hook(ib_alloc_security, 0, sec); } EXPORT_SYMBOL(security_ib_alloc_security); void security_ib_free_security(void *sec) { call_void_hook(ib_free_security, sec); } EXPORT_SYMBOL(security_ib_free_security); #endif /* CONFIG_SECURITY_INFINIBAND */ #ifdef CONFIG_SECURITY_NETWORK_XFRM int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *sec_ctx, gfp_t gfp) { return call_int_hook(xfrm_policy_alloc_security, 0, ctxp, sec_ctx, gfp); } EXPORT_SYMBOL(security_xfrm_policy_alloc); int security_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx, struct xfrm_sec_ctx **new_ctxp) { return call_int_hook(xfrm_policy_clone_security, 0, old_ctx, new_ctxp); } void security_xfrm_policy_free(struct xfrm_sec_ctx *ctx) { call_void_hook(xfrm_policy_free_security, ctx); } EXPORT_SYMBOL(security_xfrm_policy_free); int security_xfrm_policy_delete(struct xfrm_sec_ctx *ctx) { return call_int_hook(xfrm_policy_delete_security, 0, ctx); } int security_xfrm_state_alloc(struct xfrm_state *x, struct xfrm_user_sec_ctx *sec_ctx) { return call_int_hook(xfrm_state_alloc, 0, x, sec_ctx); } EXPORT_SYMBOL(security_xfrm_state_alloc); int security_xfrm_state_alloc_acquire(struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid) { return call_int_hook(xfrm_state_alloc_acquire, 0, x, polsec, secid); } int security_xfrm_state_delete(struct xfrm_state *x) { return call_int_hook(xfrm_state_delete_security, 0, x); } EXPORT_SYMBOL(security_xfrm_state_delete); void security_xfrm_state_free(struct xfrm_state *x) { call_void_hook(xfrm_state_free_security, x); } int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir) { return call_int_hook(xfrm_policy_lookup, 0, ctx, fl_secid, dir); } int security_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) { struct security_hook_list *hp; int rc = LSM_RET_DEFAULT(xfrm_state_pol_flow_match); /* * Since this function is expected to return 0 or 1, the judgment * becomes difficult if multiple LSMs supply this call. Fortunately, * we can use the first LSM's judgment because currently only SELinux * supplies this call. * * For speed optimization, we explicitly break the loop rather than * using the macro */ hlist_for_each_entry(hp, &security_hook_heads.xfrm_state_pol_flow_match, list) { rc = hp->hook.xfrm_state_pol_flow_match(x, xp, flic); break; } return rc; } int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid) { return call_int_hook(xfrm_decode_session, 0, skb, secid, 1); } void security_skb_classify_flow(struct sk_buff *skb, struct flowi_common *flic) { int rc = call_int_hook(xfrm_decode_session, 0, skb, &flic->flowic_secid, 0); BUG_ON(rc); } EXPORT_SYMBOL(security_skb_classify_flow); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ #ifdef CONFIG_KEYS int security_key_alloc(struct key *key, const struct cred *cred, unsigned long flags) { return call_int_hook(key_alloc, 0, key, cred, flags); } void security_key_free(struct key *key) { call_void_hook(key_free, key); } int security_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { return call_int_hook(key_permission, 0, key_ref, cred, need_perm); } int security_key_getsecurity(struct key *key, char **_buffer) { *_buffer = NULL; return call_int_hook(key_getsecurity, 0, key, _buffer); } #endif /* CONFIG_KEYS */ #ifdef CONFIG_AUDIT int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, gfp_t gfp) { return call_int_hook(audit_rule_init, 0, field, op, rulestr, lsmrule, gfp); } int security_audit_rule_known(struct audit_krule *krule) { return call_int_hook(audit_rule_known, 0, krule); } void security_audit_rule_free(void *lsmrule) { call_void_hook(audit_rule_free, lsmrule); } int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule) { return call_int_hook(audit_rule_match, 0, secid, field, op, lsmrule); } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_BPF_SYSCALL int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) { return call_int_hook(bpf, 0, cmd, attr, size); } int security_bpf_map(struct bpf_map *map, fmode_t fmode) { return call_int_hook(bpf_map, 0, map, fmode); } int security_bpf_prog(struct bpf_prog *prog) { return call_int_hook(bpf_prog, 0, prog); } int security_bpf_map_alloc(struct bpf_map *map) { return call_int_hook(bpf_map_alloc_security, 0, map); } int security_bpf_prog_alloc(struct bpf_prog_aux *aux) { return call_int_hook(bpf_prog_alloc_security, 0, aux); } void security_bpf_map_free(struct bpf_map *map) { call_void_hook(bpf_map_free_security, map); } void security_bpf_prog_free(struct bpf_prog_aux *aux) { call_void_hook(bpf_prog_free_security, aux); } #endif /* CONFIG_BPF_SYSCALL */ int security_locked_down(enum lockdown_reason what) { return call_int_hook(locked_down, 0, what); } EXPORT_SYMBOL(security_locked_down); #ifdef CONFIG_PERF_EVENTS int security_perf_event_open(struct perf_event_attr *attr, int type) { return call_int_hook(perf_event_open, 0, attr, type); } int security_perf_event_alloc(struct perf_event *event) { return call_int_hook(perf_event_alloc, 0, event); } void security_perf_event_free(struct perf_event *event) { call_void_hook(perf_event_free, event); } int security_perf_event_read(struct perf_event *event) { return call_int_hook(perf_event_read, 0, event); } int security_perf_event_write(struct perf_event *event) { return call_int_hook(perf_event_write, 0, event); } #endif /* CONFIG_PERF_EVENTS */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 | // SPDX-License-Identifier: GPL-2.0+ /* * XArray implementation * Copyright (c) 2017-2018 Microsoft Corporation * Copyright (c) 2018-2020 Oracle * Author: Matthew Wilcox <willy@infradead.org> */ #include <linux/bitmap.h> #include <linux/export.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/xarray.h> /* * Coding conventions in this file: * * @xa is used to refer to the entire xarray. * @xas is the 'xarray operation state'. It may be either a pointer to * an xa_state, or an xa_state stored on the stack. This is an unfortunate * ambiguity. * @index is the index of the entry being operated on * @mark is an xa_mark_t; a small number indicating one of the mark bits. * @node refers to an xa_node; usually the primary one being operated on by * this function. * @offset is the index into the slots array inside an xa_node. * @parent refers to the @xa_node closer to the head than @node. * @entry refers to something stored in a slot in the xarray */ static inline unsigned int xa_lock_type(const struct xarray *xa) { return (__force unsigned int)xa->xa_flags & 3; } static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_lock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_lock_bh(xas); else xas_lock(xas); } static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_unlock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_unlock_bh(xas); else xas_unlock(xas); } static inline bool xa_track_free(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_TRACK_FREE; } static inline bool xa_zero_busy(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_ZERO_BUSY; } static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark) { if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) xa->xa_flags |= XA_FLAGS_MARK(mark); } static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark) { if (xa->xa_flags & XA_FLAGS_MARK(mark)) xa->xa_flags &= ~(XA_FLAGS_MARK(mark)); } static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark) { return node->marks[(__force unsigned)mark]; } static inline bool node_get_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return test_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_set_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_set_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_clear_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_clear_bit(offset, node_marks(node, mark)); } static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark) { return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE); } static inline void node_mark_all(struct xa_node *node, xa_mark_t mark) { bitmap_fill(node_marks(node, mark), XA_CHUNK_SIZE); } #define mark_inc(mark) do { \ mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \ } while (0) /* * xas_squash_marks() - Merge all marks to the first entry * @xas: Array operation state. * * Set a mark on the first entry if any entry has it set. Clear marks on * all sibling entries. */ static void xas_squash_marks(const struct xa_state *xas) { unsigned int mark = 0; unsigned int limit = xas->xa_offset + xas->xa_sibs + 1; if (!xas->xa_sibs) return; do { unsigned long *marks = xas->xa_node->marks[mark]; if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit) continue; __set_bit(xas->xa_offset, marks); bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); } while (mark++ != (__force unsigned)XA_MARK_MAX); } /* extracts the offset within this node from the index */ static unsigned int get_offset(unsigned long index, struct xa_node *node) { return (index >> node->shift) & XA_CHUNK_MASK; } static void xas_set_offset(struct xa_state *xas) { xas->xa_offset = get_offset(xas->xa_index, xas->xa_node); } /* move the index either forwards (find) or backwards (sibling slot) */ static void xas_move_index(struct xa_state *xas, unsigned long offset) { unsigned int shift = xas->xa_node->shift; xas->xa_index &= ~XA_CHUNK_MASK << shift; xas->xa_index += offset << shift; } static void xas_advance(struct xa_state *xas) { xas->xa_offset++; xas_move_index(xas, xas->xa_offset); } static void *set_bounds(struct xa_state *xas) { xas->xa_node = XAS_BOUNDS; return NULL; } /* * Starts a walk. If the @xas is already valid, we assume that it's on * the right path and just return where we've got to. If we're in an * error state, return NULL. If the index is outside the current scope * of the xarray, return NULL without changing @xas->xa_node. Otherwise * set @xas->xa_node to NULL and return the current head of the array. */ static void *xas_start(struct xa_state *xas) { void *entry; if (xas_valid(xas)) return xas_reload(xas); if (xas_error(xas)) return NULL; entry = xa_head(xas->xa); if (!xa_is_node(entry)) { if (xas->xa_index) return set_bounds(xas); } else { if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK) return set_bounds(xas); } xas->xa_node = NULL; return entry; } static void *xas_descend(struct xa_state *xas, struct xa_node *node) { unsigned int offset = get_offset(xas->xa_index, node); void *entry = xa_entry(xas->xa, node, offset); xas->xa_node = node; if (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); } xas->xa_offset = offset; return entry; } /** * xas_load() - Load an entry from the XArray (advanced). * @xas: XArray operation state. * * Usually walks the @xas to the appropriate state to load the entry * stored at xa_index. However, it will do nothing and return %NULL if * @xas is in an error state. xas_load() will never expand the tree. * * If the xa_state is set up to operate on a multi-index entry, xas_load() * may return %NULL or an internal entry, even if there are entries * present within the range specified by @xas. * * Context: Any context. The caller should hold the xa_lock or the RCU lock. * Return: Usually an entry in the XArray, but see description for exceptions. */ void *xas_load(struct xa_state *xas) { void *entry = xas_start(xas); while (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); if (xas->xa_shift > node->shift) break; entry = xas_descend(xas, node); if (node->shift == 0) break; } return entry; } EXPORT_SYMBOL_GPL(xas_load); /* Move the radix tree node cache here */ extern struct kmem_cache *radix_tree_node_cachep; extern void radix_tree_node_rcu_free(struct rcu_head *head); #define XA_RCU_FREE ((struct xarray *)1) static void xa_node_free(struct xa_node *node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->array = XA_RCU_FREE; call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * xas_destroy() - Free any resources allocated during the XArray operation. * @xas: XArray operation state. * * This function is now internal-only. */ static void xas_destroy(struct xa_state *xas) { struct xa_node *next, *node = xas->xa_alloc; while (node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); next = rcu_dereference_raw(node->parent); radix_tree_node_rcu_free(&node->rcu_head); xas->xa_alloc = node = next; } } /** * xas_nomem() - Allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * If we need to add new nodes to the XArray, we try to allocate memory * with GFP_NOWAIT while holding the lock, which will usually succeed. * If it fails, @xas is flagged as needing memory to continue. The caller * should drop the lock and call xas_nomem(). If xas_nomem() succeeds, * the caller should retry the operation. * * Forward progress is guaranteed as one node is allocated here and * stored in the xa_state where it will be found by xas_alloc(). More * nodes will likely be found in the slab allocator, but we do not tie * them up here. * * Return: true if memory was needed, and was successfully allocated. */ bool xas_nomem(struct xa_state *xas, gfp_t gfp) { if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } EXPORT_SYMBOL_GPL(xas_nomem); /* * __xas_nomem() - Drop locks and allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * Internal variant of xas_nomem(). * * Return: true if memory was needed, and was successfully allocated. */ static bool __xas_nomem(struct xa_state *xas, gfp_t gfp) __must_hold(xas->xa->xa_lock) { unsigned int lock_type = xa_lock_type(xas->xa); if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; if (gfpflags_allow_blocking(gfp)) { xas_unlock_type(xas, lock_type); xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); xas_lock_type(xas, lock_type); } else { xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); } if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } static void xas_update(struct xa_state *xas, struct xa_node *node) { if (xas->xa_update) xas->xa_update(node); else XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); } static void *xas_alloc(struct xa_state *xas, unsigned int shift) { struct xa_node *parent = xas->xa_node; struct xa_node *node = xas->xa_alloc; if (xas_invalid(xas)) return NULL; if (node) { xas->xa_alloc = NULL; } else { gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN; if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; node = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!node) { xas_set_err(xas, -ENOMEM); return NULL; } } if (parent) { node->offset = xas->xa_offset; parent->count++; XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE); xas_update(xas, parent); } XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->shift = shift; node->count = 0; node->nr_values = 0; RCU_INIT_POINTER(node->parent, xas->xa_node); node->array = xas->xa; return node; } #ifdef CONFIG_XARRAY_MULTI /* Returns the number of indices covered by a given xa_state */ static unsigned long xas_size(const struct xa_state *xas) { return (xas->xa_sibs + 1UL) << xas->xa_shift; } #endif /* * Use this to calculate the maximum index that will need to be created * in order to add the entry described by @xas. Because we cannot store a * multi-index entry at index 0, the calculation is a little more complex * than you might expect. */ static unsigned long xas_max(struct xa_state *xas) { unsigned long max = xas->xa_index; #ifdef CONFIG_XARRAY_MULTI if (xas->xa_shift || xas->xa_sibs) { unsigned long mask = xas_size(xas) - 1; max |= mask; if (mask == max) max++; } #endif return max; } /* The maximum index that can be contained in the array without expanding it */ static unsigned long max_index(void *entry) { if (!xa_is_node(entry)) return 0; return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1; } static void xas_shrink(struct xa_state *xas) { struct xarray *xa = xas->xa; struct xa_node *node = xas->xa_node; for (;;) { void *entry; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count != 1) break; entry = xa_entry_locked(xa, node, 0); if (!entry) break; if (!xa_is_node(entry) && node->shift) break; if (xa_is_zero(entry) && xa_zero_busy(xa)) entry = NULL; xas->xa_node = XAS_BOUNDS; RCU_INIT_POINTER(xa->xa_head, entry); if (xa_track_free(xa) && !node_get_mark(node, 0, XA_FREE_MARK)) xa_mark_clear(xa, XA_FREE_MARK); node->count = 0; node->nr_values = 0; if (!xa_is_node(entry)) RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY); xas_update(xas, node); xa_node_free(node); if (!xa_is_node(entry)) break; node = xa_to_node(entry); node->parent = NULL; } } /* * xas_delete_node() - Attempt to delete an xa_node * @xas: Array operation state. * * Attempts to delete the @xas->xa_node. This will fail if xa->node has * a non-zero reference count. */ static void xas_delete_node(struct xa_state *xas) { struct xa_node *node = xas->xa_node; for (;;) { struct xa_node *parent; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count) break; parent = xa_parent_locked(xas->xa, node); xas->xa_node = parent; xas->xa_offset = node->offset; xa_node_free(node); if (!parent) { xas->xa->xa_head = NULL; xas->xa_node = XAS_BOUNDS; return; } parent->slots[xas->xa_offset] = NULL; parent->count--; XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE); node = parent; xas_update(xas, node); } if (!node->parent) xas_shrink(xas); } /** * xas_free_nodes() - Free this node and all nodes that it references * @xas: Array operation state. * @top: Node to free * * This node has been removed from the tree. We must now free it and all * of its subnodes. There may be RCU walkers with references into the tree, * so we must replace all entries with retry markers. */ static void xas_free_nodes(struct xa_state *xas, struct xa_node *top) { unsigned int offset = 0; struct xa_node *node = top; for (;;) { void *entry = xa_entry_locked(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) { node = xa_to_node(entry); offset = 0; continue; } if (entry) RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY); offset++; while (offset == XA_CHUNK_SIZE) { struct xa_node *parent; parent = xa_parent_locked(xas->xa, node); offset = node->offset + 1; node->count = 0; node->nr_values = 0; xas_update(xas, node); xa_node_free(node); if (node == top) return; node = parent; } } } /* * xas_expand adds nodes to the head of the tree until it has reached * sufficient height to be able to contain @xas->xa_index */ static int xas_expand(struct xa_state *xas, void *head) { struct xarray *xa = xas->xa; struct xa_node *node = NULL; unsigned int shift = 0; unsigned long max = xas_max(xas); if (!head) { if (max == 0) return 0; while ((max >> shift) >= XA_CHUNK_SIZE) shift += XA_CHUNK_SHIFT; return shift + XA_CHUNK_SHIFT; } else if (xa_is_node(head)) { node = xa_to_node(head); shift = node->shift + XA_CHUNK_SHIFT; } xas->xa_node = NULL; while (max > max_index(head)) { xa_mark_t mark = 0; XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); node = xas_alloc(xas, shift); if (!node) return -ENOMEM; node->count = 1; if (xa_is_value(head)) node->nr_values = 1; RCU_INIT_POINTER(node->slots[0], head); /* Propagate the aggregated mark info to the new child */ for (;;) { if (xa_track_free(xa) && mark == XA_FREE_MARK) { node_mark_all(node, XA_FREE_MARK); if (!xa_marked(xa, XA_FREE_MARK)) { node_clear_mark(node, 0, XA_FREE_MARK); xa_mark_set(xa, XA_FREE_MARK); } } else if (xa_marked(xa, mark)) { node_set_mark(node, 0, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } /* * Now that the new node is fully initialised, we can add * it to the tree */ if (xa_is_node(head)) { xa_to_node(head)->offset = 0; rcu_assign_pointer(xa_to_node(head)->parent, node); } head = xa_mk_node(node); rcu_assign_pointer(xa->xa_head, head); xas_update(xas, node); shift += XA_CHUNK_SHIFT; } xas->xa_node = node; return shift; } /* * xas_create() - Create a slot to store an entry in. * @xas: XArray operation state. * @allow_root: %true if we can store the entry in the root directly * * Most users will not need to call this function directly, as it is called * by xas_store(). It is useful for doing conditional store operations * (see the xa_cmpxchg() implementation for an example). * * Return: If the slot already existed, returns the contents of this slot. * If the slot was newly created, returns %NULL. If it failed to create the * slot, returns %NULL and indicates the error in @xas. */ static void *xas_create(struct xa_state *xas, bool allow_root) { struct xarray *xa = xas->xa; void *entry; void __rcu **slot; struct xa_node *node = xas->xa_node; int shift; unsigned int order = xas->xa_shift; if (xas_top(node)) { entry = xa_head_locked(xa); xas->xa_node = NULL; if (!entry && xa_zero_busy(xa)) entry = XA_ZERO_ENTRY; shift = xas_expand(xas, entry); if (shift < 0) return NULL; if (!shift && !allow_root) shift = XA_CHUNK_SHIFT; entry = xa_head_locked(xa); slot = &xa->xa_head; } else if (xas_error(xas)) { return NULL; } else if (node) { unsigned int offset = xas->xa_offset; shift = node->shift; entry = xa_entry_locked(xa, node, offset); slot = &node->slots[offset]; } else { shift = 0; entry = xa_head_locked(xa); slot = &xa->xa_head; } while (shift > order) { shift -= XA_CHUNK_SHIFT; if (!entry) { node = xas_alloc(xas, shift); if (!node) break; if (xa_track_free(xa)) node_mark_all(node, XA_FREE_MARK); rcu_assign_pointer(*slot, xa_mk_node(node)); } else if (xa_is_node(entry)) { node = xa_to_node(entry); } else { break; } entry = xas_descend(xas, node); slot = &node->slots[xas->xa_offset]; } return entry; } /** * xas_create_range() - Ensure that stores to this range will succeed * @xas: XArray operation state. * * Creates all of the slots in the range covered by @xas. Sets @xas to * create single-index entries and positions it at the beginning of the * range. This is for the benefit of users which have not yet been * converted to use multi-index entries. */ void xas_create_range(struct xa_state *xas) { unsigned long index = xas->xa_index; unsigned char shift = xas->xa_shift; unsigned char sibs = xas->xa_sibs; xas->xa_index |= ((sibs + 1UL) << shift) - 1; if (xas_is_node(xas) && xas->xa_node->shift == xas->xa_shift) xas->xa_offset |= sibs; xas->xa_shift = 0; xas->xa_sibs = 0; for (;;) { xas_create(xas, true); if (xas_error(xas)) goto restore; if (xas->xa_index <= (index | XA_CHUNK_MASK)) goto success; xas->xa_index -= XA_CHUNK_SIZE; for (;;) { struct xa_node *node = xas->xa_node; if (node->shift >= shift) break; xas->xa_node = xa_parent_locked(xas->xa, node); xas->xa_offset = node->offset - 1; if (node->offset != 0) break; } } restore: xas->xa_shift = shift; xas->xa_sibs = sibs; xas->xa_index = index; return; success: xas->xa_index = index; if (xas->xa_node) xas_set_offset(xas); } EXPORT_SYMBOL_GPL(xas_create_range); static void update_node(struct xa_state *xas, struct xa_node *node, int count, int values) { if (!node || (!count && !values)) return; node->count += count; node->nr_values += values; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE); xas_update(xas, node); if (count < 0) xas_delete_node(xas); } /** * xas_store() - Store this entry in the XArray. * @xas: XArray operation state. * @entry: New entry. * * If @xas is operating on a multi-index entry, the entry returned by this * function is essentially meaningless (it may be an internal entry or it * may be %NULL, even if there are non-NULL entries at some of the indices * covered by the range). This is not a problem for any current users, * and can be changed if needed. * * Return: The old entry at this index. */ void *xas_store(struct xa_state *xas, void *entry) { struct xa_node *node; void __rcu **slot = &xas->xa->xa_head; unsigned int offset, max; int count = 0; int values = 0; void *first, *next; bool value = xa_is_value(entry); if (entry) { bool allow_root = !xa_is_node(entry) && !xa_is_zero(entry); first = xas_create(xas, allow_root); } else { first = xas_load(xas); } if (xas_invalid(xas)) return first; node = xas->xa_node; if (node && (xas->xa_shift < node->shift)) xas->xa_sibs = 0; if ((first == entry) && !xas->xa_sibs) return first; next = first; offset = xas->xa_offset; max = xas->xa_offset + xas->xa_sibs; if (node) { slot = &node->slots[offset]; if (xas->xa_sibs) xas_squash_marks(xas); } if (!entry) xas_init_marks(xas); for (;;) { /* * Must clear the marks before setting the entry to NULL, * otherwise xas_for_each_marked may find a NULL entry and * stop early. rcu_assign_pointer contains a release barrier * so the mark clearing will appear to happen before the * entry is set to NULL. */ rcu_assign_pointer(*slot, entry); if (xa_is_node(next) && (!node || node->shift)) xas_free_nodes(xas, xa_to_node(next)); if (!node) break; count += !next - !entry; values += !xa_is_value(first) - !value; if (entry) { if (offset == max) break; if (!xa_is_sibling(entry)) entry = xa_mk_sibling(xas->xa_offset); } else { if (offset == XA_CHUNK_MASK) break; } next = xa_entry_locked(xas->xa, node, ++offset); if (!xa_is_sibling(next)) { if (!entry && (offset > max)) break; first = next; } slot++; } update_node(xas, node, count, values); return first; } EXPORT_SYMBOL_GPL(xas_store); /** * xas_get_mark() - Returns the state of this mark. * @xas: XArray operation state. * @mark: Mark number. * * Return: true if the mark is set, false if the mark is clear or @xas * is in an error state. */ bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark) { if (xas_invalid(xas)) return false; if (!xas->xa_node) return xa_marked(xas->xa, mark); return node_get_mark(xas->xa_node, xas->xa_offset, mark); } EXPORT_SYMBOL_GPL(xas_get_mark); /** * xas_set_mark() - Sets the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Sets the specified mark on this entry, and walks up the tree setting it * on all the ancestor entries. Does nothing if @xas has not been walked to * an entry, or is in an error state. */ void xas_set_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (node_set_mark(node, offset, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (!xa_marked(xas->xa, mark)) xa_mark_set(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_set_mark); /** * xas_clear_mark() - Clears the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Clears the specified mark on this entry, and walks back to the head * attempting to clear it on all the ancestor entries. Does nothing if * @xas has not been walked to an entry, or is in an error state. */ void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (!node_clear_mark(node, offset, mark)) return; if (node_any_mark(node, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (xa_marked(xas->xa, mark)) xa_mark_clear(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_clear_mark); /** * xas_init_marks() - Initialise all marks for the entry * @xas: Array operations state. * * Initialise all marks for the entry specified by @xas. If we're tracking * free entries with a mark, we need to set it on all entries. All other * marks are cleared. * * This implementation is not as efficient as it could be; we may walk * up the tree multiple times. */ void xas_init_marks(const struct xa_state *xas) { xa_mark_t mark = 0; for (;;) { if (xa_track_free(xas->xa) && mark == XA_FREE_MARK) xas_set_mark(xas, mark); else xas_clear_mark(xas, mark); if (mark == XA_MARK_MAX) break; mark_inc(mark); } } EXPORT_SYMBOL_GPL(xas_init_marks); #ifdef CONFIG_XARRAY_MULTI static unsigned int node_get_marks(struct xa_node *node, unsigned int offset) { unsigned int marks = 0; xa_mark_t mark = XA_MARK_0; for (;;) { if (node_get_mark(node, offset, mark)) marks |= 1 << (__force unsigned int)mark; if (mark == XA_MARK_MAX) break; mark_inc(mark); } return marks; } static void node_set_marks(struct xa_node *node, unsigned int offset, struct xa_node *child, unsigned int marks) { xa_mark_t mark = XA_MARK_0; for (;;) { if (marks & (1 << (__force unsigned int)mark)) { node_set_mark(node, offset, mark); if (child) node_mark_all(child, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } } /** * xas_split_alloc() - Allocate memory for splitting an entry. * @xas: XArray operation state. * @entry: New entry which will be stored in the array. * @order: New entry order. * @gfp: Memory allocation flags. * * This function should be called before calling xas_split(). * If necessary, it will allocate new nodes (and fill them with @entry) * to prepare for the upcoming split of an entry of @order size into * entries of the order stored in the @xas. * * Context: May sleep if @gfp flags permit. */ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int mask = xas->xa_sibs; /* XXX: no support for splitting really large entries yet */ if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order)) goto nomem; if (xas->xa_shift + XA_CHUNK_SHIFT > order) return; do { unsigned int i; void *sibling = NULL; struct xa_node *node; node = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!node) goto nomem; node->array = xas->xa; for (i = 0; i < XA_CHUNK_SIZE; i++) { if ((i & mask) == 0) { RCU_INIT_POINTER(node->slots[i], entry); sibling = xa_mk_sibling(i); } else { RCU_INIT_POINTER(node->slots[i], sibling); } } RCU_INIT_POINTER(node->parent, xas->xa_alloc); xas->xa_alloc = node; } while (sibs-- > 0); return; nomem: xas_destroy(xas); xas_set_err(xas, -ENOMEM); } EXPORT_SYMBOL_GPL(xas_split_alloc); /** * xas_split() - Split a multi-index entry into smaller entries. * @xas: XArray operation state. * @entry: New entry to store in the array. * @order: New entry order. * * The value in the entry is copied to all the replacement entries. * * Context: Any context. The caller should hold the xa_lock. */ void xas_split(struct xa_state *xas, void *entry, unsigned int order) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int offset, marks; struct xa_node *node; void *curr = xas_load(xas); int values = 0; node = xas->xa_node; if (xas_top(node)) return; marks = node_get_marks(node, xas->xa_offset); offset = xas->xa_offset + sibs; do { if (xas->xa_shift < node->shift) { struct xa_node *child = xas->xa_alloc; xas->xa_alloc = rcu_dereference_raw(child->parent); child->shift = node->shift - XA_CHUNK_SHIFT; child->offset = offset; child->count = XA_CHUNK_SIZE; child->nr_values = xa_is_value(entry) ? XA_CHUNK_SIZE : 0; RCU_INIT_POINTER(child->parent, node); node_set_marks(node, offset, child, marks); rcu_assign_pointer(node->slots[offset], xa_mk_node(child)); if (xa_is_value(curr)) values--; xas_update(xas, child); } else { unsigned int canon = offset - xas->xa_sibs; node_set_marks(node, canon, NULL, marks); rcu_assign_pointer(node->slots[canon], entry); while (offset > canon) rcu_assign_pointer(node->slots[offset--], xa_mk_sibling(canon)); values += (xa_is_value(entry) - xa_is_value(curr)) * (xas->xa_sibs + 1); } } while (offset-- > xas->xa_offset); node->nr_values += values; xas_update(xas, node); } EXPORT_SYMBOL_GPL(xas_split); #endif /** * xas_pause() - Pause a walk to drop a lock. * @xas: XArray operation state. * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @xas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call xas_pause(), the xa_for_each() * iterator may be more appropriate. * * Note that xas_pause() only works for forward iteration. If a user needs * to pause a reverse iteration, we will need a xas_pause_rev(). */ void xas_pause(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (xas_invalid(xas)) return; xas->xa_node = XAS_RESTART; if (node) { unsigned long offset = xas->xa_offset; while (++offset < XA_CHUNK_SIZE) { if (!xa_is_sibling(xa_entry(xas->xa, node, offset))) break; } xas->xa_index += (offset - xas->xa_offset) << node->shift; if (xas->xa_index == 0) xas->xa_node = XAS_BOUNDS; } else { xas->xa_index++; } } EXPORT_SYMBOL_GPL(xas_pause); /* * __xas_prev() - Find the previous entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_prev() which handles all the complex cases * out of line. */ void *__xas_prev(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index--; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset--; while (xas->xa_offset == 255) { xas->xa_offset = xas->xa_node->offset - 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_prev); /* * __xas_next() - Find the next entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_next() which handles all the complex cases * out of line. */ void *__xas_next(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index++; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset++; while (xas->xa_offset == XA_CHUNK_SIZE) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_next); /** * xas_find() - Find the next present entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * * If the @xas has not yet been walked to an entry, return the entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we move to the * next entry. * * If no entry is found and the array is smaller than @max, the iterator * is set to the smallest index not yet in the array. This allows @xas * to be immediately passed to xas_store(). * * Return: The entry, if found, otherwise %NULL. */ void *xas_find(struct xa_state *xas, unsigned long max) { void *entry; if (xas_error(xas) || xas->xa_node == XAS_BOUNDS) return NULL; if (xas->xa_index > max) return set_bounds(xas); if (!xas->xa_node) { xas->xa_index = 1; return set_bounds(xas); } else if (xas->xa_node == XAS_RESTART) { entry = xas_load(xas); if (entry || xas_not_node(xas->xa_node)) return entry; } else if (!xas->xa_node->shift && xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)) { xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1; } xas_advance(xas); while (xas->xa_node && (xas->xa_index <= max)) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_node(entry)) { xas->xa_node = xa_to_node(entry); xas->xa_offset = 0; continue; } if (entry && !xa_is_sibling(entry)) return entry; xas_advance(xas); } if (!xas->xa_node) xas->xa_node = XAS_BOUNDS; return NULL; } EXPORT_SYMBOL_GPL(xas_find); /** * xas_find_marked() - Find the next marked entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark number to search for. * * If the @xas has not yet been walked to an entry, return the marked entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we return the * first marked entry with an index > xas.xa_index. * * If no marked entry is found and the array is smaller than @max, @xas is * set to the bounds state and xas->xa_index is set to the smallest index * not yet in the array. This allows @xas to be immediately passed to * xas_store(). * * If no entry is found before @max is reached, @xas is set to the restart * state. * * Return: The entry, if found, otherwise %NULL. */ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { bool advance = true; unsigned int offset; void *entry; if (xas_error(xas)) return NULL; if (xas->xa_index > max) goto max; if (!xas->xa_node) { xas->xa_index = 1; goto out; } else if (xas_top(xas->xa_node)) { advance = false; entry = xa_head(xas->xa); xas->xa_node = NULL; if (xas->xa_index > max_index(entry)) goto out; if (!xa_is_node(entry)) { if (xa_marked(xas->xa, mark)) return entry; xas->xa_index = 1; goto out; } xas->xa_node = xa_to_node(entry); xas->xa_offset = xas->xa_index >> xas->xa_node->shift; } while (xas->xa_index <= max) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) break; advance = false; continue; } if (!advance) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_sibling(entry)) { xas->xa_offset = xa_to_sibling(entry); xas_move_index(xas, xas->xa_offset); } } offset = xas_find_chunk(xas, advance, mark); if (offset > xas->xa_offset) { advance = false; xas_move_index(xas, offset); /* Mind the wrap */ if ((xas->xa_index - 1) >= max) goto max; xas->xa_offset = offset; if (offset == XA_CHUNK_SIZE) continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK)) continue; if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } out: if (xas->xa_index > max) goto max; return set_bounds(xas); max: xas->xa_node = XAS_RESTART; return NULL; } EXPORT_SYMBOL_GPL(xas_find_marked); /** * xas_find_conflict() - Find the next present entry in a range. * @xas: XArray operation state. * * The @xas describes both a range and a position within that range. * * Context: Any context. Expects xa_lock to be held. * Return: The next entry in the range covered by @xas or %NULL. */ void *xas_find_conflict(struct xa_state *xas) { void *curr; if (xas_error(xas)) return NULL; if (!xas->xa_node) return NULL; if (xas_top(xas->xa_node)) { curr = xas_start(xas); if (!curr) return NULL; while (xa_is_node(curr)) { struct xa_node *node = xa_to_node(curr); curr = xas_descend(xas, node); } if (curr) return curr; } if (xas->xa_node->shift > xas->xa_shift) return NULL; for (;;) { if (xas->xa_node->shift == xas->xa_shift) { if ((xas->xa_offset & xas->xa_sibs) == xas->xa_sibs) break; } else if (xas->xa_offset == XA_CHUNK_MASK) { xas->xa_offset = xas->xa_node->offset; xas->xa_node = xa_parent_locked(xas->xa, xas->xa_node); if (!xas->xa_node) break; continue; } curr = xa_entry_locked(xas->xa, xas->xa_node, ++xas->xa_offset); if (xa_is_sibling(curr)) continue; while (xa_is_node(curr)) { xas->xa_node = xa_to_node(curr); xas->xa_offset = 0; curr = xa_entry_locked(xas->xa, xas->xa_node, 0); } if (curr) return curr; } xas->xa_offset -= xas->xa_sibs; return NULL; } EXPORT_SYMBOL_GPL(xas_find_conflict); /** * xa_load() - Load an entry from an XArray. * @xa: XArray. * @index: index into array. * * Context: Any context. Takes and releases the RCU lock. * Return: The entry at @index in @xa. */ void *xa_load(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); do { entry = xas_load(&xas); if (xa_is_zero(entry)) entry = NULL; } while (xas_retry(&xas, entry)); rcu_read_unlock(); return entry; } EXPORT_SYMBOL(xa_load); static void *xas_result(struct xa_state *xas, void *curr) { if (xa_is_zero(curr)) return NULL; if (xas_error(xas)) curr = xas->xa_node; return curr; } /** * __xa_erase() - Erase this entry from the XArray while locked. * @xa: XArray. * @index: Index into array. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Expects xa_lock to be held on entry. * Return: The entry which used to be at this index. */ void *__xa_erase(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); return xas_result(&xas, xas_store(&xas, NULL)); } EXPORT_SYMBOL(__xa_erase); /** * xa_erase() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock. * Return: The entry which used to be at this index. */ void *xa_erase(struct xarray *xa, unsigned long index) { void *entry; xa_lock(xa); entry = __xa_erase(xa, index); xa_unlock(xa); return entry; } EXPORT_SYMBOL(xa_erase); /** * __xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); if (xa_track_free(xa) && !entry) entry = XA_ZERO_ENTRY; do { curr = xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_store); /** * xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from this index will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: The old entry at this index on success, xa_err(-EINVAL) if @entry * cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation * failed. */ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; xa_lock(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock(xa); return curr; } EXPORT_SYMBOL(xa_store); /** * __xa_cmpxchg() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); do { curr = xas_load(&xas); if (curr == old) { xas_store(&xas, entry); if (xa_track_free(xa) && entry && !curr) xas_clear_mark(&xas, XA_FREE_MARK); } } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_cmpxchg); /** * __xa_insert() - Store this entry in the XArray if no entry is present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { curr = xas_load(&xas); if (!curr) { xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } else { xas_set_err(&xas, -EBUSY); } } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_insert); #ifdef CONFIG_XARRAY_MULTI static void xas_set_range(struct xa_state *xas, unsigned long first, unsigned long last) { unsigned int shift = 0; unsigned long sibs = last - first; unsigned int offset = XA_CHUNK_MASK; xas_set(xas, first); while ((first & XA_CHUNK_MASK) == 0) { if (sibs < XA_CHUNK_MASK) break; if ((sibs == XA_CHUNK_MASK) && (offset < XA_CHUNK_MASK)) break; shift += XA_CHUNK_SHIFT; if (offset == XA_CHUNK_MASK) offset = sibs & XA_CHUNK_MASK; sibs >>= XA_CHUNK_SHIFT; first >>= XA_CHUNK_SHIFT; } offset = first & XA_CHUNK_MASK; if (offset + sibs > XA_CHUNK_MASK) sibs = XA_CHUNK_MASK - offset; if ((((first + sibs + 1) << shift) - 1) > last) sibs -= 1; xas->xa_shift = shift; xas->xa_sibs = sibs; } /** * xa_store_range() - Store this entry at a range of indices in the XArray. * @xa: XArray. * @first: First index to affect. * @last: Last index to affect. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from any index between @first and @last, * inclusive will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Process context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: %NULL on success, xa_err(-EINVAL) if @entry cannot be stored in * an XArray, or xa_err(-ENOMEM) if memory allocation failed. */ void *xa_store_range(struct xarray *xa, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_internal(entry))) return XA_ERROR(-EINVAL); if (last < first) return XA_ERROR(-EINVAL); do { xas_lock(&xas); if (entry) { unsigned int order = BITS_PER_LONG; if (last + 1) order = __ffs(last + 1); xas_set_order(&xas, last, order); xas_create(&xas, true); if (xas_error(&xas)) goto unlock; } do { xas_set_range(&xas, first, last); xas_store(&xas, entry); if (xas_error(&xas)) goto unlock; first += xas_size(&xas); } while (first <= last); unlock: xas_unlock(&xas); } while (xas_nomem(&xas, gfp)); return xas_result(&xas, NULL); } EXPORT_SYMBOL(xa_store_range); /** * xa_get_order() - Get the order of an entry. * @xa: XArray. * @index: Index of the entry. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xa_get_order(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); void *entry; int order = 0; rcu_read_lock(); entry = xas_load(&xas); if (!entry) goto unlock; if (!xas.xa_node) goto unlock; for (;;) { unsigned int slot = xas.xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; if (!xa_is_sibling(xas.xa_node->slots[slot])) break; order++; } order += xas.xa_node->shift; unlock: rcu_read_unlock(); return order; } EXPORT_SYMBOL(xa_get_order); #endif /* CONFIG_XARRAY_MULTI */ /** * __xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @limit: Range for allocated ID. * @entry: New entry. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ int __xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (WARN_ON_ONCE(!xa_track_free(xa))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { xas.xa_index = limit.min; xas_find_marked(&xas, limit.max, XA_FREE_MARK); if (xas.xa_node == XAS_RESTART) xas_set_err(&xas, -EBUSY); else *id = xas.xa_index; xas_store(&xas, entry); xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_alloc); /** * __xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ int __xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { u32 min = limit.min; int ret; limit.min = max(min, *next); ret = __xa_alloc(xa, id, entry, limit, gfp); if ((xa->xa_flags & XA_FLAGS_ALLOC_WRAPPED) && ret == 0) { xa->xa_flags &= ~XA_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && limit.min > min) { limit.min = min; ret = __xa_alloc(xa, id, entry, limit, gfp); if (ret == 0) ret = 1; } if (ret >= 0) { *next = *id + 1; if (*next == 0) xa->xa_flags |= XA_FLAGS_ALLOC_WRAPPED; } return ret; } EXPORT_SYMBOL(__xa_alloc_cyclic); /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_set_mark(&xas, mark); } EXPORT_SYMBOL(__xa_set_mark); /** * __xa_clear_mark() - Clear this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_clear_mark(&xas, mark); } EXPORT_SYMBOL(__xa_clear_mark); /** * xa_get_mark() - Inquire whether this mark is set on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * This function uses the RCU read lock, so the result may be out of date * by the time it returns. If you need the result to be stable, use a lock. * * Context: Any context. Takes and releases the RCU lock. * Return: True if the entry at @index has this mark set, false if it doesn't. */ bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); entry = xas_start(&xas); while (xas_get_mark(&xas, mark)) { if (!xa_is_node(entry)) goto found; entry = xas_descend(&xas, xa_to_node(entry)); } rcu_read_unlock(); return false; found: rcu_read_unlock(); return true; } EXPORT_SYMBOL(xa_get_mark); /** * xa_set_mark() - Set this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Process context. Takes and releases the xa_lock. */ void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_set_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_set_mark); /** * xa_clear_mark() - Clear this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Clearing a mark always succeeds. * * Context: Process context. Takes and releases the xa_lock. */ void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_clear_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_clear_mark); /** * xa_find() - Search the XArray for an entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter, and has the lowest * index that is at least @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may not find * entries which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The entry, if found, otherwise %NULL. */ void *xa_find(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp); void *entry; rcu_read_lock(); do { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); } while (xas_retry(&xas, entry)); rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find); static bool xas_sibling(struct xa_state *xas) { struct xa_node *node = xas->xa_node; unsigned long mask; if (!IS_ENABLED(CONFIG_XARRAY_MULTI) || !node) return false; mask = (XA_CHUNK_SIZE << node->shift) - 1; return (xas->xa_index & mask) > ((unsigned long)xas->xa_offset << node->shift); } /** * xa_find_after() - Search the XArray for a present entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter and has the lowest * index that is above @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may miss entries * which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The pointer, if found, otherwise %NULL. */ void *xa_find_after(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp + 1); void *entry; if (xas.xa_index == 0) return NULL; rcu_read_lock(); for (;;) { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); if (xas_invalid(&xas)) break; if (xas_sibling(&xas)) continue; if (!xas_retry(&xas, entry)) break; } rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find_after); static unsigned int xas_extract_present(struct xa_state *xas, void **dst, unsigned long max, unsigned int n) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each(xas, entry, max) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } static unsigned int xas_extract_marked(struct xa_state *xas, void **dst, unsigned long max, unsigned int n, xa_mark_t mark) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each_marked(xas, entry, max, mark) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } /** * xa_extract() - Copy selected entries from the XArray into a normal array. * @xa: The source XArray to copy from. * @dst: The buffer to copy entries into. * @start: The first index in the XArray eligible to be selected. * @max: The last index in the XArray eligible to be selected. * @n: The maximum number of entries to copy. * @filter: Selection criterion. * * Copies up to @n entries that match @filter from the XArray. The * copied entries will have indices between @start and @max, inclusive. * * The @filter may be an XArray mark value, in which case entries which are * marked with that mark will be copied. It may also be %XA_PRESENT, in * which case all entries which are not %NULL will be copied. * * The entries returned may not represent a snapshot of the XArray at a * moment in time. For example, if another thread stores to index 5, then * index 10, calling xa_extract() may return the old contents of index 5 * and the new contents of index 10. Indices not modified while this * function is running will not be skipped. * * If you need stronger guarantees, holding the xa_lock across calls to this * function will prevent concurrent modification. * * Context: Any context. Takes and releases the RCU lock. * Return: The number of entries copied. */ unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t filter) { XA_STATE(xas, xa, start); if (!n) return 0; if ((__force unsigned int)filter < XA_MAX_MARKS) return xas_extract_marked(&xas, dst, max, n, filter); return xas_extract_present(&xas, dst, max, n); } EXPORT_SYMBOL(xa_extract); /** * xa_delete_node() - Private interface for workingset code. * @node: Node to be removed from the tree. * @update: Function to call to update ancestor nodes. * * Context: xa_lock must be held on entry and will not be released. */ void xa_delete_node(struct xa_node *node, xa_update_node_t update) { struct xa_state xas = { .xa = node->array, .xa_index = (unsigned long)node->offset << (node->shift + XA_CHUNK_SHIFT), .xa_shift = node->shift + XA_CHUNK_SHIFT, .xa_offset = node->offset, .xa_node = xa_parent_locked(node->array, node), .xa_update = update, }; xas_store(&xas, NULL); } EXPORT_SYMBOL_GPL(xa_delete_node); /* For the benefit of the test suite */ /** * xa_destroy() - Free all internal data structures. * @xa: XArray. * * After calling this function, the XArray is empty and has freed all memory * allocated for its internal data structures. You are responsible for * freeing the objects referenced by the XArray. * * Context: Any context. Takes and releases the xa_lock, interrupt-safe. */ void xa_destroy(struct xarray *xa) { XA_STATE(xas, xa, 0); unsigned long flags; void *entry; xas.xa_node = NULL; xas_lock_irqsave(&xas, flags); entry = xa_head_locked(xa); RCU_INIT_POINTER(xa->xa_head, NULL); xas_init_marks(&xas); if (xa_zero_busy(xa)) xa_mark_clear(xa, XA_FREE_MARK); /* lockdep checks we're still holding the lock in xas_free_nodes() */ if (xa_is_node(entry)) xas_free_nodes(&xas, xa_to_node(entry)); xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(xa_destroy); #ifdef XA_DEBUG void xa_dump_node(const struct xa_node *node) { unsigned i, j; if (!node) return; if ((unsigned long)node & 3) { pr_cont("node %px\n", node); return; } pr_cont("node %px %s %d parent %px shift %d count %d values %d " "array %px list %px %px marks", node, node->parent ? "offset" : "max", node->offset, node->parent, node->shift, node->count, node->nr_values, node->array, node->private_list.prev, node->private_list.next); for (i = 0; i < XA_MAX_MARKS; i++) for (j = 0; j < XA_MARK_LONGS; j++) pr_cont(" %lx", node->marks[i][j]); pr_cont("\n"); } void xa_dump_index(unsigned long index, unsigned int shift) { if (!shift) pr_info("%lu: ", index); else if (shift >= BITS_PER_LONG) pr_info("0-%lu: ", ~0UL); else pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1)); } void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift) { if (!entry) return; xa_dump_index(index, shift); if (xa_is_node(entry)) { if (shift == 0) { pr_cont("%px\n", entry); } else { unsigned long i; struct xa_node *node = xa_to_node(entry); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) xa_dump_entry(node->slots[i], index + (i << node->shift), node->shift); } } else if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (!xa_is_internal(entry)) pr_cont("%px\n", entry); else if (xa_is_retry(entry)) pr_cont("retry (%ld)\n", xa_to_internal(entry)); else if (xa_is_sibling(entry)) pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry)); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else pr_cont("UNKNOWN ENTRY (%px)\n", entry); } void xa_dump(const struct xarray *xa) { void *entry = xa->xa_head; unsigned int shift = 0; pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry, xa->xa_flags, xa_marked(xa, XA_MARK_0), xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2)); if (xa_is_node(entry)) shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT; xa_dump_entry(entry, 0, shift); } #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_H #define _LINUX_FS_H #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> #include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/pid.h> #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fcntl.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> #include <linux/shrinker.h> #include <linux/migrate_mode.h> #include <linux/uidgid.h> #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/delayed_call.h> #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> #include <linux/fs_types.h> #include <linux/build_bug.h> #include <linux/stddef.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> struct backing_dev_info; struct bdi_writeback; struct bio; struct export_operations; struct fiemap_extent_info; struct hd_geometry; struct iovec; struct kiocb; struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; struct vm_area_struct; struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; struct fscrypt_info; struct fscrypt_operations; struct fsverity_info; struct fsverity_operations; struct fs_context; struct fs_parameter_spec; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; extern int sysctl_protected_symlinks; extern int sysctl_protected_hardlinks; extern int sysctl_protected_fifos; extern int sysctl_protected_regular; typedef __kernel_rwf_t rwf_t; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 #define MAY_READ 0x00000004 #define MAY_APPEND 0x00000008 #define MAY_ACCESS 0x00000010 #define MAY_OPEN 0x00000020 #define MAY_CHDIR 0x00000040 /* called from RCU mode, don't block */ #define MAY_NOT_BLOCK 0x00000080 /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open() */ /* file is open for reading */ #define FMODE_READ ((__force fmode_t)0x1) /* file is open for writing */ #define FMODE_WRITE ((__force fmode_t)0x2) /* file is seekable */ #define FMODE_LSEEK ((__force fmode_t)0x4) /* file can be accessed using pread */ #define FMODE_PREAD ((__force fmode_t)0x8) /* file can be accessed using pwrite */ #define FMODE_PWRITE ((__force fmode_t)0x10) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)0x20) /* File is opened with O_NDELAY (only set for block devices) */ #define FMODE_NDELAY ((__force fmode_t)0x40) /* File is opened with O_EXCL (only set for block devices) */ #define FMODE_EXCL ((__force fmode_t)0x80) /* File is opened using open(.., 3, ..) and is writeable only for ioctls (specialy hack for floppy.c) */ #define FMODE_WRITE_IOCTL ((__force fmode_t)0x100) /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)0x200) /* 64bit hashes as llseek() offset (for directories) */ #define FMODE_64BITHASH ((__force fmode_t)0x400) /* * Don't update ctime and mtime. * * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ #define FMODE_NOCMTIME ((__force fmode_t)0x800) /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)0x1000) /* File is huge (eg. /dev/kmem): treat loff_t as unsigned */ #define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)0x4000) /* File needs atomic accesses to f_pos */ #define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)0x10000) /* Has read method(s) */ #define FMODE_CAN_READ ((__force fmode_t)0x20000) /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)0x40000) #define FMODE_OPENED ((__force fmode_t)0x80000) #define FMODE_CREATED ((__force fmode_t)0x100000) /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)0x200000) /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)0x8000000) /* File represents mount that needs unmounting */ #define FMODE_NEED_UNMOUNT ((__force fmode_t)0x10000000) /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) /* File supports async buffered reads */ #define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) /* * Attribute flags. These should be or-ed together to figure out what * has been changed! */ #define ATTR_MODE (1 << 0) #define ATTR_UID (1 << 1) #define ATTR_GID (1 << 2) #define ATTR_SIZE (1 << 3) #define ATTR_ATIME (1 << 4) #define ATTR_MTIME (1 << 5) #define ATTR_CTIME (1 << 6) #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) #define ATTR_KILL_PRIV (1 << 14) #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) /* * Whiteout is represented by a char device. The following constants define the * mode and device number to use. */ #define WHITEOUT_MODE 0 #define WHITEOUT_DEV 0 /* * This is the Inode Attributes structure, used for notify_change(). It * uses the above definitions as flags, to know which values have changed. * Also, in this manner, a Filesystem can look at only the values it cares * about. Basically, these are the attributes that the VFS layer can * request to change from the FS layer. * * Derek Atkins <warlord@MIT.EDU> 94-10-20 */ struct iattr { unsigned int ia_valid; umode_t ia_mode; kuid_t ia_uid; kgid_t ia_gid; loff_t ia_size; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to * implement an ftruncate() like method. NOTE: filesystem should * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL). */ struct file *ia_file; }; /* * Includes for diskquotas. */ #include <linux/quota.h> /* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ #define FILESYSTEM_MAX_STACK_DEPTH 2 /** * enum positive_aop_returns - aop return codes with specific semantics * * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has * completed, that the page is still locked, and * should be considered active. The VM uses this hint * to return the page to the active list -- it won't * be a candidate for writeback again in the near * future. Other callers must be careful to unlock * the page if they get this return. Returned by * writepage(); * * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has * unlocked it and the page might have been truncated. * The caller should back up to acquiring a new page and * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned * by readpage(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a * page to allow for functions that return the number of bytes operated on in a * given page. */ enum positive_aop_returns { AOP_WRITEPAGE_ACTIVATE = 0x80000, AOP_TRUNCATED_PAGE = 0x80001, }; #define AOP_FLAG_CONT_EXPAND 0x0001 /* called from cont_expand */ #define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct * helper code (eg buffer layer) * to clear GFP_FS from alloc */ /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; struct readahead_control; /* * Write life time hint values. * Stored in struct inode as u8. */ enum rw_hint { WRITE_LIFE_NOT_SET = 0, WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE, WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT, WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM, WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG, WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, }; /* Match RWF_* bits to IOCB bits */ #define IOCB_HIPRI (__force int) RWF_HIPRI #define IOCB_DSYNC (__force int) RWF_DSYNC #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) #define IOCB_DIRECT (1 << 17) #define IOCB_WRITE (1 << 18) /* iocb->ki_waitq is valid */ #define IOCB_WAITQ (1 << 19) #define IOCB_NOIO (1 << 20) /* kiocb is a read or write operation submitted by fs/aio.c. */ #define IOCB_AIO_RW (1 << 23) struct kiocb { struct file *ki_filp; /* The 'ki_filp' pointer is shared in a union for aio */ randomized_struct_fields_start loff_t ki_pos; void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); void *private; int ki_flags; u16 ki_hint; u16 ki_ioprio; /* See linux/ioprio.h */ union { unsigned int ki_cookie; /* for ->iopoll */ struct wait_page_queue *ki_waitq; /* for async buffered IO */ }; randomized_struct_fields_end }; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } /* * "descriptor" for what we're up to with a read. * This allows us to use the same read code yet * have multiple different users of the data that * we read from a file. * * The simplest case just copies the data to user * mode. */ typedef struct { size_t written; size_t count; union { char __user *buf; void *data; } arg; int error; } read_descriptor_t; typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long); struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); /* Set a page dirty. Return true if this dirtied it */ int (*set_page_dirty)(struct page *page); /* * Reads in the requested pages. Unlike ->readpage(), this is * PURELY used for read-ahead!. */ int (*readpages)(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages); void (*readahead)(struct readahead_control *); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a page to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ int (*migratepage) (struct address_space *, struct page *, struct page *, enum migrate_mode); bool (*isolate_page)(struct page *, isolate_mode_t); void (*putback_page)(struct page *); int (*launder_page) (struct page *); int (*is_partially_uptodate) (struct page *, unsigned long, unsigned long); void (*is_dirty_writeback) (struct page *, bool *, bool *); int (*error_remove_page)(struct address_space *, struct page *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); }; extern const struct address_space_operations empty_aops; /* * pagecache_write_begin/pagecache_write_end must be used by general code * to write into the pagecache. */ int pagecache_write_begin(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); int pagecache_write_end(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. * @nrexceptional: Shadow or DAX entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. * @private_lock: For use by the owner of the address_space. * @private_list: For use by the owner of the address_space. * @private_data: For use by the owner of the address_space. */ struct address_space { struct inode *host; struct xarray i_pages; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS /* number of thp, only for non-shmem files */ atomic_t nr_thps; #endif struct rb_root_cached i_mmap; struct rw_semaphore i_mmap_rwsem; unsigned long nrpages; unsigned long nrexceptional; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; errseq_t wb_err; spinlock_t private_lock; struct list_head private_list; void *private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. */ /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 #define PAGECACHE_TAG_WRITEBACK XA_MARK_1 #define PAGECACHE_TAG_TOWRITE XA_MARK_2 /* * Returns true if any of the pages in the mapping are marked with the tag. */ static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } static inline void i_mmap_lock_write(struct address_space *mapping) { down_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_write(struct address_space *mapping) { return down_write_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_write(struct address_space *mapping) { up_write(&mapping->i_mmap_rwsem); } static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_read(struct address_space *mapping) { up_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_locked(struct address_space *mapping) { lockdep_assert_held(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_write_locked(struct address_space *mapping) { lockdep_assert_held_write(&mapping->i_mmap_rwsem); } /* * Might pages of this file be mapped into userspace? */ static inline int mapping_mapped(struct address_space *mapping) { return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* * Might pages of this file have been modified in userspace? * Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * * If i_mmap_writable is negative, no new writable mappings are allowed. You * can only deny writable mappings, if none exists right now. */ static inline int mapping_writably_mapped(struct address_space *mapping) { return atomic_read(&mapping->i_mmap_writable) > 0; } static inline int mapping_map_writable(struct address_space *mapping) { return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? 0 : -EPERM; } static inline void mapping_unmap_writable(struct address_space *mapping) { atomic_dec(&mapping->i_mmap_writable); } static inline int mapping_deny_writable(struct address_space *mapping) { return atomic_dec_unless_positive(&mapping->i_mmap_writable) ? 0 : -EBUSY; } static inline void mapping_allow_writable(struct address_space *mapping) { atomic_inc(&mapping->i_mmap_writable); } /* * Use sequence counter to get consistent i_size on 32-bit processors. */ #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include <linux/seqlock.h> #define __NEED_I_SIZE_ORDERED #define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount) #else #define i_size_ordered_init(inode) do { } while (0) #endif struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) #define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) { return (void *)task + 1; } static inline bool is_uncached_acl(struct posix_acl *acl) { return (long)acl & 1; } #define IOP_FASTPERM 0x0001 #define IOP_LOOKUP 0x0002 #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 struct fsnotify_mark_connector; /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' */ struct inode { umode_t i_mode; unsigned short i_opflags; kuid_t i_uid; kgid_t i_gid; unsigned int i_flags; #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif const struct inode_operations *i_op; struct super_block *i_sb; struct address_space *i_mapping; #ifdef CONFIG_SECURITY void *i_security; #endif /* Stat data, not accessed from path walking */ unsigned long i_ino; /* * Filesystems may only read i_nlink directly. They shall use the * following functions for modification: * * (set|clear|inc|drop)_nlink * inode_(inc|dec)_link_count */ union { const unsigned int i_nlink; unsigned int __i_nlink; }; dev_t i_rdev; loff_t i_size; struct timespec64 i_atime; struct timespec64 i_mtime; struct timespec64 i_ctime; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; u8 i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif /* Misc */ unsigned long i_state; struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_io_list; /* backing dev IO list */ #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *i_wb; /* the associated cgroup wb */ /* foreign inode detection, see wbc_detach_inode() */ int i_wb_frn_winner; u16 i_wb_frn_avg_time; u16 i_wb_frn_history; #endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; struct list_head i_wb_list; /* backing dev writeback list */ union { struct hlist_head i_dentry; struct rcu_head i_rcu; }; atomic64_t i_version; atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) atomic_t i_readcount; /* struct files open RO */ #endif union { const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ void (*free_inode)(struct inode *); }; struct file_lock_context *i_flctx; struct address_space i_data; struct list_head i_devices; union { struct pipe_inode_info *i_pipe; struct block_device *i_bdev; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; }; __u32 i_generation; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_info *i_crypt_info; #endif #ifdef CONFIG_FS_VERITY struct fsverity_info *i_verity_info; #endif void *i_private; /* fs or device private pointer */ } __randomize_layout; struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); static inline unsigned int i_blocksize(const struct inode *node) { return (1 << node->i_blkbits); } static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); } /* * __mark_inode_dirty expects inodes to be hashed. Since we don't * want special inodes in the fileset inode space, we make them * appear hashed, but do not put on any lists. hlist_del() * will work fine and require no locking. */ static inline void inode_fake_hash(struct inode *inode) { hlist_add_fake(&inode->i_hash); } /* * inode->i_mutex nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent * 2: child/target * 3: xattr * 4: second non-directory * 5: second parent (when locking independent directories in rename) * * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two * non-directories at once. * * The locking order between these classes is * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { I_MUTEX_NORMAL, I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, I_MUTEX_NONDIR2, I_MUTEX_PARENT2, }; static inline void inode_lock(struct inode *inode) { down_write(&inode->i_rwsem); } static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); } static inline void inode_lock_shared(struct inode *inode) { down_read(&inode->i_rwsem); } static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); } static inline int inode_trylock(struct inode *inode) { return down_write_trylock(&inode->i_rwsem); } static inline int inode_trylock_shared(struct inode *inode) { return down_read_trylock(&inode->i_rwsem); } static inline int inode_is_locked(struct inode *inode) { return rwsem_is_locked(&inode->i_rwsem); } static inline void inode_lock_nested(struct inode *inode, unsigned subclass) { down_write_nested(&inode->i_rwsem, subclass); } static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass) { down_read_nested(&inode->i_rwsem, subclass); } void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic * with respect to the local cpu (unlike with preempt disabled), * but they don't need to be atomic with respect to other cpus like in * true SMP (so they need either to either locally disable irq around * the read or for example on x86 they can be still implemented as a * cmpxchg8b without the need of the lock prefix). For SMP compiles * and 64bit archs it makes no difference if preempt is enabled or not. */ static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; unsigned int seq; do { seq = read_seqcount_begin(&inode->i_size_seqcount); i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) loff_t i_size; preempt_disable(); i_size = inode->i_size; preempt_enable(); return i_size; #else return inode->i_size; #endif } /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); inode->i_size = i_size; preempt_enable(); #else inode->i_size = i_size; #endif } static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } static inline unsigned imajor(const struct inode *inode) { return MAJOR(inode->i_rdev); } struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ kuid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; /* * Track a single file's readahead state */ struct file_ra_state { pgoff_t start; /* where readahead started */ unsigned int size; /* # of readahead pages */ unsigned int async_size; /* do asynchronous readahead when there are only # of pages ahead */ unsigned int ra_pages; /* Maximum readahead window */ unsigned int mmap_miss; /* Cache miss stat for mmap accesses */ loff_t prev_pos; /* Cache last read() position */ }; /* * Check if @index falls in the readahead windows. */ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) { return (index >= ra->start && index < ra->start + ra->size); } struct file { union { struct llist_node fu_llist; struct rcu_head fu_rcuhead; } f_u; struct path f_path; struct inode *f_inode; /* cached value */ const struct file_operations *f_op; /* * Protects f_ep_links, f_flags. * Must not be taken from IRQ context. */ spinlock_t f_lock; enum rw_hint f_write_hint; atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; struct mutex f_pos_lock; loff_t f_pos; struct fown_struct f_owner; const struct cred *f_cred; struct file_ra_state f_ra; u64 f_version; #ifdef CONFIG_SECURITY void *f_security; #endif /* needed for tty driver, and maybe others */ void *private_data; #ifdef CONFIG_EPOLL /* Used by fs/eventpoll.c to link all the hooks to this file */ struct list_head f_ep_links; struct list_head f_tfile_llink; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; errseq_t f_wb_err; errseq_t f_sb_err; /* for syncfs */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ unsigned char f_handle[]; }; static inline struct file *get_file(struct file *f) { atomic_long_inc(&f->f_count); return f; } #define get_file_rcu_many(x, cnt) \ atomic_long_add_unless(&(x)->f_count, (cnt), 0) #define get_file_rcu(x) get_file_rcu_many((x), 1) #define file_count(x) atomic_long_read(&(x)->f_count) #define MAX_NON_LFS ((1UL<<31) - 1) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 #define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_DELEG 4 /* NFSv4 delegation */ #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_EXISTS 16 /* when unlocking, test for existence */ #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ #define FL_RECLAIM 4096 /* reclaiming from a reboot server */ #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. */ #define FILE_LOCK_DEFERRED 1 /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); }; struct lock_manager_operations { void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_break)(struct file_lock *); int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); bool (*lm_breaker_owns_lease)(struct file_lock *); bool (*lm_lock_expirable)(struct file_lock *cfl); void (*lm_expire_lock)(void); }; struct lock_manager { struct list_head list; /* * NFSv4 and up also want opens blocked during the grace period; * NLM doesn't care: */ bool block_opens; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); bool locks_in_grace(struct net *); bool opens_in_grace(struct net *); /* that will die - we need it for nfs_lock_info */ #include <linux/nfs_fs_i.h> /* * struct file_lock represents a generic "file lock". It's used to represent * POSIX byte range locks, BSD (flock) locks, and leases. It's important to * note that the same struct is used to represent both a request for a lock and * the lock itself, but the same object is never used for both. * * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * * The varous i_flctx lists are ordered by: * * 1) lock owner * 2) lock range start * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock { struct file_lock *fl_blocker; /* The lock, that is blocking us */ struct list_head fl_list; /* link into file_lock_context */ struct hlist_node fl_link; /* node in global lists */ struct list_head fl_blocked_requests; /* list of requests with * ->fl_blocker pointing here */ struct list_head fl_blocked_member; /* node in * ->fl_blocker->fl_blocked_requests */ fl_owner_t fl_owner; unsigned int fl_flags; unsigned char fl_type; unsigned int fl_pid; int fl_link_cpu; /* what cpu's list is this on? */ wait_queue_head_t fl_wait; struct file *fl_file; loff_t fl_start; loff_t fl_end; struct fasync_struct * fl_fasync; /* for lease break notifications */ /* for lease breaks: */ unsigned long fl_break_time; unsigned long fl_downgrade_time; const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; struct nfs4_lock_info nfs4_fl; struct { struct list_head link; /* link in AFS vnode's pending_locks list */ int state; /* state of grant or error if -ve */ unsigned int debug_id; } afs; } fl_u; } __randomize_layout; struct file_lock_context { spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; }; /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define INT_LIMIT(x) (~((x)1 << (sizeof(x)*8 - 1))) #define OFFSET_MAX INT_LIMIT(loff_t) #define OFFT_OFFSET_MAX INT_LIMIT(off_t) #endif extern void send_sigio(struct fown_struct *fown, int fd, int band); #define locks_inode(f) file_inode(f) #ifdef CONFIG_FILE_LOCKING extern int fcntl_getlk(struct file *, unsigned int, struct flock *); extern int fcntl_setlk(unsigned int, struct file *, unsigned int, struct flock *); #if BITS_PER_LONG == 32 extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, struct flock64 *); #endif extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); extern int fcntl_getlease(struct file *filp); /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); extern void locks_init_lock(struct file_lock *); extern struct file_lock * locks_alloc_lock(void); extern void locks_copy_lock(struct file_lock *, struct file_lock *); extern void locks_copy_conflock(struct file_lock *, struct file_lock *); extern void locks_remove_posix(struct file *, fl_owner_t); extern void locks_remove_file(struct file *); extern void locks_release_private(struct file_lock *); extern void posix_test_lock(struct file *, struct file_lock *); extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); extern int locks_delete_block(struct file_lock *); extern int vfs_test_lock(struct file *, struct file_lock *); extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); bool vfs_inode_has_locks(struct inode *inode); extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); extern void lease_get_mtime(struct inode *, struct timespec64 *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); extern int vfs_setlease(struct file *, long, struct file_lock **, void **); extern int lease_modify(struct file_lock *, int, struct list_head *); struct notifier_block; extern int lease_register_notifier(struct notifier_block *); extern void lease_unregister_notifier(struct notifier_block *); struct files_struct; extern void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); extern bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner); static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return smp_load_acquire(&inode->i_flctx); } #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) { return -EINVAL; } static inline int fcntl_setlk(unsigned int fd, struct file *file, unsigned int cmd, struct flock __user *user) { return -EACCES; } #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, struct flock64 __user *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, unsigned int cmd, struct flock64 __user *user) { return -EACCES; } #endif static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg) { return -EINVAL; } static inline int fcntl_getlease(struct file *filp) { return F_UNLCK; } static inline void locks_free_lock_context(struct inode *inode) { } static inline void locks_init_lock(struct file_lock *fl) { return; } static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) { return; } static inline void locks_remove_file(struct file *filp) { return; } static inline void posix_test_lock(struct file *filp, struct file_lock *fl) { return; } static inline int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return -ENOLCK; } static inline int locks_delete_block(struct file_lock *waiter) { return -ENOENT; } static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { return -ENOLCK; } static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline bool vfs_inode_has_locks(struct inode *inode) { return false; } static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; } static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { return 0; } static inline void lease_get_mtime(struct inode *inode, struct timespec64 *time) { return; } static inline int generic_setlease(struct file *filp, long arg, struct file_lock **flp, void **priv) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv) { return -EINVAL; } static inline int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { return -EINVAL; } struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { return false; } static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return NULL; } #endif /* !CONFIG_FILE_LOCKING */ static inline struct inode *file_inode(const struct file *f) { return f->f_inode; } static inline struct dentry *file_dentry(const struct file *file) { return d_real(file->f_path.dentry, file_inode(file)); } static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(locks_inode(filp), fl); } struct fasync_struct { rwlock_t fa_lock; int magic; int fa_fd; struct fasync_struct *fa_next; /* singly linked list */ struct file *fa_file; struct rcu_head fa_rcu; }; #define FASYNC_MAGIC 0x4601 /* SMP safe fasync helpers: */ extern int fasync_helper(int, struct file *, int, struct fasync_struct **); extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); extern int fasync_remove_entry(struct file *, struct fasync_struct **); extern struct fasync_struct *fasync_alloc(void); extern void fasync_free(struct fasync_struct *); /* can be called from interrupts */ extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, unsigned long arg, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct fown_struct *fown); /* * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ #define SB_RDONLY BIT(0) /* Mount read-only */ #define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ #define SB_NODEV BIT(2) /* Disallow access to device special files */ #define SB_NOEXEC BIT(3) /* Disallow program execution */ #define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ #define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ #define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ #define SB_NOATIME BIT(10) /* Do not update access times. */ #define SB_NODIRATIME BIT(11) /* Do not update directory access times */ #define SB_SILENT BIT(15) #define SB_POSIXACL BIT(16) /* VFS does not apply the umask */ #define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ #define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ #define SB_I_VERSION BIT(23) /* Update inode I_version field */ #define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ #define SB_SUBMOUNT BIT(26) #define SB_FORCE BIT(27) #define SB_NOSEC BIT(28) #define SB_BORN BIT(29) #define SB_ACTIVE BIT(30) #define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) #define sb_has_strict_encoding(sb) \ (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) /* * Umount options */ #define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ #define MNT_DETACH 0x00000002 /* Just detach from the tree */ #define MNT_EXPIRE 0x00000004 /* Mark for expiry */ #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ /* sb->s_iflags */ #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ #define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ #define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop * internal threads if needed) */ SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ }; #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) struct sb_writers { int frozen; /* Is sb frozen? */ wait_queue_head_t wait_unfrozen; /* for get_super_thawed() */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ unsigned char s_blocksize_bits; unsigned long s_blocksize; loff_t s_maxbytes; /* Max file size */ struct file_system_type *s_type; const struct super_operations *s_op; const struct dquot_operations *dq_op; const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; unsigned long s_iflags; /* internal SB_I_* flags */ unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; int s_count; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; #endif const struct xattr_handler **s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif #ifdef CONFIG_UNICODE struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; unsigned int s_quota_types; /* Bitmask of supported quota types */ struct quota_info s_dquot; /* Diskquota specific options */ struct sb_writers s_writers; /* * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and * s_fsnotify_marks together for cache efficiency. They are frequently * accessed and rarely modified. */ void *s_fs_info; /* Filesystem private info */ /* Granularity of c/m/atime in ns (cannot be worse than a second) */ u32 s_time_gran; /* Time limits for c/m/atime in seconds */ time64_t s_time_min; time64_t s_time_max; #ifdef CONFIG_FSNOTIFY __u32 s_fsnotify_mask; struct fsnotify_mark_connector __rcu *s_fsnotify_marks; #endif char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ unsigned int s_max_links; fmode_t s_mode; /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ struct mutex s_vfs_rename_mutex; /* Kludge */ /* * Filesystem subtype. If non-empty the filesystem type field * in /proc/mounts will be "type.subtype" */ const char *s_subtype; const struct dentry_operations *s_d_op; /* default d_op for dentries */ /* * Saved pool identifier for cleancache (-1 means none) */ int cleancache_poolid; struct shrinker s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; /* * Number of inode/mount/sb objects that are being watched, note that * inodes objects are currently double-accounted. */ atomic_long_t s_fsnotify_connectors; /* Being remounted read-only */ int s_readonly_remount; /* per-sb errseq_t for reporting writeback errors via syncfs */ errseq_t s_wb_err; /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; /* * Owning user namespace and default context in which to * interpret filesystem uids, gids, quotas, device nodes, * xattrs and security labels. */ struct user_namespace *s_user_ns; /* * The list_lru structure is essentially just a pointer to a table * of per-node lru lists, each of which has its own spinlock. * There is no need to put them into separate cachelines. */ struct list_lru s_dentry_lru; struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; struct mutex s_sync_lock; /* sync serialisation lock */ /* * Indicates how deep in a filesystem stack this SB is */ int s_stack_depth; /* s_inode_list_lock protects s_inodes */ spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; struct list_head s_inodes; /* all inodes */ spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ } __randomize_layout; /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can * instead deal with the raw numeric values that are stored * in the filesystem. */ static inline uid_t i_uid_read(const struct inode *inode) { return from_kuid(inode->i_sb->s_user_ns, inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { return from_kgid(inode->i_sb->s_user_ns, inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { inode->i_uid = make_kuid(inode->i_sb->s_user_ns, uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); } struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); /** * inode_get_ctime - fetch the current ctime from the inode * @inode: inode from which to fetch ctime * * Grab the current ctime from the inode and return it. */ static inline struct timespec64 inode_get_ctime(const struct inode *inode) { return inode->i_ctime; } /** * inode_set_ctime_to_ts - set the ctime in the inode * @inode: inode in which to set the ctime * @ts: value to set in the ctime field * * Set the ctime in @inode to @ts */ static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_ctime = ts; return ts; } /** * inode_set_ctime - set the ctime in the inode * @inode: inode in which to set the ctime * @sec: tv_sec value to set * @nsec: tv_nsec value to set * * Set the ctime in @inode to { @sec, @nsec } */ static inline struct timespec64 inode_set_ctime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_ctime_to_ts(inode, ts); } /* * Snapshotting support. */ /* * These are internal functions, please use sb_start_{write,pagefault,intwrite} * instead. */ static inline void __sb_end_write(struct super_block *sb, int level) { percpu_up_read(sb->s_writers.rw_sem + level-1); } static inline void __sb_start_write(struct super_block *sb, int level) { percpu_down_read(sb->s_writers.rw_sem + level - 1); } static inline bool __sb_start_write_trylock(struct super_block *sb, int level) { return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); } #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to * * Decrement number of writers to the filesystem. Wake up possible waiters * wanting to freeze the filesystem. */ static inline void sb_end_write(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_WRITE); } /** * sb_end_pagefault - drop write access to a superblock from a page fault * @sb: the super we wrote to * * Decrement number of processes handling write page fault to the filesystem. * Wake up possible waiters wanting to freeze the filesystem. */ static inline void sb_end_pagefault(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_end_intwrite - drop write access to a superblock for internal fs purposes * @sb: the super we wrote to * * Decrement fs-internal number of writers to the filesystem. Wake up possible * waiters wanting to freeze the filesystem. */ static inline void sb_end_intwrite(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_FS); } /** * sb_start_write - get write access to a superblock * @sb: the super we write to * * When a process wants to write data or metadata to a file system (i.e. dirty * a page or an inode), it should embed the operation in a sb_start_write() - * sb_end_write() pair to get exclusion against file system freezing. This * function increments number of writers preventing freezing. If the file * system is already frozen, the function waits until the file system is * thawed. * * Since freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. Generally, * freeze protection should be the outermost lock. In particular, we have: * * sb_start_write * -> i_mutex (write path, truncate, directory ops, ...) * -> s_umount (freeze_super, thaw_super) */ static inline void sb_start_write(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_WRITE); } static inline bool sb_start_write_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** * sb_start_pagefault - get write access to a superblock from a page fault * @sb: the super we write to * * When a process starts handling write page fault, it should embed the * operation into sb_start_pagefault() - sb_end_pagefault() pair to get * exclusion against file system freezing. This is needed since the page fault * is going to dirty a page. This function increments number of running page * faults preventing freezing. If the file system is already frozen, the * function waits until the file system is thawed. * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /* * sb_start_intwrite - get write access to a superblock for internal fs purposes * @sb: the super we write to * * This is the third level of protection against filesystem freezing. It is * free for use by a filesystem. The only requirement is that it must rank * below sb_start_pagefault. * * For example filesystem can call sb_start_intwrite() when starting a * transaction which somewhat eases handling of freezing for internal sources * of filesystem changes (internal fs threads, discarding preallocation on file * close, etc.). */ static inline void sb_start_intwrite(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_FS); } static inline bool sb_start_intwrite_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_FS); } /** * kiocb_start_write - get write access to a superblock for async file io * @iocb: the io context we want to submit the write with * * This is a variant of sb_start_write() for async io submission. * Should be matched with a call to kiocb_end_write(). */ static inline void kiocb_start_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); sb_start_write(inode->i_sb); /* * Fool lockdep by telling it the lock got released so that it * doesn't complain about the held lock when we return to userspace. */ __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE); } /** * kiocb_end_write - drop write access to a superblock after async file io * @iocb: the io context we sumbitted the write with * * Should be matched with a call to kiocb_start_write(). */ static inline void kiocb_end_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); /* * Tell lockdep we inherited freeze protection from submission thread. */ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); sb_end_write(inode->i_sb); } extern bool inode_owner_or_capable(const struct inode *inode); /* * VFS helper functions.. */ extern int vfs_create(struct inode *, struct dentry *, umode_t, bool); extern int vfs_mkdir(struct inode *, struct dentry *, umode_t); extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); extern int vfs_symlink(struct inode *, struct dentry *, const char *); extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **); extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); struct renamedata { struct inode *old_dir; struct dentry *old_dentry; struct inode *new_dir; struct dentry *new_dentry; struct inode **delegated_inode; unsigned int flags; } __randomize_layout; int vfs_rename(struct renamedata *); static inline int vfs_whiteout(struct inode *dir, struct dentry *dentry) { return vfs_mknod(dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); } extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #else #define compat_ptr_ioctl NULL #endif /* * VFS file helper functions. */ extern void inode_init_owner(struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); umode_t mode_strip_sgid(const struct inode *dir, umode_t mode); /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. */ struct dir_context; typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { filldir_t actor; loff_t pos; }; /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. * * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) * NOMMU_MAP_READ: Can be mapped for reading * NOMMU_MAP_WRITE: Can be mapped for writing * NOMMU_MAP_EXEC: Can be mapped for execution */ #define NOMMU_MAP_COPY 0x00000001 #define NOMMU_MAP_DIRECT 0x00000008 #define NOMMU_MAP_READ VM_MAYREAD #define NOMMU_MAP_WRITE VM_MAYWRITE #define NOMMU_MAP_EXEC VM_MAYEXEC #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) /* * These flags control the behavior of the remap_file_range function pointer. * If it is called with len == 0 that means "remap to end of source file". * See Documentation/filesystems/vfs.rst for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) #define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of * the behavior of the remap operation. The changes must be made by the * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) /* * These flags control the behavior of vfs_copy_file_range(). * They are not available to the user via syscall. * * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops */ #define COPY_FILE_SPLICE (1 << 0) struct iov_iter; struct file_operations { struct module *owner; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, bool spin); int (*iterate) (struct file *, struct dir_context *); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); unsigned long mmap_supported_flags; int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); int (*setlease)(struct file *, long, struct file_lock **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); bool may_pollfree; } __randomize_layout; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); int (*create) (struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct inode *,struct dentry *,const char *); int (*mkdir) (struct inode *,struct dentry *,umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *, struct timespec64 *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct inode *, struct dentry *, umode_t); int (*set_acl)(struct inode *, struct posix_acl *, int); } ____cacheline_aligned; static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio, struct iov_iter *iter) { return file->f_op->read_iter(kio, iter); } static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio, struct iov_iter *iter) { return file->f_op->write_iter(kio, iter); } static inline int call_mmap(struct file *file, struct vm_area_struct *vma) { return file->f_op->mmap(file, vma); } extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); void (*free_inode)(struct inode *); void (*dirty_inode) (struct inode *, int flags); int (*write_inode) (struct inode *, struct writeback_control *wbc); int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); int (*freeze_super) (struct super_block *); int (*freeze_fs) (struct super_block *); int (*thaw_super) (struct super_block *); int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); int (*show_devname)(struct seq_file *, struct dentry *); int (*show_path)(struct seq_file *, struct dentry *); int (*show_stats)(struct seq_file *, struct dentry *); #ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot **(*get_dquots)(struct inode *); #endif int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); }; /* * Inode flags - they have no relation to superblock flags now */ #define S_SYNC (1 << 0) /* Writes are synced at once */ #define S_NOATIME (1 << 1) /* Do not update access times */ #define S_APPEND (1 << 2) /* Append-only file */ #define S_IMMUTABLE (1 << 3) /* Immutable file */ #define S_DEAD (1 << 4) /* removed, but still open directory */ #define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ #define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ #define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ #define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ #define S_PRIVATE (1 << 9) /* Inode is fs-internal */ #define S_IMA (1 << 10) /* Inode has an associated IMA struct */ #define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ #define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX #define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ #else #define S_DAX 0 /* Make all the DAX code disappear */ #endif #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system * flags just means all the inodes inherit those flags by default. It might be * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their * i_flags updated. Hence, i_flags no longer inherit the superblock mount * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) #define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) #define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) #define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) #define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) #define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) #define IS_VERITY(inode) ((inode)->i_flags & S_VERITY) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) static inline bool HAS_UNMAPPED_ID(struct inode *inode) { return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid); } static inline enum rw_hint file_write_hint(struct file *file) { if (file->f_write_hint != WRITE_LIFE_NOT_SET) return file->f_write_hint; return file_inode(file)->i_write_hint; } static inline int iocb_flags(struct file *file); static inline u16 ki_hint_validate(enum rw_hint hint) { typeof(((struct kiocb *)0)->ki_hint) max_hint = -1; if (hint <= max_hint) return hint; return 0; } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = iocb_flags(filp), .ki_hint = ki_hint_validate(file_write_hint(filp)), .ki_ioprio = get_current_ioprio(), }; } static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, .ki_hint = kiocb_src->ki_hint, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; } /* * Inode state bits. Protected by inode->i_lock * * Three bits determine the dirty state of the inode, I_DIRTY_SYNC, * I_DIRTY_DATASYNC and I_DIRTY_PAGES. * * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at * various stages of removing an inode. * * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on * fdatasync(). i_atime is the usual cause. * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of * these changes separately from I_DIRTY_SYNC so that we * don't have to write inode on fdatasync() when only * mtime has changed in it. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and * wait for I_NEW to be released before returning. * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can * also cause waiting on I_NEW, without I_NEW actually * being set. find_inode() uses this to prevent returning * nearly-dead inodes. * I_WILL_FREE Must be set when calling write_inode_now() if i_count * is zero. I_FREEING must be set when I_WILL_FREE is * cleared. * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. * I_CLEAR Added by clear_inode(). In this state the inode is * clean and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are * prohibited for many purposes. iget() must wait for * the inode to be completely released, then create it * anew. Other functions will just ignore such inodes, * if appropriate. I_NEW is used for waiting. * * I_SYNC Writeback of inode is running. The bit is set during * data writeback, and cleared with a wakeup on the bit * address once it is done. The bit is also used to pin * the inode in memory for flusher thread. * * I_REFERENCED Marks the inode as recently references on the LRU list. * * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See * inode_switch_wbs_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * * I_CREATING New object's inode in the middle of setting up. * * I_DONTCACHE Evict inode as soon as it is not used anymore. * * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding * i_count. * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) #define I_DIRTY_DATASYNC (1 << 1) #define I_DIRTY_PAGES (1 << 2) #define __I_NEW 3 #define I_NEW (1 << __I_NEW) #define I_WILL_FREE (1 << 4) #define I_FREEING (1 << 5) #define I_CLEAR (1 << 6) #define __I_SYNC 7 #define I_SYNC (1 << __I_SYNC) #define I_REFERENCED (1 << 8) #define __I_DIO_WAKEUP 9 #define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) #define __I_LRU_ISOLATING 19 #define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY); } static inline void mark_inode_dirty_sync(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY_SYNC); } extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); extern void set_nlink(struct inode *inode, unsigned int nlink); static inline void inode_inc_link_count(struct inode *inode) { inc_nlink(inode); mark_inode_dirty(inode); } static inline void inode_dec_link_count(struct inode *inode) { drop_nlink(inode); mark_inode_dirty(inode); } enum file_time_flags { S_ATIME = 1, S_MTIME = 2, S_CTIME = 4, S_VERSION = 8, }; extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); int inode_update_time(struct inode *inode, struct timespec64 *time, int flags); static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) touch_atime(&file->f_path); } extern int file_modified(struct file *file); int sync_inode(struct inode *inode, struct writeback_control *wbc); int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { const char *name; int fs_flags; #define FS_REQUIRES_DEV 1 #define FS_BINARY_MOUNTDATA 2 #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_THP_SUPPORT 8192 /* Remove once all fs converted */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; struct hlist_head fs_supers; struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; struct lock_class_key s_vfs_rename_key; struct lock_class_key s_writers_key[SB_FREEZE_LEVELS]; struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; struct lock_class_key i_mutex_dir_key; }; #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); int set_anon_super_fc(struct super_block *s, struct fs_context *fc); int get_anon_bdev(dev_t *); void free_anon_bdev(dev_t); struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*set)(struct super_block *, struct fs_context *)); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) \ (((fops) && try_module_get((fops)->owner) ? (fops) : NULL)) #define fops_put(fops) \ do { if (fops) module_put((fops)->owner); } while(0) /* * This one is to be used *ONLY* from ->open() instances. * fops must be non-NULL, pinned down *and* module dependencies * should be sufficient to pin the caller down as well. */ #define replace_fops(f, fops) \ do { \ struct file *__file = (f); \ fops_put(__file->f_op); \ BUG_ON(!(__file->f_op = (fops))); \ } while(0) extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); extern struct vfsmount *kern_mount(struct file_system_type *); extern void kern_unmount(struct vfsmount *mnt); extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); extern long do_mount(const char *, const char __user *, const char *, unsigned long, void *); extern struct vfsmount *collect_mounts(const struct path *); extern void drop_collected_mounts(struct vfsmount *); extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, struct vfsmount *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); extern int freeze_super(struct super_block *super); extern int thaw_super(struct super_block *super); extern bool our_mnt(struct vfsmount *mnt); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); extern int generic_update_time(struct inode *, struct timespec64 *, int); /* /sys/fs */ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) #ifdef CONFIG_MANDATORY_FILE_LOCKING extern int locks_mandatory_locked(struct file *); extern int locks_mandatory_area(struct inode *, struct file *, loff_t, loff_t, unsigned char); /* * Candidates for mandatory locking have the setgid bit set * but no group execute bit - an otherwise meaningless combination. */ static inline int __mandatory_lock(struct inode *ino) { return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID; } /* * ... and these candidates should be on SB_MANDLOCK mounted fs, * otherwise these will be advisory locks */ static inline int mandatory_lock(struct inode *ino) { return IS_MANDLOCK(ino) && __mandatory_lock(ino); } static inline int locks_verify_locked(struct file *file) { if (mandatory_lock(locks_inode(file))) return locks_mandatory_locked(file); return 0; } static inline int locks_verify_truncate(struct inode *inode, struct file *f, loff_t size) { if (!inode->i_flctx || !mandatory_lock(inode)) return 0; if (size < inode->i_size) { return locks_mandatory_area(inode, f, size, inode->i_size - 1, F_WRLCK); } else { return locks_mandatory_area(inode, f, inode->i_size, size - 1, F_WRLCK); } } #else /* !CONFIG_MANDATORY_FILE_LOCKING */ static inline int locks_mandatory_locked(struct file *file) { return 0; } static inline int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start, loff_t end, unsigned char type) { return 0; } static inline int __mandatory_lock(struct inode *inode) { return 0; } static inline int mandatory_lock(struct inode *inode) { return 0; } static inline int locks_verify_locked(struct file *file) { return 0; } static inline int locks_verify_truncate(struct inode *inode, struct file *filp, size_t size) { return 0; } #endif /* CONFIG_MANDATORY_FILE_LOCKING */ #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { int ret; ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); if (ret == -EWOULDBLOCK && delegated_inode) { *delegated_inode = inode; ihold(inode); } return ret; } static inline int break_deleg_wait(struct inode **delegated_inode) { int ret; ret = break_deleg(*delegated_inode, O_WRONLY); iput(*delegated_inode); *delegated_inode = NULL; return ret; } static inline int break_layout(struct inode *inode, bool wait) { smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, FL_LAYOUT); return 0; } #else /* !CONFIG_FILE_LOCKING */ static inline int break_lease(struct inode *inode, unsigned int mode) { return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { return 0; } static inline int break_deleg_wait(struct inode **delegated_inode) { BUG(); return 0; } static inline int break_layout(struct inode *inode, bool wait) { return 0; } #endif /* CONFIG_FILE_LOCKING */ /* fs/open.c */ struct audit_names; struct filename { const char *name; /* pointer to actual string */ const __user char *uptr; /* original userland pointer */ int refcnt; struct audit_names *aname; const char iname[]; }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); extern long vfs_truncate(const struct path *, loff_t); extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int, umode_t); extern struct file * dentry_open(const struct path *, int, const struct cred *); extern struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); extern struct file * open_with_fake_path(const struct path *, int, struct inode*, const struct cred *); static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); } extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int, int *); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); extern void putname(struct filename *name); extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) extern struct super_block *blockdev_superblock; static inline bool sb_is_blkdev_sb(struct super_block *sb) { return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 /* Marks the top and bottom of the second segment of free char majors */ #define CHRDEV_MAJOR_DYN_EXT_START 511 #define CHRDEV_MAJOR_DYN_EXT_END 384 extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name, const struct file_operations *fops); extern void __unregister_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name); extern void unregister_chrdev_region(dev_t, unsigned); extern void chrdev_show(struct seq_file *,off_t); static inline int register_chrdev(unsigned int major, const char *name, const struct file_operations *fops) { return __register_chrdev(major, 0, 256, name, fops); } static inline void unregister_chrdev(unsigned int major, const char *name) { __unregister_chrdev(major, 0, 256, name); } extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); void invalidate_mapping_pagevec(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_pagevec); static inline void invalidate_remote_inode(struct inode *inode) { if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) invalidate_mapping_pages(inode->i_mapping, 0, -1); } extern int invalidate_inode_pages2(struct address_space *mapping); extern int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end); extern int write_inode_now(struct inode *, int); extern int filemap_fdatawrite(struct address_space *); extern int filemap_flush(struct address_space *); extern int filemap_fdatawait_keep_errors(struct address_space *mapping); extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); extern int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte); static inline int filemap_fdatawait(struct address_space *mapping) { return filemap_fdatawait_range(mapping, 0, LLONG_MAX); } extern bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); extern int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode); extern int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); extern int filemap_check_errors(struct address_space *mapping); extern void __filemap_set_wb_err(struct address_space *mapping, int err); static inline int filemap_write_and_wait(struct address_space *mapping) { return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); } extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); static inline int file_write_and_wait(struct file *file) { return file_write_and_wait_range(file, 0, LLONG_MAX); } /** * filemap_set_wb_err - set a writeback error on an address_space * @mapping: mapping in which to set writeback error * @err: error to be set in mapping * * When writeback fails in some way, we must record that error so that * userspace can be informed when fsync and the like are called. We endeavor * to report errors on any file that was open at the time of the error. Some * internal callers also need to know when writeback errors have occurred. * * When a writeback error occurs, most filesystems will want to call * filemap_set_wb_err to record the error in the mapping so that it will be * automatically reported whenever fsync is called on the file. */ static inline void filemap_set_wb_err(struct address_space *mapping, int err) { /* Fastpath for common case of no error */ if (unlikely(err)) __filemap_set_wb_err(mapping, err); } /** * filemap_check_wb_err - has an error occurred since the mark was sampled? * @mapping: mapping to check for writeback errors * @since: previously-sampled errseq_t * * Grab the errseq_t value from the mapping, and see if it has changed "since" * the given value was sampled. * * If it has then report the latest error set, otherwise return 0. */ static inline int filemap_check_wb_err(struct address_space *mapping, errseq_t since) { return errseq_check(&mapping->wb_err, since); } /** * filemap_sample_wb_err - sample the current errseq_t to test for later errors * @mapping: mapping to be sampled * * Writeback errors are always reported relative to a particular sample point * in the past. This function provides those sample points. */ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) { return errseq_sample(&mapping->wb_err); } /** * file_sample_sb_err - sample the current errseq_t to test for later errors * @file: file pointer to be sampled * * Grab the most current superblock-level errseq_t value for the given * struct file. */ static inline errseq_t file_sample_sb_err(struct file *file) { return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); } extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags); /* * Sync the bytes written if this was a synchronous write. Expect ki_pos * to already be updated for the write, and will return either the amount * of bytes passed in, or an error if syncing the file failed. */ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) { if (iocb->ki_flags & IOCB_DSYNC) { int ret = vfs_fsync_range(iocb->ki_filp, iocb->ki_pos - count, iocb->ki_pos - 1, (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; } return count; } extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK extern int bmap(struct inode *inode, sector_t *block); #else static inline int bmap(struct inode *inode, sector_t *block) { return -EINVAL; } #endif extern int notify_change(struct dentry *, struct iattr *, struct inode **); extern int inode_permission(struct inode *, int); extern int generic_permission(struct inode *, int); static inline int file_permission(struct file *file, int mask) { return inode_permission(file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { return inode_permission(d_inode(path->dentry), mask); } extern int __check_sticky(struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) { return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) { return (inode->i_mode ^ mode) & S_IFMT; } static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_start_write_trylock(file_inode(file)->i_sb); } static inline void file_end_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; __sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE); } /* * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. * This is used for regular files. * We cannot support write (and maybe mmap read-write shared) accesses and * MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode * can have the following values: * 0: no writers, no VM_DENYWRITE mappings * < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist * > 0: (i_writecount) users are writing to the file. * * Normally we operate on that counter with atomic_{inc,dec} and it's safe * except for the cases where we don't hold i_writecount yet. Then we need to * use {get,deny}_write_access() - these functions check the sign and refuse * to do the change if sign is wrong. */ static inline int get_write_access(struct inode *inode) { return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline int deny_write_access(struct file *file) { struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); } static inline void allow_write_access(struct file *file) { if (file) atomic_inc(&file_inode(file)->i_writecount); } static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; } #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) static inline void i_readcount_dec(struct inode *inode) { BUG_ON(!atomic_read(&inode->i_readcount)); atomic_dec(&inode->i_readcount); } static inline void i_readcount_inc(struct inode *inode) { atomic_inc(&inode->i_readcount); } #else static inline void i_readcount_dec(struct inode *inode) { return; } static inline void i_readcount_inc(struct inode *inode) { return; } #endif extern int do_pipe_flags(int *, int); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(const struct path *, const struct path *); extern char *file_path(struct file *, char *, int); #include <linux/err.h> /* needed for stackable file system support */ extern loff_t default_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence); extern int inode_init_always(struct super_block *, struct inode *); extern void inode_init_once(struct inode *); extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern int generic_delete_inode(struct inode *inode); static inline int generic_drop_inode(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); extern struct inode *find_inode_nowait(struct super_block *, unsigned long, int (*match)(struct inode *, unsigned long, void *), void *data); extern struct inode *find_inode_rcu(struct super_block *, unsigned long, int (*)(struct inode *, void *), void *); extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void lockdep_annotate_inode_mutex_key(struct inode *inode); #else static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); /* * Userspace may rely on the the inode number being non-zero. For example, glibc * simply ignores files with zero i_ino in unlink() and other places. * * As an additional complication, if userspace was compiled with * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the * lower 32 bits, so we need to check that those aren't zero explicitly. With * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but * better safe than sorry. */ static inline bool is_zero_ino(ino_t ino) { return (u32)ino == 0; } extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct inode *); extern int file_remove_privs(struct file *); extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } extern void __remove_inode_hash(struct inode *); static inline void remove_inode_hash(struct inode *inode) { if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode); } extern void inode_sb_list_add(struct inode *inode); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); extern ssize_t generic_file_buffered_read(struct kiocb *iocb, struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter); ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); /* fs/block_dev.c */ extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from); extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync); extern void block_sync_page(struct page *page); /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, struct file *out, loff_t *, size_t len, unsigned int flags); extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, loff_t *opos, size_t len, unsigned int flags); extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); extern loff_t no_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, loff_t file_offset); enum { /* need locking between buffered and direct access */ DIO_LOCKING = 0x01, /* filesystem does not support filling holes */ DIO_SKIP_HOLES = 0x02, }; ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct iov_iter *iter, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif void inode_dio_wait(struct inode *inode); /* * inode_dio_begin - signal start of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_begin(struct inode *inode) { atomic_inc(&inode->i_dio_count); } /* * inode_dio_end - signal finish of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); } /* * Warn about a page cache invalidation failure diring a direct I/O write. */ void dio_warn_stale_pagecache(struct file *filp); extern void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask); extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) extern int readlink_copy(char __user *, int, const char *); extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link_raw(struct dentry *, struct inode *, struct delayed_call *); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); extern int __page_symlink(struct inode *inode, const char *symname, int len, int nofs); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); extern void generic_fillattr(struct inode *, struct kstat *); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); static inline loff_t __inode_get_bytes(struct inode *inode) { return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; } loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); const char *simple_get_link(struct dentry *, struct inode *, struct delayed_call *); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags); int vfs_fstat(int fd, struct kstat *stat); static inline int vfs_stat(const char __user *filename, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, filename, stat, 0); } static inline int vfs_lstat(const char __user *name, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW); } extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); extern struct super_block *get_super_thawed(struct block_device *); extern struct super_block *get_super_exclusive_thawed(struct block_device *bdev); extern struct super_block *get_active_super(struct block_device *bdev); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*)(struct super_block *, void *), void *); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); extern int simple_setattr(struct dentry *, struct iattr *); extern int simple_getattr(const struct path *, struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern int noop_set_page_dirty(struct page *page); extern void noop_invalidatepage(struct page *page, unsigned int offset, unsigned int length); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); extern int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); extern int simple_nosetlease(struct file *, long, struct file_lock **, void **); extern const struct dentry_operations simple_dentry_operations; extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; extern void make_empty_dir_inode(struct inode *inode); extern bool is_empty_dir_inode(struct inode *inode); struct tree_descr { const char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, unsigned long, const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); extern int __generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); #ifdef CONFIG_UNICODE extern int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str); extern int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name); #endif #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, struct page *, struct page *, enum migrate_mode); extern int buffer_migrate_page_norefs(struct address_space *, struct page *, struct page *, enum migrate_mode); #else #define buffer_migrate_page NULL #define buffer_migrate_page_norefs NULL #endif extern int setattr_prepare(struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); static inline bool vma_is_dax(const struct vm_area_struct *vma) { return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); } static inline bool vma_is_fsdax(struct vm_area_struct *vma) { struct inode *inode; if (!vma->vm_file) return false; if (!vma_is_dax(vma)) return false; inode = file_inode(vma->vm_file); if (S_ISCHR(inode->i_mode)) return false; /* device-dax */ return true; } static inline int iocb_flags(struct file *file) { int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; if ((file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host)) res |= IOCB_DSYNC; if (file->f_flags & __O_SYNC) res |= IOCB_SYNC; return res; } static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) { int kiocb_flags = 0; /* make sure there's no overlap between RWF and private IOCB flags */ BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD); if (!flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; kiocb_flags |= IOCB_NOIO; } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; ki->ki_flags |= kiocb_flags; return 0; } static inline ino_t parent_ino(struct dentry *dentry) { ino_t res; /* * Don't strictly need d_lock here? If the parent ino could change * then surely we'd have a deeper race in the caller? */ spin_lock(&dentry->d_lock); res = dentry->d_parent->d_inode->i_ino; spin_unlock(&dentry->d_lock); return res; } /* Transaction based IO helpers */ /* * An argresp is stored in an allocated page and holds the * size of the argument or response, along with its content */ struct simple_transaction_argresp { ssize_t size; char data[]; }; #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) char *simple_transaction_get(struct file *file, const char __user *buf, size_t size); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos); int simple_transaction_release(struct inode *inode, struct file *file); void simple_transaction_set(struct file *file, size_t n); /* * simple attribute files * * These attributes behave similar to those in sysfs: * * Writing to an attribute immediately sets a value, an open file can be * written to multiple times. * * Reading from an attribute creates a buffer from the value that might get * read with multiple read calls. When the attribute has been read * completely, no further read calls are possible until the file is opened * again. * * All attributes contain a text representation of a numeric value * that are accessed with the get() and set() functions. */ #define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \ static int __fops ## _open(struct inode *inode, struct file *file) \ { \ __simple_attr_check_format(__fmt, 0ull); \ return simple_attr_open(inode, file, __get, __set, __fmt); \ } \ static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = simple_attr_read, \ .write = (__is_signed) ? simple_attr_write_signed : simple_attr_write, \ .llseek = generic_file_llseek, \ } #define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false) #define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true) static inline __printf(1, 2) void __simple_attr_check_format(const char *fmt, ...) { /* don't do anything, just let the compiler check the arguments; */ } int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt); int simple_attr_release(struct inode *inode, struct file *file); ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; int proc_nr_files(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_nr_inodes(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); #define __FMODE_EXEC ((__force int) FMODE_EXEC) #define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \ (flag & __FMODE_NONOTIFY))) static inline bool is_sxid(umode_t mode) { return mode & (S_ISUID | S_ISGID); } static inline int check_sticky(struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; return __check_sticky(dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) { if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } static inline bool is_root_inode(struct inode *inode) { return inode == inode->i_sb->s_root->d_inode; } static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { return ctx->actor(ctx, name, namelen, ctx->pos, ino, type) == 0; } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, ".", 1, ctx->pos, file->f_path.dentry->d_inode->i_ino, DT_DIR) == 0; } static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, parent_ino(file->f_path.dentry), DT_DIR) == 0; } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) return false; ctx->pos = 1; } if (ctx->pos == 1) { if (!dir_emit_dotdot(file, ctx)) return false; ctx->pos = 2; } return true; } static inline bool dir_relax(struct inode *inode) { inode_unlock(inode); inode_lock(inode); return !IS_DEADDIR(inode); } static inline bool dir_relax_shared(struct inode *inode) { inode_unlock_shared(inode); inode_lock_shared(inode); return !IS_DEADDIR(inode); } extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); /* mm/fadvise.c */ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice); extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags, unsigned int flags); int vfs_ioc_fssetxattr_check(struct inode *inode, const struct fsxattr *old_fa, struct fsxattr *fa); static inline void simple_fill_fsxattr(struct fsxattr *fa, __u32 xflags) { memset(fa, 0, sizeof(*fa)); fa->fsx_xflags = xflags; } /* * Flush file data before changing attributes. Caller must hold any locks * required to prevent further writes to this file until we're done setting * flags. */ static inline int inode_drain_writes(struct inode *inode) { inode_dio_wait(inode); return filemap_write_and_wait(inode->i_mapping); } #endif /* _LINUX_FS_H */ |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * NSA Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux security data structures for kernel objects. * * Author(s): Stephen Smalley, <sds@tycho.nsa.gov> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> * Copyright (C) 2016 Mellanox Technologies */ #ifndef _SELINUX_OBJSEC_H_ #define _SELINUX_OBJSEC_H_ #include <linux/list.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/binfmts.h> #include <linux/in.h> #include <linux/spinlock.h> #include <linux/lsm_hooks.h> #include <linux/msg.h> #include <net/net_namespace.h> #include "flask.h" #include "avc.h" struct task_security_struct { u32 osid; /* SID prior to last execve */ u32 sid; /* current SID */ u32 exec_sid; /* exec SID */ u32 create_sid; /* fscreate SID */ u32 keycreate_sid; /* keycreate SID */ u32 sockcreate_sid; /* fscreate SID */ } __randomize_layout; enum label_initialized { LABEL_INVALID, /* invalid or not initialized */ LABEL_INITIALIZED, /* initialized */ LABEL_PENDING }; struct inode_security_struct { struct inode *inode; /* back pointer to inode object */ struct list_head list; /* list of inode_security_struct */ u32 task_sid; /* SID of creating task */ u32 sid; /* SID of this object */ u16 sclass; /* security class of this object */ unsigned char initialized; /* initialization flag */ spinlock_t lock; }; struct file_security_struct { u32 sid; /* SID of open file description */ u32 fown_sid; /* SID of file owner (for SIGIO) */ u32 isid; /* SID of inode at the time of file open */ u32 pseqno; /* Policy seqno at the time of file open */ }; struct superblock_security_struct { struct super_block *sb; /* back pointer to sb object */ u32 sid; /* SID of file system superblock */ u32 def_sid; /* default SID for labeling */ u32 mntpoint_sid; /* SECURITY_FS_USE_MNTPOINT context for files */ unsigned short behavior; /* labeling behavior */ unsigned short flags; /* which mount options were specified */ struct mutex lock; struct list_head isec_head; spinlock_t isec_lock; }; struct msg_security_struct { u32 sid; /* SID of message */ }; struct ipc_security_struct { u16 sclass; /* security class of this object */ u32 sid; /* SID of IPC resource */ }; struct netif_security_struct { struct net *ns; /* network namespace */ int ifindex; /* device index */ u32 sid; /* SID for this interface */ }; struct netnode_security_struct { union { __be32 ipv4; /* IPv4 node address */ struct in6_addr ipv6; /* IPv6 node address */ } addr; u32 sid; /* SID for this node */ u16 family; /* address family */ }; struct netport_security_struct { u32 sid; /* SID for this node */ u16 port; /* port number */ u8 protocol; /* transport protocol */ }; struct sk_security_struct { #ifdef CONFIG_NETLABEL enum { /* NetLabel state */ NLBL_UNSET = 0, NLBL_REQUIRE, NLBL_LABELED, NLBL_REQSKB, NLBL_CONNLABELED, } nlbl_state; struct netlbl_lsm_secattr *nlbl_secattr; /* NetLabel sec attributes */ #endif u32 sid; /* SID of this object */ u32 peer_sid; /* SID of peer */ u16 sclass; /* sock security class */ enum { /* SCTP association state */ SCTP_ASSOC_UNSET = 0, SCTP_ASSOC_SET, } sctp_assoc_state; }; struct tun_security_struct { u32 sid; /* SID for the tun device sockets */ }; struct key_security_struct { u32 sid; /* SID of key */ }; struct ib_security_struct { u32 sid; /* SID of the queue pair or MAD agent */ }; struct pkey_security_struct { u64 subnet_prefix; /* Port subnet prefix */ u16 pkey; /* PKey number */ u32 sid; /* SID of pkey */ }; struct bpf_security_struct { u32 sid; /* SID of bpf obj creator */ }; struct perf_event_security_struct { u32 sid; /* SID of perf_event obj creator */ }; extern struct lsm_blob_sizes selinux_blob_sizes; static inline struct task_security_struct *selinux_cred(const struct cred *cred) { return cred->security + selinux_blob_sizes.lbs_cred; } static inline struct file_security_struct *selinux_file(const struct file *file) { return file->f_security + selinux_blob_sizes.lbs_file; } static inline struct inode_security_struct *selinux_inode( const struct inode *inode) { if (unlikely(!inode->i_security)) return NULL; return inode->i_security + selinux_blob_sizes.lbs_inode; } static inline struct msg_security_struct *selinux_msg_msg( const struct msg_msg *msg_msg) { return msg_msg->security + selinux_blob_sizes.lbs_msg_msg; } static inline struct ipc_security_struct *selinux_ipc( const struct kern_ipc_perm *ipc) { return ipc->security + selinux_blob_sizes.lbs_ipc; } /* * get the subjective security ID of the current task */ static inline u32 current_sid(void) { const struct task_security_struct *tsec = selinux_cred(current_cred()); return tsec->sid; } #endif /* _SELINUX_OBJSEC_H_ */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 | /* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: common low-level thread information accessors * * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds */ #ifndef _LINUX_THREAD_INFO_H #define _LINUX_THREAD_INFO_H #include <linux/types.h> #include <linux/bug.h> #include <linux/restart_block.h> #include <linux/errno.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels, * including <asm/current.h> can cause a circular dependency on some platforms. */ #include <asm/current.h> #define current_thread_info() ((struct thread_info *)current) #endif #include <linux/bitops.h> /* * For per-arch arch_within_stack_frames() implementations, defined in * asm/thread_info.h. */ enum { BAD_STACK = -1, NOT_STACK = 0, GOOD_FRAME, GOOD_STACK, }; #include <asm/thread_info.h> #ifdef __KERNEL__ #ifndef arch_set_restart_data #define arch_set_restart_data(restart) do { } while (0) #endif static inline long set_restart_fn(struct restart_block *restart, long (*fn)(struct restart_block *)) { restart->fn = fn; arch_set_restart_data(restart); return -ERESTART_RESTARTBLOCK; } #ifndef THREAD_ALIGN #define THREAD_ALIGN THREAD_SIZE #endif #define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions */ static inline void set_ti_thread_flag(struct thread_info *ti, int flag) { set_bit(flag, (unsigned long *)&ti->flags); } static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) { clear_bit(flag, (unsigned long *)&ti->flags); } static inline void update_ti_thread_flag(struct thread_info *ti, int flag, bool value) { if (value) set_ti_thread_flag(ti, flag); else clear_ti_thread_flag(ti, flag); } static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_ti_thread_flag(struct thread_info *ti, int flag) { return test_bit(flag, (unsigned long *)&ti->flags); } #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) #define update_thread_flag(flag, value) \ update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) { return 0; } #endif #ifdef CONFIG_HARDENED_USERCOPY extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); static __always_inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { if (!__builtin_constant_p(n)) __check_object_size(ptr, n, to_user); } #else static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { } #endif /* CONFIG_HARDENED_USERCOPY */ extern void __compiletime_error("copy source size is too small") __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); static inline void copy_overflow(int size, unsigned long count) { WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); } static __always_inline __must_check bool check_copy_size(const void *addr, size_t bytes, bool is_source) { int sz = __compiletime_object_size(addr); if (unlikely(sz >= 0 && sz < bytes)) { if (!__builtin_constant_p(bytes)) copy_overflow(sz, bytes); else if (is_source) __bad_copy_from(); else __bad_copy_to(); return false; } if (WARN_ON_ONCE(bytes > INT_MAX)) return false; check_object_size(addr, bytes, is_source); return true; } #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Directory notifications for Linux. * * Copyright (C) 2000,2001,2002 Stephen Rothwell * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * dnotify was largly rewritten to use the new fsnotify infrastructure */ #include <linux/fs.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/dnotify.h> #include <linux/init.h> #include <linux/security.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/fdtable.h> #include <linux/fsnotify_backend.h> int dir_notify_enable __read_mostly = 1; static struct kmem_cache *dnotify_struct_cache __read_mostly; static struct kmem_cache *dnotify_mark_cache __read_mostly; static struct fsnotify_group *dnotify_group __read_mostly; /* * dnotify will attach one of these to each inode (i_fsnotify_marks) which * is being watched by dnotify. If multiple userspace applications are watching * the same directory with dnotify their information is chained in dn */ struct dnotify_mark { struct fsnotify_mark fsn_mark; struct dnotify_struct *dn; }; /* * When a process starts or stops watching an inode the set of events which * dnotify cares about for that inode may change. This function runs the * list of everything receiving dnotify events about this directory and calculates * the set of all those events. After it updates what dnotify is interested in * it calls the fsnotify function so it can update the set of all events relevant * to this inode. */ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark) { __u32 new_mask = 0; struct dnotify_struct *dn; struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); assert_spin_locked(&fsn_mark->lock); for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next) new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT); if (fsn_mark->mask == new_mask) return; fsn_mark->mask = new_mask; fsnotify_recalc_mask(fsn_mark->connector); } /* * Mains fsnotify call where events are delivered to dnotify. * Find the dnotify mark on the relevant inode, run the list of dnotify structs * on that mark and determine which of them has expressed interest in receiving * events of this type. When found send the correct process and signal and * destroy the dnotify struct if it was not registered to receive multiple * events. */ static int dnotify_handle_event(struct fsnotify_mark *inode_mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct fown_struct *fown; __u32 test_mask = mask & ~FS_EVENT_ON_CHILD; /* not a dir, dnotify doesn't care */ if (!dir && !(mask & FS_ISDIR)) return 0; dn_mark = container_of(inode_mark, struct dnotify_mark, fsn_mark); spin_lock(&inode_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_mask & test_mask) == 0) { prev = &dn->dn_next; continue; } fown = &dn->dn_filp->f_owner; send_sigio(fown, dn->dn_fd, POLL_MSG); if (dn->dn_mask & FS_DN_MULTISHOT) prev = &dn->dn_next; else { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(inode_mark); } } spin_unlock(&inode_mark->lock); return 0; } static void dnotify_free_mark(struct fsnotify_mark *fsn_mark) { struct dnotify_mark *dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); BUG_ON(dn_mark->dn); kmem_cache_free(dnotify_mark_cache, dn_mark); } static const struct fsnotify_ops dnotify_fsnotify_ops = { .handle_inode_event = dnotify_handle_event, .free_mark = dnotify_free_mark, }; /* * Called every time a file is closed. Looks first for a dnotify mark on the * inode. If one is found run all of the ->dn structures attached to that * mark for one relevant to this process closing the file and remove that * dnotify_struct. If that was the last dnotify_struct also remove the * fsnotify_mark. */ void dnotify_flush(struct file *filp, fl_owner_t id) { struct fsnotify_mark *fsn_mark; struct dnotify_mark *dn_mark; struct dnotify_struct *dn; struct dnotify_struct **prev; struct inode *inode; bool free = false; inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) return; fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group); if (!fsn_mark) return; dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); fsnotify_group_lock(dnotify_group); spin_lock(&fsn_mark->lock); prev = &dn_mark->dn; while ((dn = *prev) != NULL) { if ((dn->dn_owner == id) && (dn->dn_filp == filp)) { *prev = dn->dn_next; kmem_cache_free(dnotify_struct_cache, dn); dnotify_recalc_inode_mask(fsn_mark); break; } prev = &dn->dn_next; } spin_unlock(&fsn_mark->lock); /* nothing else could have found us thanks to the dnotify_groups mark_mutex */ if (dn_mark->dn == NULL) { fsnotify_detach_mark(fsn_mark); free = true; } fsnotify_group_unlock(dnotify_group); if (free) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); } /* this conversion is done only at watch creation */ static __u32 convert_arg(unsigned long arg) { __u32 new_mask = FS_EVENT_ON_CHILD; if (arg & DN_MULTISHOT) new_mask |= FS_DN_MULTISHOT; if (arg & DN_DELETE) new_mask |= (FS_DELETE | FS_MOVED_FROM); if (arg & DN_MODIFY) new_mask |= FS_MODIFY; if (arg & DN_ACCESS) new_mask |= FS_ACCESS; if (arg & DN_ATTRIB) new_mask |= FS_ATTRIB; if (arg & DN_RENAME) new_mask |= FS_RENAME; if (arg & DN_CREATE) new_mask |= (FS_CREATE | FS_MOVED_TO); return new_mask; } /* * If multiple processes watch the same inode with dnotify there is only one * dnotify mark in inode->i_fsnotify_marks but we chain a dnotify_struct * onto that mark. This function either attaches the new dnotify_struct onto * that list, or it |= the mask onto an existing dnofiy_struct. */ static int attach_dn(struct dnotify_struct *dn, struct dnotify_mark *dn_mark, fl_owner_t id, int fd, struct file *filp, __u32 mask) { struct dnotify_struct *odn; odn = dn_mark->dn; while (odn != NULL) { /* adding more events to existing dnofiy_struct? */ if ((odn->dn_owner == id) && (odn->dn_filp == filp)) { odn->dn_fd = fd; odn->dn_mask |= mask; return -EEXIST; } odn = odn->dn_next; } dn->dn_mask = mask; dn->dn_fd = fd; dn->dn_filp = filp; dn->dn_owner = id; dn->dn_next = dn_mark->dn; dn_mark->dn = dn; return 0; } /* * When a process calls fcntl to attach a dnotify watch to a directory it ends * up here. Allocate both a mark for fsnotify to add and a dnotify_struct to be * attached to the fsnotify_mark. */ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg) { struct dnotify_mark *new_dn_mark, *dn_mark; struct fsnotify_mark *new_fsn_mark, *fsn_mark; struct dnotify_struct *dn; struct inode *inode; fl_owner_t id = current->files; struct file *f; int destroy = 0, error = 0; __u32 mask; /* we use these to tell if we need to kfree */ new_fsn_mark = NULL; dn = NULL; if (!dir_notify_enable) { error = -EINVAL; goto out_err; } /* a 0 mask means we are explicitly removing the watch */ if ((arg & ~DN_MULTISHOT) == 0) { dnotify_flush(filp, id); error = 0; goto out_err; } /* dnotify only works on directories */ inode = file_inode(filp); if (!S_ISDIR(inode->i_mode)) { error = -ENOTDIR; goto out_err; } /* * convert the userspace DN_* "arg" to the internal FS_* * defined in fsnotify */ mask = convert_arg(arg); error = security_path_notify(&filp->f_path, mask, FSNOTIFY_OBJ_TYPE_INODE); if (error) goto out_err; /* expect most fcntl to add new rather than augment old */ dn = kmem_cache_alloc(dnotify_struct_cache, GFP_KERNEL); if (!dn) { error = -ENOMEM; goto out_err; } /* new fsnotify mark, we expect most fcntl calls to add a new mark */ new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL); if (!new_dn_mark) { error = -ENOMEM; goto out_err; } /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); new_fsn_mark->mask = mask; new_dn_mark->dn = NULL; /* this is needed to prevent the fcntl/close race described below */ fsnotify_group_lock(dnotify_group); /* add the new_fsn_mark or find an old one. */ fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group); if (fsn_mark) { dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark); spin_lock(&fsn_mark->lock); } else { error = fsnotify_add_inode_mark_locked(new_fsn_mark, inode, 0); if (error) { fsnotify_group_unlock(dnotify_group); goto out_err; } spin_lock(&new_fsn_mark->lock); fsn_mark = new_fsn_mark; dn_mark = new_dn_mark; /* we used new_fsn_mark, so don't free it */ new_fsn_mark = NULL; } rcu_read_lock(); f = lookup_fd_rcu(fd); rcu_read_unlock(); /* if (f != filp) means that we lost a race and another task/thread * actually closed the fd we are still playing with before we grabbed * the dnotify_groups mark_mutex and fsn_mark->lock. Since closing the * fd is the only time we clean up the marks we need to get our mark * off the list. */ if (f != filp) { /* if we added ourselves, shoot ourselves, it's possible that * the flush actually did shoot this fsn_mark. That's fine too * since multiple calls to destroy_mark is perfectly safe, if * we found a dn_mark already attached to the inode, just sod * off silently as the flush at close time dealt with it. */ if (dn_mark == new_dn_mark) destroy = 1; error = 0; goto out; } __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); error = attach_dn(dn, dn_mark, id, fd, filp, mask); /* !error means that we attached the dn to the dn_mark, so don't free it */ if (!error) dn = NULL; /* -EEXIST means that we didn't add this new dn and used an old one. * that isn't an error (and the unused dn should be freed) */ else if (error == -EEXIST) error = 0; dnotify_recalc_inode_mask(fsn_mark); out: spin_unlock(&fsn_mark->lock); if (destroy) fsnotify_detach_mark(fsn_mark); fsnotify_group_unlock(dnotify_group); if (destroy) fsnotify_free_mark(fsn_mark); fsnotify_put_mark(fsn_mark); out_err: if (new_fsn_mark) fsnotify_put_mark(new_fsn_mark); if (dn) kmem_cache_free(dnotify_struct_cache, dn); return error; } static int __init dnotify_init(void) { dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC|SLAB_ACCOUNT); dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT); dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops, FSNOTIFY_GROUP_NOFS); if (IS_ERR(dnotify_group)) panic("unable to allocate fsnotify group for dnotify\n"); return 0; } module_init(dnotify_init) |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_ERR_H #define _LINUX_ERR_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/errno.h> /* * Kernel pointers have redundant information, so we can use a * scheme where we can return either an error code or a normal * pointer with the same return value. * * This should be a per-architecture thing, to allow different * error and pointer decisions. */ #define MAX_ERRNO 4095 #ifndef __ASSEMBLY__ #define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO) static inline void * __must_check ERR_PTR(long error) { return (void *) error; } static inline long __must_check PTR_ERR(__force const void *ptr) { return (long) ptr; } static inline bool __must_check IS_ERR(__force const void *ptr) { return IS_ERR_VALUE((unsigned long)ptr); } static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) { return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); } /** * ERR_CAST - Explicitly cast an error-valued pointer to another pointer type * @ptr: The pointer to cast. * * Explicitly cast an error-valued pointer to another pointer type in such a * way as to make it clear that's what's going on. */ static inline void * __must_check ERR_CAST(__force const void *ptr) { /* cast away the const */ return (void *) ptr; } static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr) { if (IS_ERR(ptr)) return PTR_ERR(ptr); else return 0; } #endif #endif /* _LINUX_ERR_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Variant of atomic_t specialized for reference counts. * * The interface matches the atomic_t interface (to aid in porting) but only * provides the few functions one should use for reference counting. * * Saturation semantics * ==================== * * refcount_t differs from atomic_t in that the counter saturates at * REFCOUNT_SATURATED and will not move once there. This avoids wrapping the * counter and causing 'spurious' use-after-free issues. In order to avoid the * cost associated with introducing cmpxchg() loops into all of the saturating * operations, we temporarily allow the counter to take on an unchecked value * and then explicitly set it to REFCOUNT_SATURATED on detecting that underflow * or overflow has occurred. Although this is racy when multiple threads * access the refcount concurrently, by placing REFCOUNT_SATURATED roughly * equidistant from 0 and INT_MAX we minimise the scope for error: * * INT_MAX REFCOUNT_SATURATED UINT_MAX * 0 (0x7fff_ffff) (0xc000_0000) (0xffff_ffff) * +--------------------------------+----------------+----------------+ * <---------- bad value! ----------> * * (in a signed view of the world, the "bad value" range corresponds to * a negative counter value). * * As an example, consider a refcount_inc() operation that causes the counter * to overflow: * * int old = atomic_fetch_add_relaxed(r); * // old is INT_MAX, refcount now INT_MIN (0x8000_0000) * if (old < 0) * atomic_set(r, REFCOUNT_SATURATED); * * If another thread also performs a refcount_inc() operation between the two * atomic operations, then the count will continue to edge closer to 0. If it * reaches a value of 1 before /any/ of the threads reset it to the saturated * value, then a concurrent refcount_dec_and_test() may erroneously free the * underlying object. * Linux limits the maximum number of tasks to PID_MAX_LIMIT, which is currently * 0x400000 (and can't easily be raised in the future beyond FUTEX_TID_MASK). * With the current PID limit, if no batched refcounting operations are used and * the attacker can't repeatedly trigger kernel oopses in the middle of refcount * operations, this makes it impossible for a saturated refcount to leave the * saturation range, even if it is possible for multiple uses of the same * refcount to nest in the context of a single task: * * (UINT_MAX+1-REFCOUNT_SATURATED) / PID_MAX_LIMIT = * 0x40000000 / 0x400000 = 0x100 = 256 * * If hundreds of references are added/removed with a single refcounting * operation, it may potentially be possible to leave the saturation range; but * given the precise timing details involved with the round-robin scheduling of * each thread manipulating the refcount and the need to hit the race multiple * times in succession, there doesn't appear to be a practical avenue of attack * even if using refcount_add() operations with larger increments. * * Memory ordering * =============== * * Memory ordering rules are slightly relaxed wrt regular atomic_t functions * and provide only what is strictly required for refcounts. * * The increments are fully relaxed; these will not provide ordering. The * rationale is that whatever is used to obtain the object we're increasing the * reference count on will provide the ordering. For locked data structures, * its the lock acquire, for RCU/lockless data structures its the dependent * load. * * Do note that inc_not_zero() provides a control dependency which will order * future stores against the inc, this ensures we'll never modify the object * if we did not in fact acquire a reference. * * The decrements will provide release order, such that all the prior loads and * stores will be issued before, it also provides a control dependency, which * will order us against the subsequent free(). * * The control dependency is against the load of the cmpxchg (ll/sc) that * succeeded. This means the stores aren't fully ordered, but this is fine * because the 1->0 transition indicates no concurrency. * * Note that the allocator is responsible for ordering things between free() * and alloc(). * * The decrements dec_and_test() and sub_and_test() also provide acquire * ordering on success. * */ #ifndef _LINUX_REFCOUNT_H #define _LINUX_REFCOUNT_H #include <linux/atomic.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/limits.h> #include <linux/spinlock_types.h> struct mutex; /** * struct refcount_t - variant of atomic_t specialized for reference counts * @refs: atomic_t counter field * * The counter saturates at REFCOUNT_SATURATED and will not move once * there. This avoids wrapping the counter and causing 'spurious' * use-after-free bugs. */ typedef struct refcount_struct { atomic_t refs; } refcount_t; #define REFCOUNT_INIT(n) { .refs = ATOMIC_INIT(n), } #define REFCOUNT_MAX INT_MAX #define REFCOUNT_SATURATED (INT_MIN / 2) enum refcount_saturation_type { REFCOUNT_ADD_NOT_ZERO_OVF, REFCOUNT_ADD_OVF, REFCOUNT_ADD_UAF, REFCOUNT_SUB_UAF, REFCOUNT_DEC_LEAK, }; void refcount_warn_saturate(refcount_t *r, enum refcount_saturation_type t); /** * refcount_set - set a refcount's value * @r: the refcount * @n: value to which the refcount will be set */ static inline void refcount_set(refcount_t *r, int n) { atomic_set(&r->refs, n); } /** * refcount_read - get a refcount's value * @r: the refcount * * Return: the refcount's value */ static inline unsigned int refcount_read(const refcount_t *r) { return atomic_read(&r->refs); } static inline __must_check bool __refcount_add_not_zero(int i, refcount_t *r, int *oldp) { int old = refcount_read(r); do { if (!old) break; } while (!atomic_try_cmpxchg_relaxed(&r->refs, &old, old + i)); if (oldp) *oldp = old; if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_NOT_ZERO_OVF); return old; } /** * refcount_add_not_zero - add a value to a refcount unless it is 0 * @i: the value to add to the refcount * @r: the refcount * * Will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. * * Return: false if the passed refcount is 0, true otherwise */ static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r) { return __refcount_add_not_zero(i, r, NULL); } static inline void __refcount_add(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_add_relaxed(i, &r->refs); if (oldp) *oldp = old; if (unlikely(!old)) refcount_warn_saturate(r, REFCOUNT_ADD_UAF); else if (unlikely(old < 0 || old + i < 0)) refcount_warn_saturate(r, REFCOUNT_ADD_OVF); } /** * refcount_add - add a value to a refcount * @i: the value to add to the refcount * @r: the refcount * * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_inc(), or one of its variants, should instead be used to * increment a reference count. */ static inline void refcount_add(int i, refcount_t *r) { __refcount_add(i, r, NULL); } static inline __must_check bool __refcount_inc_not_zero(refcount_t *r, int *oldp) { return __refcount_add_not_zero(1, r, oldp); } /** * refcount_inc_not_zero - increment a refcount unless it is 0 * @r: the refcount to increment * * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED * and WARN. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See the comment on top. * * Return: true if the increment was successful, false otherwise */ static inline __must_check bool refcount_inc_not_zero(refcount_t *r) { return __refcount_inc_not_zero(r, NULL); } static inline void __refcount_inc(refcount_t *r, int *oldp) { __refcount_add(1, r, oldp); } /** * refcount_inc - increment a refcount * @r: the refcount to increment * * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN. * * Provides no memory ordering, it is assumed the caller already has a * reference on the object. * * Will WARN if the refcount is 0, as this represents a possible use-after-free * condition. */ static inline void refcount_inc(refcount_t *r) { __refcount_inc(r, NULL); } static inline __must_check bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(i, &r->refs); if (oldp) *oldp = old; if (old == i) { smp_acquire__after_ctrl_dep(); return true; } if (unlikely(old < 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; } /** * refcount_sub_and_test - subtract from a refcount and test if it is 0 * @i: amount to subtract from the refcount * @r: the refcount * * Similar to atomic_dec_and_test(), but it will WARN, return false and * ultimately leak on underflow and will fail to decrement when saturated * at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these * cases, refcount_dec(), or one of its variants, should instead be used to * decrement a reference count. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r) { return __refcount_sub_and_test(i, r, NULL); } static inline __must_check bool __refcount_dec_and_test(refcount_t *r, int *oldp) { return __refcount_sub_and_test(1, r, oldp); } /** * refcount_dec_and_test - decrement a refcount and test if it is 0 * @r: the refcount * * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to * decrement when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Return: true if the resulting refcount is 0, false otherwise */ static inline __must_check bool refcount_dec_and_test(refcount_t *r) { return __refcount_dec_and_test(r, NULL); } static inline void __refcount_dec(refcount_t *r, int *oldp) { int old = atomic_fetch_sub_release(1, &r->refs); if (oldp) *oldp = old; if (unlikely(old <= 1)) refcount_warn_saturate(r, REFCOUNT_DEC_LEAK); } /** * refcount_dec - decrement a refcount * @r: the refcount * * Similar to atomic_dec(), it will WARN on underflow and fail to decrement * when saturated at REFCOUNT_SATURATED. * * Provides release memory ordering, such that prior loads and stores are done * before. */ static inline void refcount_dec(refcount_t *r) { __refcount_dec(r, NULL); } extern __must_check bool refcount_dec_if_one(refcount_t *r); extern __must_check bool refcount_dec_not_one(refcount_t *r); extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock); extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock); extern __must_check bool refcount_dec_and_lock_irqsave(refcount_t *r, spinlock_t *lock, unsigned long *flags); #endif /* _LINUX_REFCOUNT_H */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 | /* SPDX-License-Identifier: GPL-2.0 */ /* * A security context is a set of security attributes * associated with each subject and object controlled * by the security policy. Security contexts are * externally represented as variable-length strings * that can be interpreted by a user or application * with an understanding of the security policy. * Internally, the security server uses a simple * structure. This structure is private to the * security server and can be changed without affecting * clients of the security server. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ #ifndef _SS_CONTEXT_H_ #define _SS_CONTEXT_H_ #include "ebitmap.h" #include "mls_types.h" #include "security.h" /* * A security context consists of an authenticated user * identity, a role, a type and a MLS range. */ struct context { u32 user; u32 role; u32 type; u32 len; /* length of string in bytes */ struct mls_range range; char *str; /* string representation if context cannot be mapped. */ }; static inline void mls_context_init(struct context *c) { memset(&c->range, 0, sizeof(c->range)); } static inline int mls_context_cpy(struct context *dst, struct context *src) { int rc; dst->range.level[0].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } /* * Sets both levels in the MLS range of 'dst' to the low level of 'src'. */ static inline int mls_context_cpy_low(struct context *dst, struct context *src) { int rc; dst->range.level[0].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[0].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[0].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } /* * Sets both levels in the MLS range of 'dst' to the high level of 'src'. */ static inline int mls_context_cpy_high(struct context *dst, struct context *src) { int rc; dst->range.level[0].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[1].cat); if (rc) goto out; dst->range.level[1].sens = src->range.level[1].sens; rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat); if (rc) ebitmap_destroy(&dst->range.level[0].cat); out: return rc; } static inline int mls_context_glblub(struct context *dst, struct context *c1, struct context *c2) { struct mls_range *dr = &dst->range, *r1 = &c1->range, *r2 = &c2->range; int rc = 0; if (r1->level[1].sens < r2->level[0].sens || r2->level[1].sens < r1->level[0].sens) /* These ranges have no common sensitivities */ return -EINVAL; /* Take the greatest of the low */ dr->level[0].sens = max(r1->level[0].sens, r2->level[0].sens); /* Take the least of the high */ dr->level[1].sens = min(r1->level[1].sens, r2->level[1].sens); rc = ebitmap_and(&dr->level[0].cat, &r1->level[0].cat, &r2->level[0].cat); if (rc) goto out; rc = ebitmap_and(&dr->level[1].cat, &r1->level[1].cat, &r2->level[1].cat); if (rc) goto out; out: return rc; } static inline int mls_context_cmp(struct context *c1, struct context *c2) { return ((c1->range.level[0].sens == c2->range.level[0].sens) && ebitmap_cmp(&c1->range.level[0].cat, &c2->range.level[0].cat) && (c1->range.level[1].sens == c2->range.level[1].sens) && ebitmap_cmp(&c1->range.level[1].cat, &c2->range.level[1].cat)); } static inline void mls_context_destroy(struct context *c) { ebitmap_destroy(&c->range.level[0].cat); ebitmap_destroy(&c->range.level[1].cat); mls_context_init(c); } static inline void context_init(struct context *c) { memset(c, 0, sizeof(*c)); } static inline int context_cpy(struct context *dst, struct context *src) { int rc; dst->user = src->user; dst->role = src->role; dst->type = src->type; if (src->str) { dst->str = kstrdup(src->str, GFP_ATOMIC); if (!dst->str) return -ENOMEM; dst->len = src->len; } else { dst->str = NULL; dst->len = 0; } rc = mls_context_cpy(dst, src); if (rc) { kfree(dst->str); return rc; } return 0; } static inline void context_destroy(struct context *c) { c->user = c->role = c->type = 0; kfree(c->str); c->str = NULL; c->len = 0; mls_context_destroy(c); } static inline int context_cmp(struct context *c1, struct context *c2) { if (c1->len && c2->len) return (c1->len == c2->len && !strcmp(c1->str, c2->str)); if (c1->len || c2->len) return 0; return ((c1->user == c2->user) && (c1->role == c2->role) && (c1->type == c2->type) && mls_context_cmp(c1, c2)); } u32 context_compute_hash(const struct context *c); #endif /* _SS_CONTEXT_H_ */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 */ #include <asm/fpu/internal.h> #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> #include <asm/traps.h> #include <asm/irq_regs.h> #include <linux/hardirq.h> #include <linux/pkeys.h> #define CREATE_TRACE_POINTS #include <asm/trace/fpu.h> /* * Represents the initial FPU state. It's mostly (but not completely) zeroes, * depending on the FPU hardware format: */ union fpregs_state init_fpstate __read_mostly; /* Track in-kernel FPU usage */ static DEFINE_PER_CPU(bool, in_kernel_fpu); /* * Track which context is using the FPU on the CPU: */ DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); /* * Can we use the FPU in kernel mode with the * whole "kernel_fpu_begin/end()" sequence? */ bool irq_fpu_usable(void) { if (WARN_ON_ONCE(in_nmi())) return false; /* In kernel FPU usage already active? */ if (this_cpu_read(in_kernel_fpu)) return false; /* * When not in NMI or hard interrupt context, FPU can be used in: * * - Task context except from within fpregs_lock()'ed critical * regions. * * - Soft interrupt processing context which cannot happen * while in a fpregs_lock()'ed critical region. */ if (!in_irq()) return true; /* * In hard interrupt context it's safe when soft interrupts * are enabled, which means the interrupt did not hit in * a fpregs_lock()'ed critical region. */ return !softirq_count(); } EXPORT_SYMBOL(irq_fpu_usable); /* * These must be called with preempt disabled. Returns * 'true' if the FPU state is still intact and we can * keep registers active. * * The legacy FNSAVE instruction cleared all FPU state * unconditionally, so registers are essentially destroyed. * Modern FPU state can be kept in registers, if there are * no pending FP exceptions. */ int copy_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { copy_xregs_to_kernel(&fpu->state.xsave); /* * AVX512 state is tracked here because its use is * known to slow the max clock speed of the core. */ if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512) fpu->avx512_timestamp = jiffies; return 1; } if (likely(use_fxsr())) { copy_fxregs_to_kernel(fpu); return 1; } /* * Legacy FPU register saving, FNSAVE always clears FPU registers, * so we have to mark them inactive: */ asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave)); return 0; } EXPORT_SYMBOL(copy_fpregs_to_fpstate); void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); WARN_ON_FPU(!irq_fpu_usable()); WARN_ON_FPU(this_cpu_read(in_kernel_fpu)); this_cpu_write(in_kernel_fpu, true); if (!(current->flags & PF_KTHREAD) && !test_thread_flag(TIF_NEED_FPU_LOAD)) { set_thread_flag(TIF_NEED_FPU_LOAD); /* * Ignore return value -- we don't care if reg state * is clobbered. */ copy_fpregs_to_fpstate(¤t->thread.fpu); } __cpu_invalidate_fpregs_state(); /* Put sane initial values into the control registers. */ if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); this_cpu_write(in_kernel_fpu, false); preempt_enable(); } EXPORT_SYMBOL_GPL(kernel_fpu_end); /* * Save the FPU state (mark it for reload if necessary): * * This only ever gets called for the current task. */ void fpu__save(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); fpregs_lock(); trace_x86_fpu_before_save(fpu); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { if (!copy_fpregs_to_fpstate(fpu)) { copy_kernel_to_fpregs(&fpu->state); } } trace_x86_fpu_after_save(fpu); fpregs_unlock(); } /* * Legacy x87 fpstate state init: */ static inline void fpstate_init_fstate(struct fregs_state *fp) { fp->cwd = 0xffff037fu; fp->swd = 0xffff0000u; fp->twd = 0xffffffffu; fp->fos = 0xffff0000u; } void fpstate_init(union fpregs_state *state) { if (!static_cpu_has(X86_FEATURE_FPU)) { fpstate_init_soft(&state->soft); return; } memset(state, 0, fpu_kernel_xstate_size); if (static_cpu_has(X86_FEATURE_XSAVES)) fpstate_init_xstate(&state->xsave); if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); else fpstate_init_fstate(&state->fsave); } EXPORT_SYMBOL_GPL(fpstate_init); int fpu__copy(struct task_struct *dst, struct task_struct *src) { struct fpu *dst_fpu = &dst->thread.fpu; struct fpu *src_fpu = &src->thread.fpu; dst_fpu->last_cpu = -1; if (!static_cpu_has(X86_FEATURE_FPU)) return 0; WARN_ON_FPU(src_fpu != ¤t->thread.fpu); /* * Don't let 'init optimized' areas of the XSAVE area * leak into the child task: */ memset(&dst_fpu->state.xsave, 0, fpu_kernel_xstate_size); /* * If the FPU registers are not current just memcpy() the state. * Otherwise save current FPU registers directly into the child's FPU * context, without any memory-to-memory copying. * * ( The function 'fails' in the FNSAVE case, which destroys * register contents so we have to load them back. ) */ fpregs_lock(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) memcpy(&dst_fpu->state, &src_fpu->state, fpu_kernel_xstate_size); else if (!copy_fpregs_to_fpstate(dst_fpu)) copy_kernel_to_fpregs(&dst_fpu->state); fpregs_unlock(); set_tsk_thread_flag(dst, TIF_NEED_FPU_LOAD); trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); return 0; } /* * Activate the current task's in-memory FPU context, * if it has not been used before: */ static void fpu__initialize(struct fpu *fpu) { WARN_ON_FPU(fpu != ¤t->thread.fpu); set_thread_flag(TIF_NEED_FPU_LOAD); fpstate_init(&fpu->state); trace_x86_fpu_init_state(fpu); } /* * This function must be called before we read a task's fpstate. * * There's two cases where this gets called: * * - for the current task (when coredumping), in which case we have * to save the latest FPU registers into the fpstate, * * - or it's called for stopped tasks (ptrace), in which case the * registers were already saved by the context-switch code when * the task scheduled out. * * If the task has used the FPU before then save it. */ void fpu__prepare_read(struct fpu *fpu) { if (fpu == ¤t->thread.fpu) fpu__save(fpu); } /* * This function must be called before we write a task's fpstate. * * Invalidate any cached FPU registers. * * After this function call, after registers in the fpstate are * modified and the child task has woken up, the child task will * restore the modified FPU state from the modified context. If we * didn't clear its cached status here then the cached in-registers * state pending on its former CPU could be restored, corrupting * the modifications. */ void fpu__prepare_write(struct fpu *fpu) { /* * Only stopped child tasks can be used to modify the FPU * state in the fpstate buffer: */ WARN_ON_FPU(fpu == ¤t->thread.fpu); /* Invalidate any cached state: */ __fpu_invalidate_fpregs_state(fpu); } /* * Drops current FPU state: deactivates the fpregs and * the fpstate. NOTE: it still leaves previous contents * in the fpregs in the eager-FPU case. * * This function can be used in cases where we know that * a state-restore is coming: either an explicit one, * or a reschedule. */ void fpu__drop(struct fpu *fpu) { preempt_disable(); if (fpu == ¤t->thread.fpu) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" "2:\n" _ASM_EXTABLE(1b, 2b)); fpregs_deactivate(fpu); } trace_x86_fpu_dropped(fpu); preempt_enable(); } /* * Clear FPU registers by setting them up from the init fpstate. * Caller must do fpregs_[un]lock() around it. */ static inline void copy_init_fpstate_to_fpregs(u64 features_mask) { if (use_xsave()) copy_kernel_to_xregs(&init_fpstate.xsave, features_mask); else if (static_cpu_has(X86_FEATURE_FXSR)) copy_kernel_to_fxregs(&init_fpstate.fxsave); else copy_kernel_to_fregs(&init_fpstate.fsave); if (boot_cpu_has(X86_FEATURE_OSPKE)) copy_init_pkru_to_fpregs(); } /* * Clear the FPU state back to init state. * * Called by sys_execve(), by the signal handler code and by various * error paths. */ static void fpu__clear(struct fpu *fpu, bool user_only) { WARN_ON_FPU(fpu != ¤t->thread.fpu); if (!static_cpu_has(X86_FEATURE_FPU)) { fpu__drop(fpu); fpu__initialize(fpu); return; } fpregs_lock(); if (user_only) { if (!fpregs_state_valid(fpu, smp_processor_id()) && xfeatures_mask_supervisor()) copy_kernel_to_xregs(&fpu->state.xsave, xfeatures_mask_supervisor()); copy_init_fpstate_to_fpregs(xfeatures_mask_user()); } else { copy_init_fpstate_to_fpregs(xfeatures_mask_all); } fpregs_mark_activate(); fpregs_unlock(); } void fpu__clear_user_states(struct fpu *fpu) { fpu__clear(fpu, true); } void fpu__clear_all(struct fpu *fpu) { fpu__clear(fpu, false); } /* * Load FPU context before returning to userspace. */ void switch_fpu_return(void) { if (!static_cpu_has(X86_FEATURE_FPU)) return; __fpregs_load_activate(); } EXPORT_SYMBOL_GPL(switch_fpu_return); #ifdef CONFIG_X86_DEBUG_FPU /* * If current FPU state according to its tracking (loaded FPU context on this * CPU) is not valid then we must have TIF_NEED_FPU_LOAD set so the context is * loaded on return to userland. */ void fpregs_assert_state_consistent(void) { struct fpu *fpu = ¤t->thread.fpu; if (test_thread_flag(TIF_NEED_FPU_LOAD)) return; WARN_ON_FPU(!fpregs_state_valid(fpu, smp_processor_id())); } EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent); #endif void fpregs_mark_activate(void) { struct fpu *fpu = ¤t->thread.fpu; fpregs_activate(fpu); fpu->last_cpu = smp_processor_id(); clear_thread_flag(TIF_NEED_FPU_LOAD); } EXPORT_SYMBOL_GPL(fpregs_mark_activate); /* * x87 math exception handling: */ int fpu__exception_code(struct fpu *fpu, int trap_nr) { int err; if (trap_nr == X86_TRAP_MF) { unsigned short cwd, swd; /* * (~cwd & swd) will mask out exceptions that are not set to unmasked * status. 0x3f is the exception bits in these regs, 0x200 is the * C1 reg you need in case of a stack fault, 0x040 is the stack * fault bit. We should only be taking one exception at a time, * so if this combination doesn't produce any single exception, * then we have a bad program that isn't synchronizing its FPU usage * and it will suffer the consequences since we won't be able to * fully reproduce the context of the exception. */ if (boot_cpu_has(X86_FEATURE_FXSR)) { cwd = fpu->state.fxsave.cwd; swd = fpu->state.fxsave.swd; } else { cwd = (unsigned short)fpu->state.fsave.cwd; swd = (unsigned short)fpu->state.fsave.swd; } err = swd & ~cwd; } else { /* * The SIMD FPU exceptions are handled a little differently, as there * is only a single status/control register. Thus, to determine which * unmasked exception was caught we must mask the exception mask bits * at 0x1f80, and then use these to mask the exception bits at 0x3f. */ unsigned short mxcsr = MXCSR_DEFAULT; if (boot_cpu_has(X86_FEATURE_XMM)) mxcsr = fpu->state.fxsave.mxcsr; err = ~(mxcsr >> 7) & mxcsr; } if (err & 0x001) { /* Invalid op */ /* * swd & 0x240 == 0x040: Stack Underflow * swd & 0x240 == 0x240: Stack Overflow * User must clear the SF bit (0x40) if set */ return FPE_FLTINV; } else if (err & 0x004) { /* Divide by Zero */ return FPE_FLTDIV; } else if (err & 0x008) { /* Overflow */ return FPE_FLTOVF; } else if (err & 0x012) { /* Denormal, Underflow */ return FPE_FLTUND; } else if (err & 0x020) { /* Precision */ return FPE_FLTRES; } /* * If we're using IRQ 13, or supposedly even some trap * X86_TRAP_MF implementations, it's possible * we get a spurious trap, which is not an error. */ return 0; } |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 | // SPDX-License-Identifier: GPL-2.0-only /* * Implementation of the policy database. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * * Support for enhanced MLS infrastructure. * * Updated: Frank Mayer <mayerf@tresys.com> and Karl MacMillan <kmacmillan@tresys.com> * * Added conditional policy language extensions * * Updated: Hewlett-Packard <paul@paul-moore.com> * * Added support for the policy capability bitmap * * Update: Mellanox Techonologies * * Added Infiniband support * * Copyright (C) 2016 Mellanox Techonologies * Copyright (C) 2007 Hewlett-Packard Development Company, L.P. * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. * Copyright (C) 2003 - 2004 Tresys Technology, LLC */ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/audit.h> #include "security.h" #include "policydb.h" #include "conditional.h" #include "mls.h" #include "services.h" #define _DEBUG_HASHES #ifdef DEBUG_HASHES static const char *symtab_name[SYM_NUM] = { "common prefixes", "classes", "roles", "types", "users", "bools", "levels", "categories", }; #endif struct policydb_compat_info { int version; int sym_num; int ocon_num; }; /* These need to be updated if SYM_NUM or OCON_NUM changes */ static struct policydb_compat_info policydb_compat[] = { { .version = POLICYDB_VERSION_BASE, .sym_num = SYM_NUM - 3, .ocon_num = OCON_NUM - 3, }, { .version = POLICYDB_VERSION_BOOL, .sym_num = SYM_NUM - 2, .ocon_num = OCON_NUM - 3, }, { .version = POLICYDB_VERSION_IPV6, .sym_num = SYM_NUM - 2, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_NLCLASS, .sym_num = SYM_NUM - 2, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_MLS, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_AVTAB, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_RANGETRANS, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_POLCAP, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_PERMISSIVE, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_BOUNDARY, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_FILENAME_TRANS, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_ROLETRANS, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_NEW_OBJECT_DEFAULTS, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_DEFAULT_TYPE, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_CONSTRAINT_NAMES, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_XPERMS_IOCTL, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_INFINIBAND, .sym_num = SYM_NUM, .ocon_num = OCON_NUM, }, { .version = POLICYDB_VERSION_GLBLUB, .sym_num = SYM_NUM, .ocon_num = OCON_NUM, }, { .version = POLICYDB_VERSION_COMP_FTRANS, .sym_num = SYM_NUM, .ocon_num = OCON_NUM, }, }; static struct policydb_compat_info *policydb_lookup_compat(int version) { int i; struct policydb_compat_info *info = NULL; for (i = 0; i < ARRAY_SIZE(policydb_compat); i++) { if (policydb_compat[i].version == version) { info = &policydb_compat[i]; break; } } return info; } /* * The following *_destroy functions are used to * free any memory allocated for each kind of * symbol data in the policy database. */ static int perm_destroy(void *key, void *datum, void *p) { kfree(key); kfree(datum); return 0; } static int common_destroy(void *key, void *datum, void *p) { struct common_datum *comdatum; kfree(key); if (datum) { comdatum = datum; hashtab_map(&comdatum->permissions.table, perm_destroy, NULL); hashtab_destroy(&comdatum->permissions.table); } kfree(datum); return 0; } static void constraint_expr_destroy(struct constraint_expr *expr) { if (expr) { ebitmap_destroy(&expr->names); if (expr->type_names) { ebitmap_destroy(&expr->type_names->types); ebitmap_destroy(&expr->type_names->negset); kfree(expr->type_names); } kfree(expr); } } static int cls_destroy(void *key, void *datum, void *p) { struct class_datum *cladatum; struct constraint_node *constraint, *ctemp; struct constraint_expr *e, *etmp; kfree(key); if (datum) { cladatum = datum; hashtab_map(&cladatum->permissions.table, perm_destroy, NULL); hashtab_destroy(&cladatum->permissions.table); constraint = cladatum->constraints; while (constraint) { e = constraint->expr; while (e) { etmp = e; e = e->next; constraint_expr_destroy(etmp); } ctemp = constraint; constraint = constraint->next; kfree(ctemp); } constraint = cladatum->validatetrans; while (constraint) { e = constraint->expr; while (e) { etmp = e; e = e->next; constraint_expr_destroy(etmp); } ctemp = constraint; constraint = constraint->next; kfree(ctemp); } kfree(cladatum->comkey); } kfree(datum); return 0; } static int role_destroy(void *key, void *datum, void *p) { struct role_datum *role; kfree(key); if (datum) { role = datum; ebitmap_destroy(&role->dominates); ebitmap_destroy(&role->types); } kfree(datum); return 0; } static int type_destroy(void *key, void *datum, void *p) { kfree(key); kfree(datum); return 0; } static int user_destroy(void *key, void *datum, void *p) { struct user_datum *usrdatum; kfree(key); if (datum) { usrdatum = datum; ebitmap_destroy(&usrdatum->roles); ebitmap_destroy(&usrdatum->range.level[0].cat); ebitmap_destroy(&usrdatum->range.level[1].cat); ebitmap_destroy(&usrdatum->dfltlevel.cat); } kfree(datum); return 0; } static int sens_destroy(void *key, void *datum, void *p) { struct level_datum *levdatum; kfree(key); if (datum) { levdatum = datum; if (levdatum->level) ebitmap_destroy(&levdatum->level->cat); kfree(levdatum->level); } kfree(datum); return 0; } static int cat_destroy(void *key, void *datum, void *p) { kfree(key); kfree(datum); return 0; } static int (*destroy_f[SYM_NUM]) (void *key, void *datum, void *datap) = { common_destroy, cls_destroy, role_destroy, type_destroy, user_destroy, cond_destroy_bool, sens_destroy, cat_destroy, }; static int filenametr_destroy(void *key, void *datum, void *p) { struct filename_trans_key *ft = key; struct filename_trans_datum *next, *d = datum; kfree(ft->name); kfree(key); do { ebitmap_destroy(&d->stypes); next = d->next; kfree(d); d = next; } while (unlikely(d)); cond_resched(); return 0; } static int range_tr_destroy(void *key, void *datum, void *p) { struct mls_range *rt = datum; kfree(key); ebitmap_destroy(&rt->level[0].cat); ebitmap_destroy(&rt->level[1].cat); kfree(datum); cond_resched(); return 0; } static int role_tr_destroy(void *key, void *datum, void *p) { kfree(key); kfree(datum); return 0; } static void ocontext_destroy(struct ocontext *c, int i) { if (!c) return; context_destroy(&c->context[0]); context_destroy(&c->context[1]); if (i == OCON_ISID || i == OCON_FS || i == OCON_NETIF || i == OCON_FSUSE) kfree(c->u.name); kfree(c); } /* * Initialize the role table. */ static int roles_init(struct policydb *p) { char *key = NULL; int rc; struct role_datum *role; role = kzalloc(sizeof(*role), GFP_KERNEL); if (!role) return -ENOMEM; rc = -EINVAL; role->value = ++p->p_roles.nprim; if (role->value != OBJECT_R_VAL) goto out; rc = -ENOMEM; key = kstrdup(OBJECT_R, GFP_KERNEL); if (!key) goto out; rc = symtab_insert(&p->p_roles, key, role); if (rc) goto out; return 0; out: kfree(key); kfree(role); return rc; } static u32 filenametr_hash(const void *k) { const struct filename_trans_key *ft = k; unsigned long hash; unsigned int byte_num; unsigned char focus; hash = ft->ttype ^ ft->tclass; byte_num = 0; while ((focus = ft->name[byte_num++])) hash = partial_name_hash(focus, hash); return hash; } static int filenametr_cmp(const void *k1, const void *k2) { const struct filename_trans_key *ft1 = k1; const struct filename_trans_key *ft2 = k2; int v; v = ft1->ttype - ft2->ttype; if (v) return v; v = ft1->tclass - ft2->tclass; if (v) return v; return strcmp(ft1->name, ft2->name); } static const struct hashtab_key_params filenametr_key_params = { .hash = filenametr_hash, .cmp = filenametr_cmp, }; struct filename_trans_datum *policydb_filenametr_search( struct policydb *p, struct filename_trans_key *key) { return hashtab_search(&p->filename_trans, key, filenametr_key_params); } static u32 rangetr_hash(const void *k) { const struct range_trans *key = k; return key->source_type + (key->target_type << 3) + (key->target_class << 5); } static int rangetr_cmp(const void *k1, const void *k2) { const struct range_trans *key1 = k1, *key2 = k2; int v; v = key1->source_type - key2->source_type; if (v) return v; v = key1->target_type - key2->target_type; if (v) return v; v = key1->target_class - key2->target_class; return v; } static const struct hashtab_key_params rangetr_key_params = { .hash = rangetr_hash, .cmp = rangetr_cmp, }; struct mls_range *policydb_rangetr_search(struct policydb *p, struct range_trans *key) { return hashtab_search(&p->range_tr, key, rangetr_key_params); } static u32 role_trans_hash(const void *k) { const struct role_trans_key *key = k; return key->role + (key->type << 3) + (key->tclass << 5); } static int role_trans_cmp(const void *k1, const void *k2) { const struct role_trans_key *key1 = k1, *key2 = k2; int v; v = key1->role - key2->role; if (v) return v; v = key1->type - key2->type; if (v) return v; return key1->tclass - key2->tclass; } static const struct hashtab_key_params roletr_key_params = { .hash = role_trans_hash, .cmp = role_trans_cmp, }; struct role_trans_datum *policydb_roletr_search(struct policydb *p, struct role_trans_key *key) { return hashtab_search(&p->role_tr, key, roletr_key_params); } /* * Initialize a policy database structure. */ static void policydb_init(struct policydb *p) { memset(p, 0, sizeof(*p)); avtab_init(&p->te_avtab); cond_policydb_init(p); ebitmap_init(&p->filename_trans_ttypes); ebitmap_init(&p->policycaps); ebitmap_init(&p->permissive_map); } /* * The following *_index functions are used to * define the val_to_name and val_to_struct arrays * in a policy database structure. The val_to_name * arrays are used when converting security context * structures into string representations. The * val_to_struct arrays are used when the attributes * of a class, role, or user are needed. */ static int common_index(void *key, void *datum, void *datap) { struct policydb *p; struct common_datum *comdatum; comdatum = datum; p = datap; if (!comdatum->value || comdatum->value > p->p_commons.nprim) return -EINVAL; p->sym_val_to_name[SYM_COMMONS][comdatum->value - 1] = key; return 0; } static int class_index(void *key, void *datum, void *datap) { struct policydb *p; struct class_datum *cladatum; cladatum = datum; p = datap; if (!cladatum->value || cladatum->value > p->p_classes.nprim) return -EINVAL; p->sym_val_to_name[SYM_CLASSES][cladatum->value - 1] = key; p->class_val_to_struct[cladatum->value - 1] = cladatum; return 0; } static int role_index(void *key, void *datum, void *datap) { struct policydb *p; struct role_datum *role; role = datum; p = datap; if (!role->value || role->value > p->p_roles.nprim || role->bounds > p->p_roles.nprim) return -EINVAL; p->sym_val_to_name[SYM_ROLES][role->value - 1] = key; p->role_val_to_struct[role->value - 1] = role; return 0; } static int type_index(void *key, void *datum, void *datap) { struct policydb *p; struct type_datum *typdatum; typdatum = datum; p = datap; if (typdatum->primary) { if (!typdatum->value || typdatum->value > p->p_types.nprim || typdatum->bounds > p->p_types.nprim) return -EINVAL; p->sym_val_to_name[SYM_TYPES][typdatum->value - 1] = key; p->type_val_to_struct[typdatum->value - 1] = typdatum; } return 0; } static int user_index(void *key, void *datum, void *datap) { struct policydb *p; struct user_datum *usrdatum; usrdatum = datum; p = datap; if (!usrdatum->value || usrdatum->value > p->p_users.nprim || usrdatum->bounds > p->p_users.nprim) return -EINVAL; p->sym_val_to_name[SYM_USERS][usrdatum->value - 1] = key; p->user_val_to_struct[usrdatum->value - 1] = usrdatum; return 0; } static int sens_index(void *key, void *datum, void *datap) { struct policydb *p; struct level_datum *levdatum; levdatum = datum; p = datap; if (!levdatum->isalias) { if (!levdatum->level->sens || levdatum->level->sens > p->p_levels.nprim) return -EINVAL; p->sym_val_to_name[SYM_LEVELS][levdatum->level->sens - 1] = key; } return 0; } static int cat_index(void *key, void *datum, void *datap) { struct policydb *p; struct cat_datum *catdatum; catdatum = datum; p = datap; if (!catdatum->isalias) { if (!catdatum->value || catdatum->value > p->p_cats.nprim) return -EINVAL; p->sym_val_to_name[SYM_CATS][catdatum->value - 1] = key; } return 0; } static int (*index_f[SYM_NUM]) (void *key, void *datum, void *datap) = { common_index, class_index, role_index, type_index, user_index, cond_index_bool, sens_index, cat_index, }; #ifdef DEBUG_HASHES static void hash_eval(struct hashtab *h, const char *hash_name) { struct hashtab_info info; hashtab_stat(h, &info); pr_debug("SELinux: %s: %d entries and %d/%d buckets used, longest chain length %d\n", hash_name, h->nel, info.slots_used, h->size, info.max_chain_len); } static void symtab_hash_eval(struct symtab *s) { int i; for (i = 0; i < SYM_NUM; i++) hash_eval(&s[i].table, symtab_name[i]); } #else static inline void hash_eval(struct hashtab *h, char *hash_name) { } #endif /* * Define the other val_to_name and val_to_struct arrays * in a policy database structure. * * Caller must clean up on failure. */ static int policydb_index(struct policydb *p) { int i, rc; if (p->mls_enabled) pr_debug("SELinux: %d users, %d roles, %d types, %d bools, %d sens, %d cats\n", p->p_users.nprim, p->p_roles.nprim, p->p_types.nprim, p->p_bools.nprim, p->p_levels.nprim, p->p_cats.nprim); else pr_debug("SELinux: %d users, %d roles, %d types, %d bools\n", p->p_users.nprim, p->p_roles.nprim, p->p_types.nprim, p->p_bools.nprim); pr_debug("SELinux: %d classes, %d rules\n", p->p_classes.nprim, p->te_avtab.nel); #ifdef DEBUG_HASHES avtab_hash_eval(&p->te_avtab, "rules"); symtab_hash_eval(p->symtab); #endif p->class_val_to_struct = kcalloc(p->p_classes.nprim, sizeof(*p->class_val_to_struct), GFP_KERNEL); if (!p->class_val_to_struct) return -ENOMEM; p->role_val_to_struct = kcalloc(p->p_roles.nprim, sizeof(*p->role_val_to_struct), GFP_KERNEL); if (!p->role_val_to_struct) return -ENOMEM; p->user_val_to_struct = kcalloc(p->p_users.nprim, sizeof(*p->user_val_to_struct), GFP_KERNEL); if (!p->user_val_to_struct) return -ENOMEM; p->type_val_to_struct = kvcalloc(p->p_types.nprim, sizeof(*p->type_val_to_struct), GFP_KERNEL); if (!p->type_val_to_struct) return -ENOMEM; rc = cond_init_bool_indexes(p); if (rc) goto out; for (i = 0; i < SYM_NUM; i++) { p->sym_val_to_name[i] = kvcalloc(p->symtab[i].nprim, sizeof(char *), GFP_KERNEL); if (!p->sym_val_to_name[i]) return -ENOMEM; rc = hashtab_map(&p->symtab[i].table, index_f[i], p); if (rc) goto out; } rc = 0; out: return rc; } /* * Free any memory allocated by a policy database structure. */ void policydb_destroy(struct policydb *p) { struct ocontext *c, *ctmp; struct genfs *g, *gtmp; int i; struct role_allow *ra, *lra = NULL; for (i = 0; i < SYM_NUM; i++) { cond_resched(); hashtab_map(&p->symtab[i].table, destroy_f[i], NULL); hashtab_destroy(&p->symtab[i].table); } for (i = 0; i < SYM_NUM; i++) kvfree(p->sym_val_to_name[i]); kfree(p->class_val_to_struct); kfree(p->role_val_to_struct); kfree(p->user_val_to_struct); kvfree(p->type_val_to_struct); avtab_destroy(&p->te_avtab); for (i = 0; i < OCON_NUM; i++) { cond_resched(); c = p->ocontexts[i]; while (c) { ctmp = c; c = c->next; ocontext_destroy(ctmp, i); } p->ocontexts[i] = NULL; } g = p->genfs; while (g) { cond_resched(); kfree(g->fstype); c = g->head; while (c) { ctmp = c; c = c->next; ocontext_destroy(ctmp, OCON_FSUSE); } gtmp = g; g = g->next; kfree(gtmp); } p->genfs = NULL; cond_policydb_destroy(p); hashtab_map(&p->role_tr, role_tr_destroy, NULL); hashtab_destroy(&p->role_tr); for (ra = p->role_allow; ra; ra = ra->next) { cond_resched(); kfree(lra); lra = ra; } kfree(lra); hashtab_map(&p->filename_trans, filenametr_destroy, NULL); hashtab_destroy(&p->filename_trans); hashtab_map(&p->range_tr, range_tr_destroy, NULL); hashtab_destroy(&p->range_tr); if (p->type_attr_map_array) { for (i = 0; i < p->p_types.nprim; i++) ebitmap_destroy(&p->type_attr_map_array[i]); kvfree(p->type_attr_map_array); } ebitmap_destroy(&p->filename_trans_ttypes); ebitmap_destroy(&p->policycaps); ebitmap_destroy(&p->permissive_map); } /* * Load the initial SIDs specified in a policy database * structure into a SID table. */ int policydb_load_isids(struct policydb *p, struct sidtab *s) { struct ocontext *head, *c; int rc; rc = sidtab_init(s); if (rc) { pr_err("SELinux: out of memory on SID table init\n"); return rc; } head = p->ocontexts[OCON_ISID]; for (c = head; c; c = c->next) { u32 sid = c->sid[0]; const char *name = security_get_initial_sid_context(sid); if (sid == SECSID_NULL) { pr_err("SELinux: SID 0 was assigned a context.\n"); sidtab_destroy(s); return -EINVAL; } /* Ignore initial SIDs unused by this kernel. */ if (!name) continue; rc = sidtab_set_initial(s, sid, &c->context[0]); if (rc) { pr_err("SELinux: unable to load initial SID %s.\n", name); sidtab_destroy(s); return rc; } } return 0; } int policydb_class_isvalid(struct policydb *p, unsigned int class) { if (!class || class > p->p_classes.nprim) return 0; return 1; } int policydb_role_isvalid(struct policydb *p, unsigned int role) { if (!role || role > p->p_roles.nprim) return 0; return 1; } int policydb_type_isvalid(struct policydb *p, unsigned int type) { if (!type || type > p->p_types.nprim) return 0; return 1; } /* * Return 1 if the fields in the security context * structure `c' are valid. Return 0 otherwise. */ int policydb_context_isvalid(struct policydb *p, struct context *c) { struct role_datum *role; struct user_datum *usrdatum; if (!c->role || c->role > p->p_roles.nprim) return 0; if (!c->user || c->user > p->p_users.nprim) return 0; if (!c->type || c->type > p->p_types.nprim) return 0; if (c->role != OBJECT_R_VAL) { /* * Role must be authorized for the type. */ role = p->role_val_to_struct[c->role - 1]; if (!role || !ebitmap_get_bit(&role->types, c->type - 1)) /* role may not be associated with type */ return 0; /* * User must be authorized for the role. */ usrdatum = p->user_val_to_struct[c->user - 1]; if (!usrdatum) return 0; if (!ebitmap_get_bit(&usrdatum->roles, c->role - 1)) /* user may not be associated with role */ return 0; } if (!mls_context_isvalid(p, c)) return 0; return 1; } /* * Read a MLS range structure from a policydb binary * representation file. */ static int mls_read_range_helper(struct mls_range *r, void *fp) { __le32 buf[2]; u32 items; int rc; rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; rc = -EINVAL; items = le32_to_cpu(buf[0]); if (items > ARRAY_SIZE(buf)) { pr_err("SELinux: mls: range overflow\n"); goto out; } rc = next_entry(buf, fp, sizeof(u32) * items); if (rc) { pr_err("SELinux: mls: truncated range\n"); goto out; } r->level[0].sens = le32_to_cpu(buf[0]); if (items > 1) r->level[1].sens = le32_to_cpu(buf[1]); else r->level[1].sens = r->level[0].sens; rc = ebitmap_read(&r->level[0].cat, fp); if (rc) { pr_err("SELinux: mls: error reading low categories\n"); goto out; } if (items > 1) { rc = ebitmap_read(&r->level[1].cat, fp); if (rc) { pr_err("SELinux: mls: error reading high categories\n"); goto bad_high; } } else { rc = ebitmap_cpy(&r->level[1].cat, &r->level[0].cat); if (rc) { pr_err("SELinux: mls: out of memory\n"); goto bad_high; } } return 0; bad_high: ebitmap_destroy(&r->level[0].cat); out: return rc; } /* * Read and validate a security context structure * from a policydb binary representation file. */ static int context_read_and_validate(struct context *c, struct policydb *p, void *fp) { __le32 buf[3]; int rc; rc = next_entry(buf, fp, sizeof buf); if (rc) { pr_err("SELinux: context truncated\n"); goto out; } c->user = le32_to_cpu(buf[0]); c->role = le32_to_cpu(buf[1]); c->type = le32_to_cpu(buf[2]); if (p->policyvers >= POLICYDB_VERSION_MLS) { rc = mls_read_range_helper(&c->range, fp); if (rc) { pr_err("SELinux: error reading MLS range of context\n"); goto out; } } rc = -EINVAL; if (!policydb_context_isvalid(p, c)) { pr_err("SELinux: invalid security context\n"); context_destroy(c); goto out; } rc = 0; out: return rc; } /* * The following *_read functions are used to * read the symbol data from a policy database * binary representation file. */ static int str_read(char **strp, gfp_t flags, void *fp, u32 len) { int rc; char *str; if ((len == 0) || (len == (u32)-1)) return -EINVAL; str = kmalloc(len + 1, flags | __GFP_NOWARN); if (!str) return -ENOMEM; rc = next_entry(str, fp, len); if (rc) { kfree(str); return rc; } str[len] = '\0'; *strp = str; return 0; } static int perm_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct perm_datum *perdatum; int rc; __le32 buf[2]; u32 len; perdatum = kzalloc(sizeof(*perdatum), GFP_KERNEL); if (!perdatum) return -ENOMEM; rc = next_entry(buf, fp, sizeof buf); if (rc) goto bad; len = le32_to_cpu(buf[0]); perdatum->value = le32_to_cpu(buf[1]); rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; rc = symtab_insert(s, key, perdatum); if (rc) goto bad; return 0; bad: perm_destroy(key, perdatum, NULL); return rc; } static int common_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct common_datum *comdatum; __le32 buf[4]; u32 len, nel; int i, rc; comdatum = kzalloc(sizeof(*comdatum), GFP_KERNEL); if (!comdatum) return -ENOMEM; rc = next_entry(buf, fp, sizeof buf); if (rc) goto bad; len = le32_to_cpu(buf[0]); comdatum->value = le32_to_cpu(buf[1]); nel = le32_to_cpu(buf[3]); rc = symtab_init(&comdatum->permissions, nel); if (rc) goto bad; comdatum->permissions.nprim = le32_to_cpu(buf[2]); rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; for (i = 0; i < nel; i++) { rc = perm_read(p, &comdatum->permissions, fp); if (rc) goto bad; } rc = symtab_insert(s, key, comdatum); if (rc) goto bad; return 0; bad: common_destroy(key, comdatum, NULL); return rc; } static void type_set_init(struct type_set *t) { ebitmap_init(&t->types); ebitmap_init(&t->negset); } static int type_set_read(struct type_set *t, void *fp) { __le32 buf[1]; int rc; if (ebitmap_read(&t->types, fp)) return -EINVAL; if (ebitmap_read(&t->negset, fp)) return -EINVAL; rc = next_entry(buf, fp, sizeof(u32)); if (rc < 0) return -EINVAL; t->flags = le32_to_cpu(buf[0]); return 0; } static int read_cons_helper(struct policydb *p, struct constraint_node **nodep, int ncons, int allowxtarget, void *fp) { struct constraint_node *c, *lc; struct constraint_expr *e, *le; __le32 buf[3]; u32 nexpr; int rc, i, j, depth; lc = NULL; for (i = 0; i < ncons; i++) { c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) return -ENOMEM; if (lc) lc->next = c; else *nodep = c; rc = next_entry(buf, fp, (sizeof(u32) * 2)); if (rc) return rc; c->permissions = le32_to_cpu(buf[0]); nexpr = le32_to_cpu(buf[1]); le = NULL; depth = -1; for (j = 0; j < nexpr; j++) { e = kzalloc(sizeof(*e), GFP_KERNEL); if (!e) return -ENOMEM; if (le) le->next = e; else c->expr = e; rc = next_entry(buf, fp, (sizeof(u32) * 3)); if (rc) return rc; e->expr_type = le32_to_cpu(buf[0]); e->attr = le32_to_cpu(buf[1]); e->op = le32_to_cpu(buf[2]); switch (e->expr_type) { case CEXPR_NOT: if (depth < 0) return -EINVAL; break; case CEXPR_AND: case CEXPR_OR: if (depth < 1) return -EINVAL; depth--; break; case CEXPR_ATTR: if (depth == (CEXPR_MAXDEPTH - 1)) return -EINVAL; depth++; break; case CEXPR_NAMES: if (!allowxtarget && (e->attr & CEXPR_XTARGET)) return -EINVAL; if (depth == (CEXPR_MAXDEPTH - 1)) return -EINVAL; depth++; rc = ebitmap_read(&e->names, fp); if (rc) return rc; if (p->policyvers >= POLICYDB_VERSION_CONSTRAINT_NAMES) { e->type_names = kzalloc(sizeof (*e->type_names), GFP_KERNEL); if (!e->type_names) return -ENOMEM; type_set_init(e->type_names); rc = type_set_read(e->type_names, fp); if (rc) return rc; } break; default: return -EINVAL; } le = e; } if (depth != 0) return -EINVAL; lc = c; } return 0; } static int class_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct class_datum *cladatum; __le32 buf[6]; u32 len, len2, ncons, nel; int i, rc; cladatum = kzalloc(sizeof(*cladatum), GFP_KERNEL); if (!cladatum) return -ENOMEM; rc = next_entry(buf, fp, sizeof(u32)*6); if (rc) goto bad; len = le32_to_cpu(buf[0]); len2 = le32_to_cpu(buf[1]); cladatum->value = le32_to_cpu(buf[2]); nel = le32_to_cpu(buf[4]); rc = symtab_init(&cladatum->permissions, nel); if (rc) goto bad; cladatum->permissions.nprim = le32_to_cpu(buf[3]); ncons = le32_to_cpu(buf[5]); rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; if (len2) { rc = str_read(&cladatum->comkey, GFP_KERNEL, fp, len2); if (rc) goto bad; rc = -EINVAL; cladatum->comdatum = symtab_search(&p->p_commons, cladatum->comkey); if (!cladatum->comdatum) { pr_err("SELinux: unknown common %s\n", cladatum->comkey); goto bad; } } for (i = 0; i < nel; i++) { rc = perm_read(p, &cladatum->permissions, fp); if (rc) goto bad; } rc = read_cons_helper(p, &cladatum->constraints, ncons, 0, fp); if (rc) goto bad; if (p->policyvers >= POLICYDB_VERSION_VALIDATETRANS) { /* grab the validatetrans rules */ rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto bad; ncons = le32_to_cpu(buf[0]); rc = read_cons_helper(p, &cladatum->validatetrans, ncons, 1, fp); if (rc) goto bad; } if (p->policyvers >= POLICYDB_VERSION_NEW_OBJECT_DEFAULTS) { rc = next_entry(buf, fp, sizeof(u32) * 3); if (rc) goto bad; cladatum->default_user = le32_to_cpu(buf[0]); cladatum->default_role = le32_to_cpu(buf[1]); cladatum->default_range = le32_to_cpu(buf[2]); } if (p->policyvers >= POLICYDB_VERSION_DEFAULT_TYPE) { rc = next_entry(buf, fp, sizeof(u32) * 1); if (rc) goto bad; cladatum->default_type = le32_to_cpu(buf[0]); } rc = symtab_insert(s, key, cladatum); if (rc) goto bad; return 0; bad: cls_destroy(key, cladatum, NULL); return rc; } static int role_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct role_datum *role; int rc, to_read = 2; __le32 buf[3]; u32 len; role = kzalloc(sizeof(*role), GFP_KERNEL); if (!role) return -ENOMEM; if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) to_read = 3; rc = next_entry(buf, fp, sizeof(buf[0]) * to_read); if (rc) goto bad; len = le32_to_cpu(buf[0]); role->value = le32_to_cpu(buf[1]); if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) role->bounds = le32_to_cpu(buf[2]); rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; rc = ebitmap_read(&role->dominates, fp); if (rc) goto bad; rc = ebitmap_read(&role->types, fp); if (rc) goto bad; if (strcmp(key, OBJECT_R) == 0) { rc = -EINVAL; if (role->value != OBJECT_R_VAL) { pr_err("SELinux: Role %s has wrong value %d\n", OBJECT_R, role->value); goto bad; } rc = 0; goto bad; } rc = symtab_insert(s, key, role); if (rc) goto bad; return 0; bad: role_destroy(key, role, NULL); return rc; } static int type_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct type_datum *typdatum; int rc, to_read = 3; __le32 buf[4]; u32 len; typdatum = kzalloc(sizeof(*typdatum), GFP_KERNEL); if (!typdatum) return -ENOMEM; if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) to_read = 4; rc = next_entry(buf, fp, sizeof(buf[0]) * to_read); if (rc) goto bad; len = le32_to_cpu(buf[0]); typdatum->value = le32_to_cpu(buf[1]); if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) { u32 prop = le32_to_cpu(buf[2]); if (prop & TYPEDATUM_PROPERTY_PRIMARY) typdatum->primary = 1; if (prop & TYPEDATUM_PROPERTY_ATTRIBUTE) typdatum->attribute = 1; typdatum->bounds = le32_to_cpu(buf[3]); } else { typdatum->primary = le32_to_cpu(buf[2]); } rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; rc = symtab_insert(s, key, typdatum); if (rc) goto bad; return 0; bad: type_destroy(key, typdatum, NULL); return rc; } /* * Read a MLS level structure from a policydb binary * representation file. */ static int mls_read_level(struct mls_level *lp, void *fp) { __le32 buf[1]; int rc; memset(lp, 0, sizeof(*lp)); rc = next_entry(buf, fp, sizeof buf); if (rc) { pr_err("SELinux: mls: truncated level\n"); return rc; } lp->sens = le32_to_cpu(buf[0]); rc = ebitmap_read(&lp->cat, fp); if (rc) { pr_err("SELinux: mls: error reading level categories\n"); return rc; } return 0; } static int user_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct user_datum *usrdatum; int rc, to_read = 2; __le32 buf[3]; u32 len; usrdatum = kzalloc(sizeof(*usrdatum), GFP_KERNEL); if (!usrdatum) return -ENOMEM; if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) to_read = 3; rc = next_entry(buf, fp, sizeof(buf[0]) * to_read); if (rc) goto bad; len = le32_to_cpu(buf[0]); usrdatum->value = le32_to_cpu(buf[1]); if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) usrdatum->bounds = le32_to_cpu(buf[2]); rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; rc = ebitmap_read(&usrdatum->roles, fp); if (rc) goto bad; if (p->policyvers >= POLICYDB_VERSION_MLS) { rc = mls_read_range_helper(&usrdatum->range, fp); if (rc) goto bad; rc = mls_read_level(&usrdatum->dfltlevel, fp); if (rc) goto bad; } rc = symtab_insert(s, key, usrdatum); if (rc) goto bad; return 0; bad: user_destroy(key, usrdatum, NULL); return rc; } static int sens_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct level_datum *levdatum; int rc; __le32 buf[2]; u32 len; levdatum = kzalloc(sizeof(*levdatum), GFP_ATOMIC); if (!levdatum) return -ENOMEM; rc = next_entry(buf, fp, sizeof buf); if (rc) goto bad; len = le32_to_cpu(buf[0]); levdatum->isalias = le32_to_cpu(buf[1]); rc = str_read(&key, GFP_ATOMIC, fp, len); if (rc) goto bad; rc = -ENOMEM; levdatum->level = kmalloc(sizeof(*levdatum->level), GFP_ATOMIC); if (!levdatum->level) goto bad; rc = mls_read_level(levdatum->level, fp); if (rc) goto bad; rc = symtab_insert(s, key, levdatum); if (rc) goto bad; return 0; bad: sens_destroy(key, levdatum, NULL); return rc; } static int cat_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct cat_datum *catdatum; int rc; __le32 buf[3]; u32 len; catdatum = kzalloc(sizeof(*catdatum), GFP_ATOMIC); if (!catdatum) return -ENOMEM; rc = next_entry(buf, fp, sizeof buf); if (rc) goto bad; len = le32_to_cpu(buf[0]); catdatum->value = le32_to_cpu(buf[1]); catdatum->isalias = le32_to_cpu(buf[2]); rc = str_read(&key, GFP_ATOMIC, fp, len); if (rc) goto bad; rc = symtab_insert(s, key, catdatum); if (rc) goto bad; return 0; bad: cat_destroy(key, catdatum, NULL); return rc; } static int (*read_f[SYM_NUM]) (struct policydb *p, struct symtab *s, void *fp) = { common_read, class_read, role_read, type_read, user_read, cond_read_bool, sens_read, cat_read, }; static int user_bounds_sanity_check(void *key, void *datum, void *datap) { struct user_datum *upper, *user; struct policydb *p = datap; int depth = 0; upper = user = datum; while (upper->bounds) { struct ebitmap_node *node; unsigned long bit; if (++depth == POLICYDB_BOUNDS_MAXDEPTH) { pr_err("SELinux: user %s: " "too deep or looped boundary", (char *) key); return -EINVAL; } upper = p->user_val_to_struct[upper->bounds - 1]; ebitmap_for_each_positive_bit(&user->roles, node, bit) { if (ebitmap_get_bit(&upper->roles, bit)) continue; pr_err("SELinux: boundary violated policy: " "user=%s role=%s bounds=%s\n", sym_name(p, SYM_USERS, user->value - 1), sym_name(p, SYM_ROLES, bit), sym_name(p, SYM_USERS, upper->value - 1)); return -EINVAL; } } return 0; } static int role_bounds_sanity_check(void *key, void *datum, void *datap) { struct role_datum *upper, *role; struct policydb *p = datap; int depth = 0; upper = role = datum; while (upper->bounds) { struct ebitmap_node *node; unsigned long bit; if (++depth == POLICYDB_BOUNDS_MAXDEPTH) { pr_err("SELinux: role %s: " "too deep or looped bounds\n", (char *) key); return -EINVAL; } upper = p->role_val_to_struct[upper->bounds - 1]; ebitmap_for_each_positive_bit(&role->types, node, bit) { if (ebitmap_get_bit(&upper->types, bit)) continue; pr_err("SELinux: boundary violated policy: " "role=%s type=%s bounds=%s\n", sym_name(p, SYM_ROLES, role->value - 1), sym_name(p, SYM_TYPES, bit), sym_name(p, SYM_ROLES, upper->value - 1)); return -EINVAL; } } return 0; } static int type_bounds_sanity_check(void *key, void *datum, void *datap) { struct type_datum *upper; struct policydb *p = datap; int depth = 0; upper = datum; while (upper->bounds) { if (++depth == POLICYDB_BOUNDS_MAXDEPTH) { pr_err("SELinux: type %s: " "too deep or looped boundary\n", (char *) key); return -EINVAL; } upper = p->type_val_to_struct[upper->bounds - 1]; BUG_ON(!upper); if (upper->attribute) { pr_err("SELinux: type %s: " "bounded by attribute %s", (char *) key, sym_name(p, SYM_TYPES, upper->value - 1)); return -EINVAL; } } return 0; } static int policydb_bounds_sanity_check(struct policydb *p) { int rc; if (p->policyvers < POLICYDB_VERSION_BOUNDARY) return 0; rc = hashtab_map(&p->p_users.table, user_bounds_sanity_check, p); if (rc) return rc; rc = hashtab_map(&p->p_roles.table, role_bounds_sanity_check, p); if (rc) return rc; rc = hashtab_map(&p->p_types.table, type_bounds_sanity_check, p); if (rc) return rc; return 0; } u16 string_to_security_class(struct policydb *p, const char *name) { struct class_datum *cladatum; cladatum = symtab_search(&p->p_classes, name); if (!cladatum) return 0; return cladatum->value; } u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name) { struct class_datum *cladatum; struct perm_datum *perdatum = NULL; struct common_datum *comdatum; if (!tclass || tclass > p->p_classes.nprim) return 0; cladatum = p->class_val_to_struct[tclass-1]; comdatum = cladatum->comdatum; if (comdatum) perdatum = symtab_search(&comdatum->permissions, name); if (!perdatum) perdatum = symtab_search(&cladatum->permissions, name); if (!perdatum) return 0; return 1U << (perdatum->value-1); } static int range_read(struct policydb *p, void *fp) { struct range_trans *rt = NULL; struct mls_range *r = NULL; int i, rc; __le32 buf[2]; u32 nel; if (p->policyvers < POLICYDB_VERSION_MLS) return 0; rc = next_entry(buf, fp, sizeof(u32)); if (rc) return rc; nel = le32_to_cpu(buf[0]); rc = hashtab_init(&p->range_tr, nel); if (rc) return rc; for (i = 0; i < nel; i++) { rc = -ENOMEM; rt = kzalloc(sizeof(*rt), GFP_KERNEL); if (!rt) goto out; rc = next_entry(buf, fp, (sizeof(u32) * 2)); if (rc) goto out; rt->source_type = le32_to_cpu(buf[0]); rt->target_type = le32_to_cpu(buf[1]); if (p->policyvers >= POLICYDB_VERSION_RANGETRANS) { rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; rt->target_class = le32_to_cpu(buf[0]); } else rt->target_class = p->process_class; rc = -EINVAL; if (!policydb_type_isvalid(p, rt->source_type) || !policydb_type_isvalid(p, rt->target_type) || !policydb_class_isvalid(p, rt->target_class)) goto out; rc = -ENOMEM; r = kzalloc(sizeof(*r), GFP_KERNEL); if (!r) goto out; rc = mls_read_range_helper(r, fp); if (rc) goto out; rc = -EINVAL; if (!mls_range_isvalid(p, r)) { pr_warn("SELinux: rangetrans: invalid range\n"); goto out; } rc = hashtab_insert(&p->range_tr, rt, r, rangetr_key_params); if (rc) goto out; rt = NULL; r = NULL; } hash_eval(&p->range_tr, "rangetr"); rc = 0; out: kfree(rt); kfree(r); return rc; } static int filename_trans_read_helper_compat(struct policydb *p, void *fp) { struct filename_trans_key key, *ft = NULL; struct filename_trans_datum *last, *datum = NULL; char *name = NULL; u32 len, stype, otype; __le32 buf[4]; int rc; /* length of the path component string */ rc = next_entry(buf, fp, sizeof(u32)); if (rc) return rc; len = le32_to_cpu(buf[0]); /* path component string */ rc = str_read(&name, GFP_KERNEL, fp, len); if (rc) return rc; rc = next_entry(buf, fp, sizeof(u32) * 4); if (rc) goto out; stype = le32_to_cpu(buf[0]); key.ttype = le32_to_cpu(buf[1]); key.tclass = le32_to_cpu(buf[2]); key.name = name; otype = le32_to_cpu(buf[3]); last = NULL; datum = policydb_filenametr_search(p, &key); while (datum) { if (unlikely(ebitmap_get_bit(&datum->stypes, stype - 1))) { /* conflicting/duplicate rules are ignored */ datum = NULL; goto out; } if (likely(datum->otype == otype)) break; last = datum; datum = datum->next; } if (!datum) { rc = -ENOMEM; datum = kmalloc(sizeof(*datum), GFP_KERNEL); if (!datum) goto out; ebitmap_init(&datum->stypes); datum->otype = otype; datum->next = NULL; if (unlikely(last)) { last->next = datum; } else { rc = -ENOMEM; ft = kmemdup(&key, sizeof(key), GFP_KERNEL); if (!ft) goto out; rc = hashtab_insert(&p->filename_trans, ft, datum, filenametr_key_params); if (rc) goto out; name = NULL; rc = ebitmap_set_bit(&p->filename_trans_ttypes, key.ttype, 1); if (rc) return rc; } } kfree(name); return ebitmap_set_bit(&datum->stypes, stype - 1, 1); out: kfree(ft); kfree(name); kfree(datum); return rc; } static int filename_trans_read_helper(struct policydb *p, void *fp) { struct filename_trans_key *ft = NULL; struct filename_trans_datum **dst, *datum, *first = NULL; char *name = NULL; u32 len, ttype, tclass, ndatum, i; __le32 buf[3]; int rc; /* length of the path component string */ rc = next_entry(buf, fp, sizeof(u32)); if (rc) return rc; len = le32_to_cpu(buf[0]); /* path component string */ rc = str_read(&name, GFP_KERNEL, fp, len); if (rc) return rc; rc = next_entry(buf, fp, sizeof(u32) * 3); if (rc) goto out; ttype = le32_to_cpu(buf[0]); tclass = le32_to_cpu(buf[1]); ndatum = le32_to_cpu(buf[2]); if (ndatum == 0) { pr_err("SELinux: Filename transition key with no datum\n"); rc = -ENOENT; goto out; } dst = &first; for (i = 0; i < ndatum; i++) { rc = -ENOMEM; datum = kmalloc(sizeof(*datum), GFP_KERNEL); if (!datum) goto out; datum->next = NULL; *dst = datum; /* ebitmap_read() will at least init the bitmap */ rc = ebitmap_read(&datum->stypes, fp); if (rc) goto out; rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; datum->otype = le32_to_cpu(buf[0]); dst = &datum->next; } rc = -ENOMEM; ft = kmalloc(sizeof(*ft), GFP_KERNEL); if (!ft) goto out; ft->ttype = ttype; ft->tclass = tclass; ft->name = name; rc = hashtab_insert(&p->filename_trans, ft, first, filenametr_key_params); if (rc == -EEXIST) pr_err("SELinux: Duplicate filename transition key\n"); if (rc) goto out; return ebitmap_set_bit(&p->filename_trans_ttypes, ttype, 1); out: kfree(ft); kfree(name); while (first) { datum = first; first = first->next; ebitmap_destroy(&datum->stypes); kfree(datum); } return rc; } static int filename_trans_read(struct policydb *p, void *fp) { u32 nel; __le32 buf[1]; int rc, i; if (p->policyvers < POLICYDB_VERSION_FILENAME_TRANS) return 0; rc = next_entry(buf, fp, sizeof(u32)); if (rc) return rc; nel = le32_to_cpu(buf[0]); if (p->policyvers < POLICYDB_VERSION_COMP_FTRANS) { p->compat_filename_trans_count = nel; rc = hashtab_init(&p->filename_trans, (1 << 11)); if (rc) return rc; for (i = 0; i < nel; i++) { rc = filename_trans_read_helper_compat(p, fp); if (rc) return rc; } } else { rc = hashtab_init(&p->filename_trans, nel); if (rc) return rc; for (i = 0; i < nel; i++) { rc = filename_trans_read_helper(p, fp); if (rc) return rc; } } hash_eval(&p->filename_trans, "filenametr"); return 0; } static int genfs_read(struct policydb *p, void *fp) { int i, j, rc; u32 nel, nel2, len, len2; __le32 buf[1]; struct ocontext *l, *c; struct ocontext *newc = NULL; struct genfs *genfs_p, *genfs; struct genfs *newgenfs = NULL; rc = next_entry(buf, fp, sizeof(u32)); if (rc) return rc; nel = le32_to_cpu(buf[0]); for (i = 0; i < nel; i++) { rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; len = le32_to_cpu(buf[0]); rc = -ENOMEM; newgenfs = kzalloc(sizeof(*newgenfs), GFP_KERNEL); if (!newgenfs) goto out; rc = str_read(&newgenfs->fstype, GFP_KERNEL, fp, len); if (rc) goto out; for (genfs_p = NULL, genfs = p->genfs; genfs; genfs_p = genfs, genfs = genfs->next) { rc = -EINVAL; if (strcmp(newgenfs->fstype, genfs->fstype) == 0) { pr_err("SELinux: dup genfs fstype %s\n", newgenfs->fstype); goto out; } if (strcmp(newgenfs->fstype, genfs->fstype) < 0) break; } newgenfs->next = genfs; if (genfs_p) genfs_p->next = newgenfs; else p->genfs = newgenfs; genfs = newgenfs; newgenfs = NULL; rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; nel2 = le32_to_cpu(buf[0]); for (j = 0; j < nel2; j++) { rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; len = le32_to_cpu(buf[0]); rc = -ENOMEM; newc = kzalloc(sizeof(*newc), GFP_KERNEL); if (!newc) goto out; rc = str_read(&newc->u.name, GFP_KERNEL, fp, len); if (rc) goto out; rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; newc->v.sclass = le32_to_cpu(buf[0]); rc = context_read_and_validate(&newc->context[0], p, fp); if (rc) goto out; for (l = NULL, c = genfs->head; c; l = c, c = c->next) { rc = -EINVAL; if (!strcmp(newc->u.name, c->u.name) && (!c->v.sclass || !newc->v.sclass || newc->v.sclass == c->v.sclass)) { pr_err("SELinux: dup genfs entry (%s,%s)\n", genfs->fstype, c->u.name); goto out; } len = strlen(newc->u.name); len2 = strlen(c->u.name); if (len > len2) break; } newc->next = c; if (l) l->next = newc; else genfs->head = newc; newc = NULL; } } rc = 0; out: if (newgenfs) { kfree(newgenfs->fstype); kfree(newgenfs); } ocontext_destroy(newc, OCON_FSUSE); return rc; } static int ocontext_read(struct policydb *p, struct policydb_compat_info *info, void *fp) { int i, j, rc; u32 nel, len; __be64 prefixbuf[1]; __le32 buf[3]; struct ocontext *l, *c; u32 nodebuf[8]; for (i = 0; i < info->ocon_num; i++) { rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; nel = le32_to_cpu(buf[0]); l = NULL; for (j = 0; j < nel; j++) { rc = -ENOMEM; c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) goto out; if (l) l->next = c; else p->ocontexts[i] = c; l = c; switch (i) { case OCON_ISID: rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; c->sid[0] = le32_to_cpu(buf[0]); rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; case OCON_FS: case OCON_NETIF: rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; len = le32_to_cpu(buf[0]); rc = str_read(&c->u.name, GFP_KERNEL, fp, len); if (rc) goto out; rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; rc = context_read_and_validate(&c->context[1], p, fp); if (rc) goto out; break; case OCON_PORT: rc = next_entry(buf, fp, sizeof(u32)*3); if (rc) goto out; c->u.port.protocol = le32_to_cpu(buf[0]); c->u.port.low_port = le32_to_cpu(buf[1]); c->u.port.high_port = le32_to_cpu(buf[2]); rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; case OCON_NODE: rc = next_entry(nodebuf, fp, sizeof(u32) * 2); if (rc) goto out; c->u.node.addr = nodebuf[0]; /* network order */ c->u.node.mask = nodebuf[1]; /* network order */ rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; case OCON_FSUSE: rc = next_entry(buf, fp, sizeof(u32)*2); if (rc) goto out; rc = -EINVAL; c->v.behavior = le32_to_cpu(buf[0]); /* Determined at runtime, not in policy DB. */ if (c->v.behavior == SECURITY_FS_USE_MNTPOINT) goto out; if (c->v.behavior > SECURITY_FS_USE_MAX) goto out; len = le32_to_cpu(buf[1]); rc = str_read(&c->u.name, GFP_KERNEL, fp, len); if (rc) goto out; rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; case OCON_NODE6: { int k; rc = next_entry(nodebuf, fp, sizeof(u32) * 8); if (rc) goto out; for (k = 0; k < 4; k++) c->u.node6.addr[k] = nodebuf[k]; for (k = 0; k < 4; k++) c->u.node6.mask[k] = nodebuf[k+4]; rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; } case OCON_IBPKEY: { u32 pkey_lo, pkey_hi; rc = next_entry(prefixbuf, fp, sizeof(u64)); if (rc) goto out; /* we need to have subnet_prefix in CPU order */ c->u.ibpkey.subnet_prefix = be64_to_cpu(prefixbuf[0]); rc = next_entry(buf, fp, sizeof(u32) * 2); if (rc) goto out; pkey_lo = le32_to_cpu(buf[0]); pkey_hi = le32_to_cpu(buf[1]); if (pkey_lo > U16_MAX || pkey_hi > U16_MAX) { rc = -EINVAL; goto out; } c->u.ibpkey.low_pkey = pkey_lo; c->u.ibpkey.high_pkey = pkey_hi; rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; } case OCON_IBENDPORT: { u32 port; rc = next_entry(buf, fp, sizeof(u32) * 2); if (rc) goto out; len = le32_to_cpu(buf[0]); rc = str_read(&c->u.ibendport.dev_name, GFP_KERNEL, fp, len); if (rc) goto out; port = le32_to_cpu(buf[1]); if (port > U8_MAX || port == 0) { rc = -EINVAL; goto out; } c->u.ibendport.port = port; rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; } /* end case */ } /* end switch */ } } rc = 0; out: return rc; } /* * Read the configuration data from a policy database binary * representation file into a policy database structure. */ int policydb_read(struct policydb *p, void *fp) { struct role_allow *ra, *lra; struct role_trans_key *rtk = NULL; struct role_trans_datum *rtd = NULL; int i, j, rc; __le32 buf[4]; u32 len, nprim, nel, perm; char *policydb_str; struct policydb_compat_info *info; policydb_init(p); /* Read the magic number and string length. */ rc = next_entry(buf, fp, sizeof(u32) * 2); if (rc) goto bad; rc = -EINVAL; if (le32_to_cpu(buf[0]) != POLICYDB_MAGIC) { pr_err("SELinux: policydb magic number 0x%x does " "not match expected magic number 0x%x\n", le32_to_cpu(buf[0]), POLICYDB_MAGIC); goto bad; } rc = -EINVAL; len = le32_to_cpu(buf[1]); if (len != strlen(POLICYDB_STRING)) { pr_err("SELinux: policydb string length %d does not " "match expected length %zu\n", len, strlen(POLICYDB_STRING)); goto bad; } rc = -ENOMEM; policydb_str = kmalloc(len + 1, GFP_KERNEL); if (!policydb_str) { pr_err("SELinux: unable to allocate memory for policydb " "string of length %d\n", len); goto bad; } rc = next_entry(policydb_str, fp, len); if (rc) { pr_err("SELinux: truncated policydb string identifier\n"); kfree(policydb_str); goto bad; } rc = -EINVAL; policydb_str[len] = '\0'; if (strcmp(policydb_str, POLICYDB_STRING)) { pr_err("SELinux: policydb string %s does not match " "my string %s\n", policydb_str, POLICYDB_STRING); kfree(policydb_str); goto bad; } /* Done with policydb_str. */ kfree(policydb_str); policydb_str = NULL; /* Read the version and table sizes. */ rc = next_entry(buf, fp, sizeof(u32)*4); if (rc) goto bad; rc = -EINVAL; p->policyvers = le32_to_cpu(buf[0]); if (p->policyvers < POLICYDB_VERSION_MIN || p->policyvers > POLICYDB_VERSION_MAX) { pr_err("SELinux: policydb version %d does not match " "my version range %d-%d\n", le32_to_cpu(buf[0]), POLICYDB_VERSION_MIN, POLICYDB_VERSION_MAX); goto bad; } if ((le32_to_cpu(buf[1]) & POLICYDB_CONFIG_MLS)) { p->mls_enabled = 1; rc = -EINVAL; if (p->policyvers < POLICYDB_VERSION_MLS) { pr_err("SELinux: security policydb version %d " "(MLS) not backwards compatible\n", p->policyvers); goto bad; } } p->reject_unknown = !!(le32_to_cpu(buf[1]) & REJECT_UNKNOWN); p->allow_unknown = !!(le32_to_cpu(buf[1]) & ALLOW_UNKNOWN); if (p->policyvers >= POLICYDB_VERSION_POLCAP) { rc = ebitmap_read(&p->policycaps, fp); if (rc) goto bad; } if (p->policyvers >= POLICYDB_VERSION_PERMISSIVE) { rc = ebitmap_read(&p->permissive_map, fp); if (rc) goto bad; } rc = -EINVAL; info = policydb_lookup_compat(p->policyvers); if (!info) { pr_err("SELinux: unable to find policy compat info " "for version %d\n", p->policyvers); goto bad; } rc = -EINVAL; if (le32_to_cpu(buf[2]) != info->sym_num || le32_to_cpu(buf[3]) != info->ocon_num) { pr_err("SELinux: policydb table sizes (%d,%d) do " "not match mine (%d,%d)\n", le32_to_cpu(buf[2]), le32_to_cpu(buf[3]), info->sym_num, info->ocon_num); goto bad; } for (i = 0; i < info->sym_num; i++) { rc = next_entry(buf, fp, sizeof(u32)*2); if (rc) goto bad; nprim = le32_to_cpu(buf[0]); nel = le32_to_cpu(buf[1]); rc = symtab_init(&p->symtab[i], nel); if (rc) goto out; if (i == SYM_ROLES) { rc = roles_init(p); if (rc) goto out; } for (j = 0; j < nel; j++) { rc = read_f[i](p, &p->symtab[i], fp); if (rc) goto bad; } p->symtab[i].nprim = nprim; } rc = -EINVAL; p->process_class = string_to_security_class(p, "process"); if (!p->process_class) { pr_err("SELinux: process class is required, not defined in policy\n"); goto bad; } rc = avtab_read(&p->te_avtab, fp, p); if (rc) goto bad; if (p->policyvers >= POLICYDB_VERSION_BOOL) { rc = cond_read_list(p, fp); if (rc) goto bad; } rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto bad; nel = le32_to_cpu(buf[0]); rc = hashtab_init(&p->role_tr, nel); if (rc) goto bad; for (i = 0; i < nel; i++) { rc = -ENOMEM; rtk = kmalloc(sizeof(*rtk), GFP_KERNEL); if (!rtk) goto bad; rc = -ENOMEM; rtd = kmalloc(sizeof(*rtd), GFP_KERNEL); if (!rtd) goto bad; rc = next_entry(buf, fp, sizeof(u32)*3); if (rc) goto bad; rc = -EINVAL; rtk->role = le32_to_cpu(buf[0]); rtk->type = le32_to_cpu(buf[1]); rtd->new_role = le32_to_cpu(buf[2]); if (p->policyvers >= POLICYDB_VERSION_ROLETRANS) { rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto bad; rtk->tclass = le32_to_cpu(buf[0]); } else rtk->tclass = p->process_class; rc = -EINVAL; if (!policydb_role_isvalid(p, rtk->role) || !policydb_type_isvalid(p, rtk->type) || !policydb_class_isvalid(p, rtk->tclass) || !policydb_role_isvalid(p, rtd->new_role)) goto bad; rc = hashtab_insert(&p->role_tr, rtk, rtd, roletr_key_params); if (rc) goto bad; rtk = NULL; rtd = NULL; } rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto bad; nel = le32_to_cpu(buf[0]); lra = NULL; for (i = 0; i < nel; i++) { rc = -ENOMEM; ra = kzalloc(sizeof(*ra), GFP_KERNEL); if (!ra) goto bad; if (lra) lra->next = ra; else p->role_allow = ra; rc = next_entry(buf, fp, sizeof(u32)*2); if (rc) goto bad; rc = -EINVAL; ra->role = le32_to_cpu(buf[0]); ra->new_role = le32_to_cpu(buf[1]); if (!policydb_role_isvalid(p, ra->role) || !policydb_role_isvalid(p, ra->new_role)) goto bad; lra = ra; } rc = filename_trans_read(p, fp); if (rc) goto bad; rc = policydb_index(p); if (rc) goto bad; rc = -EINVAL; perm = string_to_av_perm(p, p->process_class, "transition"); if (!perm) { pr_err("SELinux: process transition permission is required, not defined in policy\n"); goto bad; } p->process_trans_perms = perm; perm = string_to_av_perm(p, p->process_class, "dyntransition"); if (!perm) { pr_err("SELinux: process dyntransition permission is required, not defined in policy\n"); goto bad; } p->process_trans_perms |= perm; rc = ocontext_read(p, info, fp); if (rc) goto bad; rc = genfs_read(p, fp); if (rc) goto bad; rc = range_read(p, fp); if (rc) goto bad; rc = -ENOMEM; p->type_attr_map_array = kvcalloc(p->p_types.nprim, sizeof(*p->type_attr_map_array), GFP_KERNEL); if (!p->type_attr_map_array) goto bad; /* just in case ebitmap_init() becomes more than just a memset(0): */ for (i = 0; i < p->p_types.nprim; i++) ebitmap_init(&p->type_attr_map_array[i]); for (i = 0; i < p->p_types.nprim; i++) { struct ebitmap *e = &p->type_attr_map_array[i]; if (p->policyvers >= POLICYDB_VERSION_AVTAB) { rc = ebitmap_read(e, fp); if (rc) goto bad; } /* add the type itself as the degenerate case */ rc = ebitmap_set_bit(e, i, 1); if (rc) goto bad; } rc = policydb_bounds_sanity_check(p); if (rc) goto bad; rc = 0; out: return rc; bad: kfree(rtk); kfree(rtd); policydb_destroy(p); goto out; } /* * Write a MLS level structure to a policydb binary * representation file. */ static int mls_write_level(struct mls_level *l, void *fp) { __le32 buf[1]; int rc; buf[0] = cpu_to_le32(l->sens); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = ebitmap_write(&l->cat, fp); if (rc) return rc; return 0; } /* * Write a MLS range structure to a policydb binary * representation file. */ static int mls_write_range_helper(struct mls_range *r, void *fp) { __le32 buf[3]; size_t items; int rc, eq; eq = mls_level_eq(&r->level[1], &r->level[0]); if (eq) items = 2; else items = 3; buf[0] = cpu_to_le32(items-1); buf[1] = cpu_to_le32(r->level[0].sens); if (!eq) buf[2] = cpu_to_le32(r->level[1].sens); BUG_ON(items > ARRAY_SIZE(buf)); rc = put_entry(buf, sizeof(u32), items, fp); if (rc) return rc; rc = ebitmap_write(&r->level[0].cat, fp); if (rc) return rc; if (!eq) { rc = ebitmap_write(&r->level[1].cat, fp); if (rc) return rc; } return 0; } static int sens_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct level_datum *levdatum = datum; struct policy_data *pd = ptr; void *fp = pd->fp; __le32 buf[2]; size_t len; int rc; len = strlen(key); buf[0] = cpu_to_le32(len); buf[1] = cpu_to_le32(levdatum->isalias); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; rc = mls_write_level(levdatum->level, fp); if (rc) return rc; return 0; } static int cat_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct cat_datum *catdatum = datum; struct policy_data *pd = ptr; void *fp = pd->fp; __le32 buf[3]; size_t len; int rc; len = strlen(key); buf[0] = cpu_to_le32(len); buf[1] = cpu_to_le32(catdatum->value); buf[2] = cpu_to_le32(catdatum->isalias); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; return 0; } static int role_trans_write_one(void *key, void *datum, void *ptr) { struct role_trans_key *rtk = key; struct role_trans_datum *rtd = datum; struct policy_data *pd = ptr; void *fp = pd->fp; struct policydb *p = pd->p; __le32 buf[3]; int rc; buf[0] = cpu_to_le32(rtk->role); buf[1] = cpu_to_le32(rtk->type); buf[2] = cpu_to_le32(rtd->new_role); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; if (p->policyvers >= POLICYDB_VERSION_ROLETRANS) { buf[0] = cpu_to_le32(rtk->tclass); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; } return 0; } static int role_trans_write(struct policydb *p, void *fp) { struct policy_data pd = { .p = p, .fp = fp }; __le32 buf[1]; int rc; buf[0] = cpu_to_le32(p->role_tr.nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; return hashtab_map(&p->role_tr, role_trans_write_one, &pd); } static int role_allow_write(struct role_allow *r, void *fp) { struct role_allow *ra; __le32 buf[2]; size_t nel; int rc; nel = 0; for (ra = r; ra; ra = ra->next) nel++; buf[0] = cpu_to_le32(nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (ra = r; ra; ra = ra->next) { buf[0] = cpu_to_le32(ra->role); buf[1] = cpu_to_le32(ra->new_role); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; } return 0; } /* * Write a security context structure * to a policydb binary representation file. */ static int context_write(struct policydb *p, struct context *c, void *fp) { int rc; __le32 buf[3]; buf[0] = cpu_to_le32(c->user); buf[1] = cpu_to_le32(c->role); buf[2] = cpu_to_le32(c->type); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; rc = mls_write_range_helper(&c->range, fp); if (rc) return rc; return 0; } /* * The following *_write functions are used to * write the symbol data to a policy database * binary representation file. */ static int perm_write(void *vkey, void *datum, void *fp) { char *key = vkey; struct perm_datum *perdatum = datum; __le32 buf[2]; size_t len; int rc; len = strlen(key); buf[0] = cpu_to_le32(len); buf[1] = cpu_to_le32(perdatum->value); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; return 0; } static int common_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct common_datum *comdatum = datum; struct policy_data *pd = ptr; void *fp = pd->fp; __le32 buf[4]; size_t len; int rc; len = strlen(key); buf[0] = cpu_to_le32(len); buf[1] = cpu_to_le32(comdatum->value); buf[2] = cpu_to_le32(comdatum->permissions.nprim); buf[3] = cpu_to_le32(comdatum->permissions.table.nel); rc = put_entry(buf, sizeof(u32), 4, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; rc = hashtab_map(&comdatum->permissions.table, perm_write, fp); if (rc) return rc; return 0; } static int type_set_write(struct type_set *t, void *fp) { int rc; __le32 buf[1]; if (ebitmap_write(&t->types, fp)) return -EINVAL; if (ebitmap_write(&t->negset, fp)) return -EINVAL; buf[0] = cpu_to_le32(t->flags); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return -EINVAL; return 0; } static int write_cons_helper(struct policydb *p, struct constraint_node *node, void *fp) { struct constraint_node *c; struct constraint_expr *e; __le32 buf[3]; u32 nel; int rc; for (c = node; c; c = c->next) { nel = 0; for (e = c->expr; e; e = e->next) nel++; buf[0] = cpu_to_le32(c->permissions); buf[1] = cpu_to_le32(nel); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; for (e = c->expr; e; e = e->next) { buf[0] = cpu_to_le32(e->expr_type); buf[1] = cpu_to_le32(e->attr); buf[2] = cpu_to_le32(e->op); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; switch (e->expr_type) { case CEXPR_NAMES: rc = ebitmap_write(&e->names, fp); if (rc) return rc; if (p->policyvers >= POLICYDB_VERSION_CONSTRAINT_NAMES) { rc = type_set_write(e->type_names, fp); if (rc) return rc; } break; default: break; } } } return 0; } static int class_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct class_datum *cladatum = datum; struct policy_data *pd = ptr; void *fp = pd->fp; struct policydb *p = pd->p; struct constraint_node *c; __le32 buf[6]; u32 ncons; size_t len, len2; int rc; len = strlen(key); if (cladatum->comkey) len2 = strlen(cladatum->comkey); else len2 = 0; ncons = 0; for (c = cladatum->constraints; c; c = c->next) ncons++; buf[0] = cpu_to_le32(len); buf[1] = cpu_to_le32(len2); buf[2] = cpu_to_le32(cladatum->value); buf[3] = cpu_to_le32(cladatum->permissions.nprim); buf[4] = cpu_to_le32(cladatum->permissions.table.nel); buf[5] = cpu_to_le32(ncons); rc = put_entry(buf, sizeof(u32), 6, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; if (cladatum->comkey) { rc = put_entry(cladatum->comkey, 1, len2, fp); if (rc) return rc; } rc = hashtab_map(&cladatum->permissions.table, perm_write, fp); if (rc) return rc; rc = write_cons_helper(p, cladatum->constraints, fp); if (rc) return rc; /* write out the validatetrans rule */ ncons = 0; for (c = cladatum->validatetrans; c; c = c->next) ncons++; buf[0] = cpu_to_le32(ncons); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = write_cons_helper(p, cladatum->validatetrans, fp); if (rc) return rc; if (p->policyvers >= POLICYDB_VERSION_NEW_OBJECT_DEFAULTS) { buf[0] = cpu_to_le32(cladatum->default_user); buf[1] = cpu_to_le32(cladatum->default_role); buf[2] = cpu_to_le32(cladatum->default_range); rc = put_entry(buf, sizeof(uint32_t), 3, fp); if (rc) return rc; } if (p->policyvers >= POLICYDB_VERSION_DEFAULT_TYPE) { buf[0] = cpu_to_le32(cladatum->default_type); rc = put_entry(buf, sizeof(uint32_t), 1, fp); if (rc) return rc; } return 0; } static int role_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct role_datum *role = datum; struct policy_data *pd = ptr; void *fp = pd->fp; struct policydb *p = pd->p; __le32 buf[3]; size_t items, len; int rc; len = strlen(key); items = 0; buf[items++] = cpu_to_le32(len); buf[items++] = cpu_to_le32(role->value); if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) buf[items++] = cpu_to_le32(role->bounds); BUG_ON(items > ARRAY_SIZE(buf)); rc = put_entry(buf, sizeof(u32), items, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; rc = ebitmap_write(&role->dominates, fp); if (rc) return rc; rc = ebitmap_write(&role->types, fp); if (rc) return rc; return 0; } static int type_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct type_datum *typdatum = datum; struct policy_data *pd = ptr; struct policydb *p = pd->p; void *fp = pd->fp; __le32 buf[4]; int rc; size_t items, len; len = strlen(key); items = 0; buf[items++] = cpu_to_le32(len); buf[items++] = cpu_to_le32(typdatum->value); if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) { u32 properties = 0; if (typdatum->primary) properties |= TYPEDATUM_PROPERTY_PRIMARY; if (typdatum->attribute) properties |= TYPEDATUM_PROPERTY_ATTRIBUTE; buf[items++] = cpu_to_le32(properties); buf[items++] = cpu_to_le32(typdatum->bounds); } else { buf[items++] = cpu_to_le32(typdatum->primary); } BUG_ON(items > ARRAY_SIZE(buf)); rc = put_entry(buf, sizeof(u32), items, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; return 0; } static int user_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct user_datum *usrdatum = datum; struct policy_data *pd = ptr; struct policydb *p = pd->p; void *fp = pd->fp; __le32 buf[3]; size_t items, len; int rc; len = strlen(key); items = 0; buf[items++] = cpu_to_le32(len); buf[items++] = cpu_to_le32(usrdatum->value); if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) buf[items++] = cpu_to_le32(usrdatum->bounds); BUG_ON(items > ARRAY_SIZE(buf)); rc = put_entry(buf, sizeof(u32), items, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; rc = ebitmap_write(&usrdatum->roles, fp); if (rc) return rc; rc = mls_write_range_helper(&usrdatum->range, fp); if (rc) return rc; rc = mls_write_level(&usrdatum->dfltlevel, fp); if (rc) return rc; return 0; } static int (*write_f[SYM_NUM]) (void *key, void *datum, void *datap) = { common_write, class_write, role_write, type_write, user_write, cond_write_bool, sens_write, cat_write, }; static int ocontext_write(struct policydb *p, struct policydb_compat_info *info, void *fp) { unsigned int i, j, rc; size_t nel, len; __be64 prefixbuf[1]; __le32 buf[3]; u32 nodebuf[8]; struct ocontext *c; for (i = 0; i < info->ocon_num; i++) { nel = 0; for (c = p->ocontexts[i]; c; c = c->next) nel++; buf[0] = cpu_to_le32(nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (c = p->ocontexts[i]; c; c = c->next) { switch (i) { case OCON_ISID: buf[0] = cpu_to_le32(c->sid[0]); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; case OCON_FS: case OCON_NETIF: len = strlen(c->u.name); buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = put_entry(c->u.name, 1, len, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; rc = context_write(p, &c->context[1], fp); if (rc) return rc; break; case OCON_PORT: buf[0] = cpu_to_le32(c->u.port.protocol); buf[1] = cpu_to_le32(c->u.port.low_port); buf[2] = cpu_to_le32(c->u.port.high_port); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; case OCON_NODE: nodebuf[0] = c->u.node.addr; /* network order */ nodebuf[1] = c->u.node.mask; /* network order */ rc = put_entry(nodebuf, sizeof(u32), 2, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; case OCON_FSUSE: buf[0] = cpu_to_le32(c->v.behavior); len = strlen(c->u.name); buf[1] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = put_entry(c->u.name, 1, len, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; case OCON_NODE6: for (j = 0; j < 4; j++) nodebuf[j] = c->u.node6.addr[j]; /* network order */ for (j = 0; j < 4; j++) nodebuf[j + 4] = c->u.node6.mask[j]; /* network order */ rc = put_entry(nodebuf, sizeof(u32), 8, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; case OCON_IBPKEY: /* subnet_prefix is in CPU order */ prefixbuf[0] = cpu_to_be64(c->u.ibpkey.subnet_prefix); rc = put_entry(prefixbuf, sizeof(u64), 1, fp); if (rc) return rc; buf[0] = cpu_to_le32(c->u.ibpkey.low_pkey); buf[1] = cpu_to_le32(c->u.ibpkey.high_pkey); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; case OCON_IBENDPORT: len = strlen(c->u.ibendport.dev_name); buf[0] = cpu_to_le32(len); buf[1] = cpu_to_le32(c->u.ibendport.port); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = put_entry(c->u.ibendport.dev_name, 1, len, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; } } } return 0; } static int genfs_write(struct policydb *p, void *fp) { struct genfs *genfs; struct ocontext *c; size_t len; __le32 buf[1]; int rc; len = 0; for (genfs = p->genfs; genfs; genfs = genfs->next) len++; buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (genfs = p->genfs; genfs; genfs = genfs->next) { len = strlen(genfs->fstype); buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = put_entry(genfs->fstype, 1, len, fp); if (rc) return rc; len = 0; for (c = genfs->head; c; c = c->next) len++; buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (c = genfs->head; c; c = c->next) { len = strlen(c->u.name); buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = put_entry(c->u.name, 1, len, fp); if (rc) return rc; buf[0] = cpu_to_le32(c->v.sclass); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; } } return 0; } static int range_write_helper(void *key, void *data, void *ptr) { __le32 buf[2]; struct range_trans *rt = key; struct mls_range *r = data; struct policy_data *pd = ptr; void *fp = pd->fp; struct policydb *p = pd->p; int rc; buf[0] = cpu_to_le32(rt->source_type); buf[1] = cpu_to_le32(rt->target_type); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; if (p->policyvers >= POLICYDB_VERSION_RANGETRANS) { buf[0] = cpu_to_le32(rt->target_class); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; } rc = mls_write_range_helper(r, fp); if (rc) return rc; return 0; } static int range_write(struct policydb *p, void *fp) { __le32 buf[1]; int rc; struct policy_data pd; pd.p = p; pd.fp = fp; buf[0] = cpu_to_le32(p->range_tr.nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; /* actually write all of the entries */ rc = hashtab_map(&p->range_tr, range_write_helper, &pd); if (rc) return rc; return 0; } static int filename_write_helper_compat(void *key, void *data, void *ptr) { struct filename_trans_key *ft = key; struct filename_trans_datum *datum = data; struct ebitmap_node *node; void *fp = ptr; __le32 buf[4]; int rc; u32 bit, len = strlen(ft->name); do { ebitmap_for_each_positive_bit(&datum->stypes, node, bit) { buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = put_entry(ft->name, sizeof(char), len, fp); if (rc) return rc; buf[0] = cpu_to_le32(bit + 1); buf[1] = cpu_to_le32(ft->ttype); buf[2] = cpu_to_le32(ft->tclass); buf[3] = cpu_to_le32(datum->otype); rc = put_entry(buf, sizeof(u32), 4, fp); if (rc) return rc; } datum = datum->next; } while (unlikely(datum)); return 0; } static int filename_write_helper(void *key, void *data, void *ptr) { struct filename_trans_key *ft = key; struct filename_trans_datum *datum; void *fp = ptr; __le32 buf[3]; int rc; u32 ndatum, len = strlen(ft->name); buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = put_entry(ft->name, sizeof(char), len, fp); if (rc) return rc; ndatum = 0; datum = data; do { ndatum++; datum = datum->next; } while (unlikely(datum)); buf[0] = cpu_to_le32(ft->ttype); buf[1] = cpu_to_le32(ft->tclass); buf[2] = cpu_to_le32(ndatum); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; datum = data; do { rc = ebitmap_write(&datum->stypes, fp); if (rc) return rc; buf[0] = cpu_to_le32(datum->otype); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; datum = datum->next; } while (unlikely(datum)); return 0; } static int filename_trans_write(struct policydb *p, void *fp) { __le32 buf[1]; int rc; if (p->policyvers < POLICYDB_VERSION_FILENAME_TRANS) return 0; if (p->policyvers < POLICYDB_VERSION_COMP_FTRANS) { buf[0] = cpu_to_le32(p->compat_filename_trans_count); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = hashtab_map(&p->filename_trans, filename_write_helper_compat, fp); } else { buf[0] = cpu_to_le32(p->filename_trans.nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = hashtab_map(&p->filename_trans, filename_write_helper, fp); } return rc; } /* * Write the configuration data in a policy database * structure to a policy database binary representation * file. */ int policydb_write(struct policydb *p, void *fp) { unsigned int i, num_syms; int rc; __le32 buf[4]; u32 config; size_t len; struct policydb_compat_info *info; /* * refuse to write policy older than compressed avtab * to simplify the writer. There are other tests dropped * since we assume this throughout the writer code. Be * careful if you ever try to remove this restriction */ if (p->policyvers < POLICYDB_VERSION_AVTAB) { pr_err("SELinux: refusing to write policy version %d." " Because it is less than version %d\n", p->policyvers, POLICYDB_VERSION_AVTAB); return -EINVAL; } config = 0; if (p->mls_enabled) config |= POLICYDB_CONFIG_MLS; if (p->reject_unknown) config |= REJECT_UNKNOWN; if (p->allow_unknown) config |= ALLOW_UNKNOWN; /* Write the magic number and string identifiers. */ buf[0] = cpu_to_le32(POLICYDB_MAGIC); len = strlen(POLICYDB_STRING); buf[1] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = put_entry(POLICYDB_STRING, 1, len, fp); if (rc) return rc; /* Write the version, config, and table sizes. */ info = policydb_lookup_compat(p->policyvers); if (!info) { pr_err("SELinux: compatibility lookup failed for policy " "version %d", p->policyvers); return -EINVAL; } buf[0] = cpu_to_le32(p->policyvers); buf[1] = cpu_to_le32(config); buf[2] = cpu_to_le32(info->sym_num); buf[3] = cpu_to_le32(info->ocon_num); rc = put_entry(buf, sizeof(u32), 4, fp); if (rc) return rc; if (p->policyvers >= POLICYDB_VERSION_POLCAP) { rc = ebitmap_write(&p->policycaps, fp); if (rc) return rc; } if (p->policyvers >= POLICYDB_VERSION_PERMISSIVE) { rc = ebitmap_write(&p->permissive_map, fp); if (rc) return rc; } num_syms = info->sym_num; for (i = 0; i < num_syms; i++) { struct policy_data pd; pd.fp = fp; pd.p = p; buf[0] = cpu_to_le32(p->symtab[i].nprim); buf[1] = cpu_to_le32(p->symtab[i].table.nel); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = hashtab_map(&p->symtab[i].table, write_f[i], &pd); if (rc) return rc; } rc = avtab_write(p, &p->te_avtab, fp); if (rc) return rc; rc = cond_write_list(p, fp); if (rc) return rc; rc = role_trans_write(p, fp); if (rc) return rc; rc = role_allow_write(p->role_allow, fp); if (rc) return rc; rc = filename_trans_write(p, fp); if (rc) return rc; rc = ocontext_write(p, info, fp); if (rc) return rc; rc = genfs_write(p, fp); if (rc) return rc; rc = range_write(p, fp); if (rc) return rc; for (i = 0; i < p->p_types.nprim; i++) { struct ebitmap *e = &p->type_attr_map_array[i]; rc = ebitmap_write(e, fp); if (rc) return rc; } return 0; } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RMAP_H #define _LINUX_RMAP_H /* * Declarations for Reverse Mapping functions in mm/rmap.c */ #include <linux/list.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/rwsem.h> #include <linux/memcontrol.h> #include <linux/highmem.h> /* * The anon_vma heads a list of private "related" vmas, to scan if * an anonymous page pointing to this anon_vma needs to be unmapped: * the vmas on the list will be related by forking, or by splitting. * * Since vmas come and go as they are split and merged (particularly * in mprotect), the mapping field of an anonymous page cannot point * directly to a vma: instead it points to an anon_vma, on whose list * the related vmas can be easily linked or unlinked. * * After unlinking the last vma on the list, we must garbage collect * the anon_vma object itself: we're guaranteed no page can be * pointing to this anon_vma once its vma list is empty. */ struct anon_vma { struct anon_vma *root; /* Root of this anon_vma tree */ struct rw_semaphore rwsem; /* W: modification, R: walking the list */ /* * The refcount is taken on an anon_vma when there is no * guarantee that the vma of page tables will exist for * the duration of the operation. A caller that takes * the reference is responsible for clearing up the * anon_vma if they are the last user on release */ atomic_t refcount; /* * Count of child anon_vmas. Equals to the count of all anon_vmas that * have ->parent pointing to this one, including itself. * * This counter is used for making decision about reusing anon_vma * instead of forking new one. See comments in function anon_vma_clone. */ unsigned long num_children; /* Count of VMAs whose ->anon_vma pointer points to this object. */ unsigned long num_active_vmas; struct anon_vma *parent; /* Parent of this anon_vma */ /* * NOTE: the LSB of the rb_root.rb_node is set by * mm_take_all_locks() _after_ taking the above lock. So the * rb_root must only be read/written after taking the above lock * to be sure to see a valid next pointer. The LSB bit itself * is serialized by a system wide lock only visible to * mm_take_all_locks() (mm_all_locks_mutex). */ /* Interval tree of private "related" vmas */ struct rb_root_cached rb_root; }; /* * The copy-on-write semantics of fork mean that an anon_vma * can become associated with multiple processes. Furthermore, * each child process will have its own anon_vma, where new * pages for that process are instantiated. * * This structure allows us to find the anon_vmas associated * with a VMA, or the VMAs associated with an anon_vma. * The "same_vma" list contains the anon_vma_chains linking * all the anon_vmas associated with this VMA. * The "rb" field indexes on an interval tree the anon_vma_chains * which link all the VMAs associated with this anon_vma. */ struct anon_vma_chain { struct vm_area_struct *vma; struct anon_vma *anon_vma; struct list_head same_vma; /* locked by mmap_lock & page_table_lock */ struct rb_node rb; /* locked by anon_vma->rwsem */ unsigned long rb_subtree_last; #ifdef CONFIG_DEBUG_VM_RB unsigned long cached_vma_start, cached_vma_last; #endif }; enum ttu_flags { TTU_MIGRATION = 0x1, /* migration mode */ TTU_MUNLOCK = 0x2, /* munlock mode */ TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */ TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */ TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */ TTU_IGNORE_HWPOISON = 0x20, /* corrupted page is recoverable */ TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible * and caller guarantees they will * do a final flush if necessary */ TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock: * caller holds it */ TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ }; #ifdef CONFIG_MMU static inline void get_anon_vma(struct anon_vma *anon_vma) { atomic_inc(&anon_vma->refcount); } void __put_anon_vma(struct anon_vma *anon_vma); static inline void put_anon_vma(struct anon_vma *anon_vma) { if (atomic_dec_and_test(&anon_vma->refcount)) __put_anon_vma(anon_vma); } static inline void anon_vma_lock_write(struct anon_vma *anon_vma) { down_write(&anon_vma->root->rwsem); } static inline void anon_vma_unlock_write(struct anon_vma *anon_vma) { up_write(&anon_vma->root->rwsem); } static inline void anon_vma_lock_read(struct anon_vma *anon_vma) { down_read(&anon_vma->root->rwsem); } static inline void anon_vma_unlock_read(struct anon_vma *anon_vma) { up_read(&anon_vma->root->rwsem); } /* * anon_vma helper functions. */ void anon_vma_init(void); /* create anon_vma_cachep */ int __anon_vma_prepare(struct vm_area_struct *); void unlink_anon_vmas(struct vm_area_struct *); int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *); int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *); static inline int anon_vma_prepare(struct vm_area_struct *vma) { if (likely(vma->anon_vma)) return 0; return __anon_vma_prepare(vma); } static inline void anon_vma_merge(struct vm_area_struct *vma, struct vm_area_struct *next) { VM_BUG_ON_VMA(vma->anon_vma != next->anon_vma, vma); unlink_anon_vmas(next); } struct anon_vma *page_get_anon_vma(struct page *page); /* bitflags for do_page_add_anon_rmap() */ #define RMAP_EXCLUSIVE 0x01 #define RMAP_COMPOUND 0x02 /* * rmap interfaces called when adding or removing pte of page */ void page_move_anon_rmap(struct page *, struct vm_area_struct *); void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, bool); void do_page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, int); void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long, bool); void page_add_file_rmap(struct page *, bool); void page_remove_rmap(struct page *, bool); void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long); static inline void page_dup_rmap(struct page *page, bool compound) { atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount); } /* * Called from mm/vmscan.c to handle paging out */ int page_referenced(struct page *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); bool try_to_unmap(struct page *, enum ttu_flags flags); /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) /* Look for migarion entries rather than present PTEs */ #define PVMW_MIGRATION (1 << 1) struct page_vma_mapped_walk { struct page *page; struct vm_area_struct *vma; unsigned long address; pmd_t *pmd; pte_t *pte; spinlock_t *ptl; unsigned int flags; }; static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) { /* HugeTLB pte is set to the relevant page table entry without pte_mapped. */ if (pvmw->pte && !PageHuge(pvmw->page)) pte_unmap(pvmw->pte); if (pvmw->ptl) spin_unlock(pvmw->ptl); } bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw); /* * Used by swapoff to help locate where page is expected in vma. */ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); /* * Cleans the PTEs of shared mappings. * (and since clean PTEs should also be readonly, write protects them too) * * returns the number of cleaned PTEs. */ int page_mkclean(struct page *); /* * called in munlock()/munmap() path to check for other vmas holding * the page mlocked. */ void try_to_munlock(struct page *); void remove_migration_ptes(struct page *old, struct page *new, bool locked); /* * Called by memory-failure.c to kill processes. */ struct anon_vma *page_lock_anon_vma_read(struct page *page); void page_unlock_anon_vma_read(struct anon_vma *anon_vma); int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); /* * rmap_walk_control: To control rmap traversing for specific needs * * arg: passed to rmap_one() and invalid_vma() * rmap_one: executed on each vma where page is mapped * done: for checking traversing termination condition * anon_lock: for getting anon_lock by optimized way rather than default * invalid_vma: for skipping uninterested vma */ struct rmap_walk_control { void *arg; /* * Return false if page table scanning in rmap_walk should be stopped. * Otherwise, return true. */ bool (*rmap_one)(struct page *page, struct vm_area_struct *vma, unsigned long addr, void *arg); int (*done)(struct page *page); struct anon_vma *(*anon_lock)(struct page *page); bool (*invalid_vma)(struct vm_area_struct *vma, void *arg); }; void rmap_walk(struct page *page, struct rmap_walk_control *rwc); void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc); #else /* !CONFIG_MMU */ #define anon_vma_init() do {} while (0) #define anon_vma_prepare(vma) (0) #define anon_vma_link(vma) do {} while (0) static inline int page_referenced(struct page *page, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { *vm_flags = 0; return 0; } #define try_to_unmap(page, refs) false static inline int page_mkclean(struct page *page) { return 0; } #endif /* CONFIG_MMU */ #endif /* _LINUX_RMAP_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/ns_common.h> #include <linux/fs_pin.h> struct mnt_namespace { atomic_t count; struct ns_common ns; struct mount * root; /* * Traversal and modification of .list is protected by either * - taking namespace_sem for write, OR * - taking namespace_sem for read AND taking .ns_lock. */ struct list_head list; spinlock_t ns_lock; struct user_namespace *user_ns; struct ucounts *ucounts; u64 seq; /* Sequence number to prevent loops */ wait_queue_head_t poll; u64 event; unsigned int mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; } __randomize_layout; struct mnt_pcp { int mnt_count; int mnt_writers; }; struct mountpoint { struct hlist_node m_hash; struct dentry *m_dentry; struct hlist_head m_list; int m_count; }; struct mount { struct hlist_node mnt_hash; struct mount *mnt_parent; struct dentry *mnt_mountpoint; struct vfsmount mnt; union { struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; #ifdef CONFIG_SMP struct mnt_pcp __percpu *mnt_pcp; #else int mnt_count; int mnt_writers; #endif struct list_head mnt_mounts; /* list of children, anchored here */ struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ struct list_head mnt_slave; /* slave list entry */ struct mount *mnt_master; /* slave is on master->mnt_slave_list */ struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ union { struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ struct hlist_node mnt_umount; }; struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; #endif int mnt_id; /* mount identifier */ int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; struct hlist_head mnt_stuck_children; } __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ static inline struct mount *real_mount(struct vfsmount *mnt) { return container_of(mnt, struct mount, mnt); } static inline int mnt_has_parent(struct mount *mnt) { return mnt != mnt->mnt_parent; } static inline int is_mounted(struct vfsmount *mnt) { /* neither detached nor internal? */ return !IS_ERR_OR_NULL(real_mount(mnt)->mnt_ns); } extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *); extern int __legitimize_mnt(struct vfsmount *, unsigned); extern bool legitimize_mnt(struct vfsmount *, unsigned); static inline bool __path_is_mountpoint(const struct path *path) { struct mount *m = __lookup_mnt(path->mnt, path->dentry); return m && likely(!(m->mnt.mnt_flags & MNT_SYNC_UMOUNT)); } extern void __detach_mounts(struct dentry *dentry); static inline void detach_mounts(struct dentry *dentry) { if (!d_mountpoint(dentry)) return; __detach_mounts(dentry); } static inline void get_mnt_ns(struct mnt_namespace *ns) { atomic_inc(&ns->count); } extern seqlock_t mount_lock; static inline void lock_mount_hash(void) { write_seqlock(&mount_lock); } static inline void unlock_mount_hash(void) { write_sequnlock(&mount_lock); } struct proc_mounts { struct mnt_namespace *ns; struct path root; int (*show)(struct seq_file *, struct vfsmount *); struct mount cursor; }; extern const struct seq_operations mounts_op; extern bool __is_local_mountpoint(struct dentry *dentry); static inline bool is_local_mountpoint(struct dentry *dentry) { if (!d_mountpoint(dentry)) return false; return __is_local_mountpoint(dentry); } static inline bool is_anon_ns(struct mnt_namespace *ns) { return ns->seq == 0; } extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 | /* * Implementation of the access vector table type. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ /* Updated: Frank Mayer <mayerf@tresys.com> and Karl MacMillan <kmacmillan@tresys.com> * * Added conditional policy language extensions * * Copyright (C) 2003 Tresys Technology, LLC * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation, version 2. * * Updated: Yuichi Nakamura <ynakam@hitachisoft.jp> * Tuned number of hash slots for avtab to reduce memory usage */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include "avtab.h" #include "policydb.h" static struct kmem_cache *avtab_node_cachep; static struct kmem_cache *avtab_xperms_cachep; /* Based on MurmurHash3, written by Austin Appleby and placed in the * public domain. */ static inline int avtab_hash(struct avtab_key *keyp, u32 mask) { static const u32 c1 = 0xcc9e2d51; static const u32 c2 = 0x1b873593; static const u32 r1 = 15; static const u32 r2 = 13; static const u32 m = 5; static const u32 n = 0xe6546b64; u32 hash = 0; #define mix(input) { \ u32 v = input; \ v *= c1; \ v = (v << r1) | (v >> (32 - r1)); \ v *= c2; \ hash ^= v; \ hash = (hash << r2) | (hash >> (32 - r2)); \ hash = hash * m + n; \ } mix(keyp->target_class); mix(keyp->target_type); mix(keyp->source_type); #undef mix hash ^= hash >> 16; hash *= 0x85ebca6b; hash ^= hash >> 13; hash *= 0xc2b2ae35; hash ^= hash >> 16; return hash & mask; } static struct avtab_node* avtab_insert_node(struct avtab *h, int hvalue, struct avtab_node *prev, struct avtab_node *cur, struct avtab_key *key, struct avtab_datum *datum) { struct avtab_node *newnode; struct avtab_extended_perms *xperms; newnode = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL); if (newnode == NULL) return NULL; newnode->key = *key; if (key->specified & AVTAB_XPERMS) { xperms = kmem_cache_zalloc(avtab_xperms_cachep, GFP_KERNEL); if (xperms == NULL) { kmem_cache_free(avtab_node_cachep, newnode); return NULL; } *xperms = *(datum->u.xperms); newnode->datum.u.xperms = xperms; } else { newnode->datum.u.data = datum->u.data; } if (prev) { newnode->next = prev->next; prev->next = newnode; } else { struct avtab_node **n = &h->htable[hvalue]; newnode->next = *n; *n = newnode; } h->nel++; return newnode; } static int avtab_insert(struct avtab *h, struct avtab_key *key, struct avtab_datum *datum) { int hvalue; struct avtab_node *prev, *cur, *newnode; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); if (!h || !h->nslot) return -EINVAL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class == cur->key.target_class && (specified & cur->key.specified)) { /* extended perms may not be unique */ if (specified & AVTAB_XPERMS) break; return -EEXIST; } if (key->source_type < cur->key.source_type) break; if (key->source_type == cur->key.source_type && key->target_type < cur->key.target_type) break; if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class < cur->key.target_class) break; } newnode = avtab_insert_node(h, hvalue, prev, cur, key, datum); if (!newnode) return -ENOMEM; return 0; } /* Unlike avtab_insert(), this function allow multiple insertions of the same * key/specified mask into the table, as needed by the conditional avtab. * It also returns a pointer to the node inserted. */ struct avtab_node * avtab_insert_nonunique(struct avtab *h, struct avtab_key *key, struct avtab_datum *datum) { int hvalue; struct avtab_node *prev, *cur; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class == cur->key.target_class && (specified & cur->key.specified)) break; if (key->source_type < cur->key.source_type) break; if (key->source_type == cur->key.source_type && key->target_type < cur->key.target_type) break; if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class < cur->key.target_class) break; } return avtab_insert_node(h, hvalue, prev, cur, key, datum); } struct avtab_datum *avtab_search(struct avtab *h, struct avtab_key *key) { int hvalue; struct avtab_node *cur; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (cur = h->htable[hvalue]; cur; cur = cur->next) { if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class == cur->key.target_class && (specified & cur->key.specified)) return &cur->datum; if (key->source_type < cur->key.source_type) break; if (key->source_type == cur->key.source_type && key->target_type < cur->key.target_type) break; if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class < cur->key.target_class) break; } return NULL; } /* This search function returns a node pointer, and can be used in * conjunction with avtab_search_next_node() */ struct avtab_node* avtab_search_node(struct avtab *h, struct avtab_key *key) { int hvalue; struct avtab_node *cur; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (cur = h->htable[hvalue]; cur; cur = cur->next) { if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class == cur->key.target_class && (specified & cur->key.specified)) return cur; if (key->source_type < cur->key.source_type) break; if (key->source_type == cur->key.source_type && key->target_type < cur->key.target_type) break; if (key->source_type == cur->key.source_type && key->target_type == cur->key.target_type && key->target_class < cur->key.target_class) break; } return NULL; } struct avtab_node* avtab_search_node_next(struct avtab_node *node, int specified) { struct avtab_node *cur; if (!node) return NULL; specified &= ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); for (cur = node->next; cur; cur = cur->next) { if (node->key.source_type == cur->key.source_type && node->key.target_type == cur->key.target_type && node->key.target_class == cur->key.target_class && (specified & cur->key.specified)) return cur; if (node->key.source_type < cur->key.source_type) break; if (node->key.source_type == cur->key.source_type && node->key.target_type < cur->key.target_type) break; if (node->key.source_type == cur->key.source_type && node->key.target_type == cur->key.target_type && node->key.target_class < cur->key.target_class) break; } return NULL; } void avtab_destroy(struct avtab *h) { int i; struct avtab_node *cur, *temp; if (!h) return; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; while (cur) { temp = cur; cur = cur->next; if (temp->key.specified & AVTAB_XPERMS) kmem_cache_free(avtab_xperms_cachep, temp->datum.u.xperms); kmem_cache_free(avtab_node_cachep, temp); } } kvfree(h->htable); h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } void avtab_init(struct avtab *h) { h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } static int avtab_alloc_common(struct avtab *h, u32 nslot) { if (!nslot) return 0; h->htable = kvcalloc(nslot, sizeof(void *), GFP_KERNEL); if (!h->htable) return -ENOMEM; h->nslot = nslot; h->mask = nslot - 1; return 0; } int avtab_alloc(struct avtab *h, u32 nrules) { int rc; u32 nslot = 0; if (nrules != 0) { u32 shift = 1; u32 work = nrules >> 3; while (work) { work >>= 1; shift++; } nslot = 1 << shift; if (nslot > MAX_AVTAB_HASH_BUCKETS) nslot = MAX_AVTAB_HASH_BUCKETS; rc = avtab_alloc_common(h, nslot); if (rc) return rc; } pr_debug("SELinux: %d avtab hash slots, %d rules.\n", nslot, nrules); return 0; } int avtab_alloc_dup(struct avtab *new, const struct avtab *orig) { return avtab_alloc_common(new, orig->nslot); } void avtab_hash_eval(struct avtab *h, char *tag) { int i, chain_len, slots_used, max_chain_len; unsigned long long chain2_len_sum; struct avtab_node *cur; slots_used = 0; max_chain_len = 0; chain2_len_sum = 0; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; if (cur) { slots_used++; chain_len = 0; while (cur) { chain_len++; cur = cur->next; } if (chain_len > max_chain_len) max_chain_len = chain_len; chain2_len_sum += chain_len * chain_len; } } pr_debug("SELinux: %s: %d entries and %d/%d buckets used, " "longest chain length %d sum of chain length^2 %llu\n", tag, h->nel, slots_used, h->nslot, max_chain_len, chain2_len_sum); } static uint16_t spec_order[] = { AVTAB_ALLOWED, AVTAB_AUDITDENY, AVTAB_AUDITALLOW, AVTAB_TRANSITION, AVTAB_CHANGE, AVTAB_MEMBER, AVTAB_XPERMS_ALLOWED, AVTAB_XPERMS_AUDITALLOW, AVTAB_XPERMS_DONTAUDIT }; int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol, int (*insertf)(struct avtab *a, struct avtab_key *k, struct avtab_datum *d, void *p), void *p) { __le16 buf16[4]; u16 enabled; u32 items, items2, val, vers = pol->policyvers; struct avtab_key key; struct avtab_datum datum; struct avtab_extended_perms xperms; __le32 buf32[ARRAY_SIZE(xperms.perms.p)]; int i, rc; unsigned set; memset(&key, 0, sizeof(struct avtab_key)); memset(&datum, 0, sizeof(struct avtab_datum)); if (vers < POLICYDB_VERSION_AVTAB) { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items2 = le32_to_cpu(buf32[0]); if (items2 > ARRAY_SIZE(buf32)) { pr_err("SELinux: avtab: entry overflow\n"); return -EINVAL; } rc = next_entry(buf32, fp, sizeof(u32)*items2); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; val = le32_to_cpu(buf32[items++]); key.source_type = (u16)val; if (key.source_type != val) { pr_err("SELinux: avtab: truncated source type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_type = (u16)val; if (key.target_type != val) { pr_err("SELinux: avtab: truncated target type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_class = (u16)val; if (key.target_class != val) { pr_err("SELinux: avtab: truncated target class\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); enabled = (val & AVTAB_ENABLED_OLD) ? AVTAB_ENABLED : 0; if (!(val & (AVTAB_AV | AVTAB_TYPE))) { pr_err("SELinux: avtab: null entry\n"); return -EINVAL; } if ((val & AVTAB_AV) && (val & AVTAB_TYPE)) { pr_err("SELinux: avtab: entry has both access vectors and types\n"); return -EINVAL; } if (val & AVTAB_XPERMS) { pr_err("SELinux: avtab: entry has extended permissions\n"); return -EINVAL; } for (i = 0; i < ARRAY_SIZE(spec_order); i++) { if (val & spec_order[i]) { key.specified = spec_order[i] | enabled; datum.u.data = le32_to_cpu(buf32[items++]); rc = insertf(a, &key, &datum, p); if (rc) return rc; } } if (items != items2) { pr_err("SELinux: avtab: entry only had %d items, expected %d\n", items2, items); return -EINVAL; } return 0; } rc = next_entry(buf16, fp, sizeof(u16)*4); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; key.source_type = le16_to_cpu(buf16[items++]); key.target_type = le16_to_cpu(buf16[items++]); key.target_class = le16_to_cpu(buf16[items++]); key.specified = le16_to_cpu(buf16[items++]); if (!policydb_type_isvalid(pol, key.source_type) || !policydb_type_isvalid(pol, key.target_type) || !policydb_class_isvalid(pol, key.target_class)) { pr_err("SELinux: avtab: invalid type or class\n"); return -EINVAL; } set = 0; for (i = 0; i < ARRAY_SIZE(spec_order); i++) { if (key.specified & spec_order[i]) set++; } if (!set || set > 1) { pr_err("SELinux: avtab: more than one specifier\n"); return -EINVAL; } if ((vers < POLICYDB_VERSION_XPERMS_IOCTL) && (key.specified & AVTAB_XPERMS)) { pr_err("SELinux: avtab: policy version %u does not " "support extended permissions rules and one " "was specified\n", vers); return -EINVAL; } else if (key.specified & AVTAB_XPERMS) { memset(&xperms, 0, sizeof(struct avtab_extended_perms)); rc = next_entry(&xperms.specified, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(&xperms.driver, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(buf32, fp, sizeof(u32)*ARRAY_SIZE(xperms.perms.p)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } for (i = 0; i < ARRAY_SIZE(xperms.perms.p); i++) xperms.perms.p[i] = le32_to_cpu(buf32[i]); datum.u.xperms = &xperms; } else { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } datum.u.data = le32_to_cpu(*buf32); } if ((key.specified & AVTAB_TYPE) && !policydb_type_isvalid(pol, datum.u.data)) { pr_err("SELinux: avtab: invalid type\n"); return -EINVAL; } return insertf(a, &key, &datum, p); } static int avtab_insertf(struct avtab *a, struct avtab_key *k, struct avtab_datum *d, void *p) { return avtab_insert(a, k, d); } int avtab_read(struct avtab *a, void *fp, struct policydb *pol) { int rc; __le32 buf[1]; u32 nel, i; rc = next_entry(buf, fp, sizeof(u32)); if (rc < 0) { pr_err("SELinux: avtab: truncated table\n"); goto bad; } nel = le32_to_cpu(buf[0]); if (!nel) { pr_err("SELinux: avtab: table is empty\n"); rc = -EINVAL; goto bad; } rc = avtab_alloc(a, nel); if (rc) goto bad; for (i = 0; i < nel; i++) { rc = avtab_read_item(a, fp, pol, avtab_insertf, NULL); if (rc) { if (rc == -ENOMEM) pr_err("SELinux: avtab: out of memory\n"); else if (rc == -EEXIST) pr_err("SELinux: avtab: duplicate entry\n"); goto bad; } } rc = 0; out: return rc; bad: avtab_destroy(a); goto out; } int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp) { __le16 buf16[4]; __le32 buf32[ARRAY_SIZE(cur->datum.u.xperms->perms.p)]; int rc; unsigned int i; buf16[0] = cpu_to_le16(cur->key.source_type); buf16[1] = cpu_to_le16(cur->key.target_type); buf16[2] = cpu_to_le16(cur->key.target_class); buf16[3] = cpu_to_le16(cur->key.specified); rc = put_entry(buf16, sizeof(u16), 4, fp); if (rc) return rc; if (cur->key.specified & AVTAB_XPERMS) { rc = put_entry(&cur->datum.u.xperms->specified, sizeof(u8), 1, fp); if (rc) return rc; rc = put_entry(&cur->datum.u.xperms->driver, sizeof(u8), 1, fp); if (rc) return rc; for (i = 0; i < ARRAY_SIZE(cur->datum.u.xperms->perms.p); i++) buf32[i] = cpu_to_le32(cur->datum.u.xperms->perms.p[i]); rc = put_entry(buf32, sizeof(u32), ARRAY_SIZE(cur->datum.u.xperms->perms.p), fp); } else { buf32[0] = cpu_to_le32(cur->datum.u.data); rc = put_entry(buf32, sizeof(u32), 1, fp); } if (rc) return rc; return 0; } int avtab_write(struct policydb *p, struct avtab *a, void *fp) { unsigned int i; int rc = 0; struct avtab_node *cur; __le32 buf[1]; buf[0] = cpu_to_le32(a->nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (i = 0; i < a->nslot; i++) { for (cur = a->htable[i]; cur; cur = cur->next) { rc = avtab_write_item(p, cur, fp); if (rc) return rc; } } return rc; } void __init avtab_cache_init(void) { avtab_node_cachep = kmem_cache_create("avtab_node", sizeof(struct avtab_node), 0, SLAB_PANIC, NULL); avtab_xperms_cachep = kmem_cache_create("avtab_extended_perms", sizeof(struct avtab_extended_perms), 0, SLAB_PANIC, NULL); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/filemap.c * * Copyright (C) 1994-1999 Linus Torvalds */ /* * This file handles the generic file mmap semantics used by * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ #include <linux/export.h> #include <linux/compiler.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/error-injection.h> #include <linux/hash.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> #include <linux/blkdev.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/cleancache.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/filemap.h> /* * FIXME: remove all knowledge of the buffer layer from the core VM */ #include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. * * Shared mappings now work. 15.8.1995 Bruno. * * finished 'unifying' the page and buffer cache and SMP-threaded the * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com> * * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de> */ /* * Lock ordering: * * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->__set_page_dirty_buffers) * ->swap_lock (exclusive_swap_page, others) * ->i_pages lock * * ->i_mutex * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_lock * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_lock * ->lock_page (access_process_vm) * * ->i_mutex (generic_perform_write) * ->mmap_lock (fault_in_pages_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) * ->i_pages lock (__sync_single_inode) * * ->i_mmap_rwsem * ->anon_vma.lock (vma_adjust) * * ->anon_vma.lock * ->page_table_lock or pte_lock (anon_vma_prepare and various) * * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) * ->pgdat->lru_lock (follow_page->mark_page_accessed) * ->pgdat->lru_lock (check_pte_range->isolate_lru_page) * ->private_lock (page_remove_rmap->set_page_dirty) * ->i_pages lock (page_remove_rmap->set_page_dirty) * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) * ->inode->i_lock (page_remove_rmap->set_page_dirty) * ->memcg->move_lock (page_remove_rmap->lock_page_memcg) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) * * ->i_mmap_rwsem * ->tasklist_lock (memory_failure, collect_procs_ao) */ static void page_cache_delete(struct address_space *mapping, struct page *page, void *shadow) { XA_STATE(xas, &mapping->i_pages, page->index); unsigned int nr = 1; mapping_set_update(&xas, mapping); /* hugetlb pages are represented by a single entry in the xarray */ if (!PageHuge(page)) { xas_set_order(&xas, page->index, compound_order(page)); nr = compound_nr(page); } VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(nr != 1 && shadow, page); xas_store(&xas, shadow); xas_init_marks(&xas); page->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ if (shadow) { mapping->nrexceptional += nr; /* * Make sure the nrexceptional update is committed before * the nrpages update so that final truncate racing * with reclaim does not see both counters 0 at the * same time and miss a shadow entry. */ smp_wmb(); } mapping->nrpages -= nr; } static void unaccount_page_cache_page(struct address_space *mapping, struct page *page) { int nr; /* * if we're uptodate, flush out into the cleancache, otherwise * invalidate any existing cleancache entries. We can't leave * stale data around in the cleancache once our page is gone */ if (PageUptodate(page) && PageMappedToDisk(page)) cleancache_put_page(page); else cleancache_invalidate_page(mapping, page); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_mapped(page), page); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) { int mapcount; pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); dump_page(page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); mapcount = page_mapcount(page); if (mapping_exiting(mapping) && page_count(page) >= mapcount + 2) { /* * All vmas have already been torn down, so it's * a good bet that actually the page is unmapped, * and we'd prefer not to leak it: if we're wrong, * some other bad page check should catch it later. */ page_mapcount_reset(page); page_ref_sub(page, mapcount); } } /* hugetlb pages do not participate in page cache accounting. */ if (PageHuge(page)) return; nr = thp_nr_pages(page); __mod_lruvec_page_state(page, NR_FILE_PAGES, -nr); if (PageSwapBacked(page)) { __mod_lruvec_page_state(page, NR_SHMEM, -nr); if (PageTransHuge(page)) __dec_node_page_state(page, NR_SHMEM_THPS); } else if (PageTransHuge(page)) { __dec_node_page_state(page, NR_FILE_THPS); filemap_nr_thps_dec(mapping); } /* * At this point page must be either written or cleaned by * truncate. Dirty page here signals a bug and loss of * unwritten data. * * This fixes dirty accounting after removing the page entirely * but leaves PageDirty set: it has no effect for truncated * page and anyway will be cleared before returning page into * buddy allocator. */ if (WARN_ON_ONCE(PageDirty(page))) account_page_cleaned(page, mapping, inode_to_wb(mapping->host)); } /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ void __delete_from_page_cache(struct page *page, void *shadow) { struct address_space *mapping = page->mapping; trace_mm_filemap_delete_from_page_cache(page); unaccount_page_cache_page(mapping, page); page_cache_delete(mapping, page, shadow); } static void page_cache_free_page(struct address_space *mapping, struct page *page) { void (*freepage)(struct page *); freepage = mapping->a_ops->freepage; if (freepage) freepage(page); if (PageTransHuge(page) && !PageHuge(page)) { page_ref_sub(page, thp_nr_pages(page)); VM_BUG_ON_PAGE(page_count(page) <= 0, page); } else { put_page(page); } } /** * delete_from_page_cache - delete page from page cache * @page: the page which the kernel is trying to remove from page cache * * This must be called only on pages that have been verified to be in the page * cache and locked. It will never put the page into the free list, the caller * has a reference on the page. */ void delete_from_page_cache(struct page *page) { struct address_space *mapping = page_mapping(page); unsigned long flags; BUG_ON(!PageLocked(page)); xa_lock_irqsave(&mapping->i_pages, flags); __delete_from_page_cache(page, NULL); xa_unlock_irqrestore(&mapping->i_pages, flags); page_cache_free_page(mapping, page); } EXPORT_SYMBOL(delete_from_page_cache); /* * page_cache_delete_batch - delete several pages from page cache * @mapping: the mapping to which pages belong * @pvec: pagevec with pages to delete * * The function walks over mapping->i_pages and removes pages passed in @pvec * from the mapping. The function expects @pvec to be sorted by page index * and is optimised for it to be dense. * It tolerates holes in @pvec (mapping entries at those indices are not * modified). The function expects only THP head pages to be present in the * @pvec. * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, struct pagevec *pvec) { XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index); int total_pages = 0; int i = 0; struct page *page; mapping_set_update(&xas, mapping); xas_for_each(&xas, page, ULONG_MAX) { if (i >= pagevec_count(pvec)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ if (xa_is_value(page)) continue; /* * A page got inserted in our range? Skip it. We have our * pages locked so they are protected from being removed. * If we see a page whose index is higher than ours, it * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ if (page != pvec->pages[i]) { VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index, page); continue; } WARN_ON_ONCE(!PageLocked(page)); if (page->index == xas.xa_index) page->mapping = NULL; /* Leave page->index set: truncation lookup relies on it */ /* * Move to the next page in the vector if this is a regular * page or the index is of the last sub-page of this compound * page. */ if (page->index + compound_nr(page) - 1 == xas.xa_index) i++; xas_store(&xas, NULL); total_pages++; } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec) { int i; unsigned long flags; if (!pagevec_count(pvec)) return; xa_lock_irqsave(&mapping->i_pages, flags); for (i = 0; i < pagevec_count(pvec); i++) { trace_mm_filemap_delete_from_page_cache(pvec->pages[i]); unaccount_page_cache_page(mapping, pvec->pages[i]); } page_cache_delete_batch(mapping, pvec); xa_unlock_irqrestore(&mapping->i_pages, flags); for (i = 0; i < pagevec_count(pvec); i++) page_cache_free_page(mapping, pvec->pages[i]); } int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ if (test_bit(AS_ENOSPC, &mapping->flags) && test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; if (test_bit(AS_EIO, &mapping->flags) && test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } EXPORT_SYMBOL(filemap_check_errors); static int filemap_check_and_keep_errors(struct address_space *mapping) { /* Check for outstanding write errors */ if (test_bit(AS_EIO, &mapping->flags)) return -EIO; if (test_bit(AS_ENOSPC, &mapping->flags)) return -ENOSPC; return 0; } /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts * @end: offset in bytes where the range ends (inclusive) * @sync_mode: enable synchronous operation * * Start writeback against all of a mapping's dirty pages that lie * within the byte offsets <start, end> inclusive. * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as * opposed to a regular memory cleansing writeback. The difference between * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. * * Return: %0 on success, negative error code otherwise. */ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode) { int ret; struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; if (!mapping_can_writeback(mapping) || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; wbc_attach_fdatawrite_inode(&wbc, mapping->host); ret = do_writepages(mapping, &wbc); wbc_detach_inode(&wbc); return ret; } static inline int __filemap_fdatawrite(struct address_space *mapping, int sync_mode) { return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); } int filemap_fdatawrite(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end) { return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite_range); /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_NONE); } EXPORT_SYMBOL(filemap_flush); /** * filemap_range_has_page - check if a page exists in range. * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. * * Return: %true if at least one page exists in the specified range, * %false otherwise. */ bool filemap_range_has_page(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { struct page *page; XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; if (end_byte < start_byte) return false; rcu_read_lock(); for (;;) { page = xas_find(&xas, max); if (xas_retry(&xas, page)) continue; /* Shadow entries don't count */ if (xa_is_value(page)) continue; /* * We don't need to try to pin this page; we're about to * release the RCU lock anyway. It is enough to know that * there was a page here recently. */ break; } rcu_read_unlock(); return page != NULL; } EXPORT_SYMBOL(filemap_range_has_page); static void __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { pgoff_t index = start_byte >> PAGE_SHIFT; pgoff_t end = end_byte >> PAGE_SHIFT; struct pagevec pvec; int nr_pages; if (end_byte < start_byte) return; pagevec_init(&pvec); while (index <= end) { unsigned i; nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, PAGECACHE_TAG_WRITEBACK); if (!nr_pages) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; wait_on_page_writeback(page); ClearPageError(page); } pagevec_release(&pvec); cond_resched(); } } /** * filemap_fdatawait_range - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space * in the given range and wait for all of them. Check error status of * the address space and return it. * * Since the error status of the address space is cleared by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space. */ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait_range_keep_errors - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space in the * given range and wait for all of them. Unlike filemap_fdatawait_range(), * this function does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) */ int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the address space that file * refers to, in the given range and wait for all of them. Check error * status of the address space vs. the file->f_wb_err cursor and return it. * * Since the error status of the file is advanced by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space vs. the file->f_wb_err cursor. */ int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte) { struct address_space *mapping = file->f_mapping; __filemap_fdatawait_range(mapping, start_byte, end_byte); return file_check_and_advance_wb_err(file); } EXPORT_SYMBOL(file_fdatawait_range); /** * filemap_fdatawait_keep_errors - wait for writeback without clearing errors * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. Unlike filemap_fdatawait(), this function * does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) * * Return: error status of the address space. */ int filemap_fdatawait_keep_errors(struct address_space *mapping) { __filemap_fdatawait_range(mapping, 0, LLONG_MAX); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { if (dax_mapping(mapping)) return mapping->nrexceptional; return mapping->nrpages; } /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * Return: error status of the address space. */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { int err = 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* * Even if the above returned error, the pages may be * written partially (e.g. -ENOSPC), so we wait for it. * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ if (err != -EIO) { int err2 = filemap_fdatawait_range(mapping, lstart, lend); if (!err) err = err2; } else { /* Clear any previously stored errors */ filemap_check_errors(mapping); } } else { err = filemap_check_errors(mapping); } return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); void __filemap_set_wb_err(struct address_space *mapping, int err) { errseq_t eseq = errseq_set(&mapping->wb_err, err); trace_filemap_set_wb_err(mapping, eseq); } EXPORT_SYMBOL(__filemap_set_wb_err); /** * file_check_and_advance_wb_err - report wb error (if any) that was previously * and advance wb_err to current one * @file: struct file on which the error is being reported * * When userland calls fsync (or something like nfsd does the equivalent), we * want to report any writeback errors that occurred since the last fsync (or * since the file was opened if there haven't been any). * * Grab the wb_err from the mapping. If it matches what we have in the file, * then just quickly return 0. The file is all caught up. * * If it doesn't match, then take the mapping value, set the "seen" flag in * it and try to swap it into place. If it works, or another task beat us * to it with the new value, then update the f_wb_err and return the error * portion. The error at this point must be reported via proper channels * (a'la fsync, or NFS COMMIT operation, etc.). * * While we handle mapping->wb_err with atomic operations, the f_wb_err * value is protected by the f_lock since we must ensure that it reflects * the latest value swapped in for this file descriptor. * * Return: %0 on success, negative error code otherwise. */ int file_check_and_advance_wb_err(struct file *file) { int err = 0; errseq_t old = READ_ONCE(file->f_wb_err); struct address_space *mapping = file->f_mapping; /* Locklessly handle the common case where nothing has changed */ if (errseq_check(&mapping->wb_err, old)) { /* Something changed, must use slow path */ spin_lock(&file->f_lock); old = file->f_wb_err; err = errseq_check_and_advance(&mapping->wb_err, &file->f_wb_err); trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } /* * We're mostly using this function as a drop in replacement for * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect * that the legacy code would have had on these flags. */ clear_bit(AS_EIO, &mapping->flags); clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); /** * file_write_and_wait_range - write out & wait on a file range * @file: file pointing to address_space with pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * After writing out and waiting on the data, we check and advance the * f_wb_err cursor to the latest value, and return any errors detected there. * * Return: %0 on success, negative error code otherwise. */ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) { int err = 0, err2; struct address_space *mapping = file->f_mapping; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = file_check_and_advance_wb_err(file); if (!err) err = err2; return err; } EXPORT_SYMBOL(file_write_and_wait_range); /** * replace_page_cache_page - replace a pagecache page with a new one * @old: page to be replaced * @new: page to replace with * @gfp_mask: allocation mode * * This function replaces a page in the pagecache with a new one. On * success it acquires the pagecache reference for the new page and * drops it for the old page. Both the old and new pages must be * locked. This function does not add the new page to the LRU, the * caller must do that. * * The remove + add is atomic. This function cannot fail. * * Return: %0 */ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) { struct address_space *mapping = old->mapping; void (*freepage)(struct page *) = mapping->a_ops->freepage; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); unsigned long flags; VM_BUG_ON_PAGE(!PageLocked(old), old); VM_BUG_ON_PAGE(!PageLocked(new), new); VM_BUG_ON_PAGE(new->mapping, new); get_page(new); new->mapping = mapping; new->index = offset; mem_cgroup_migrate(old, new); xas_lock_irqsave(&xas, flags); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!PageHuge(old)) __dec_lruvec_page_state(old, NR_FILE_PAGES); if (!PageHuge(new)) __inc_lruvec_page_state(new, NR_FILE_PAGES); if (PageSwapBacked(old)) __dec_lruvec_page_state(old, NR_SHMEM); if (PageSwapBacked(new)) __inc_lruvec_page_state(new, NR_SHMEM); xas_unlock_irqrestore(&xas, flags); if (freepage) freepage(old); put_page(old); return 0; } EXPORT_SYMBOL_GPL(replace_page_cache_page); noinline int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp, void **shadowp) { XA_STATE(xas, &mapping->i_pages, offset); int huge = PageHuge(page); int error; bool charged = false; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageSwapBacked(page), page); mapping_set_update(&xas, mapping); get_page(page); page->mapping = mapping; page->index = offset; if (!huge) { error = mem_cgroup_charge(page, current->mm, gfp); if (error) goto error; charged = true; } gfp &= GFP_RECLAIM_MASK; do { unsigned int order = xa_get_order(xas.xa, xas.xa_index); void *entry, *old = NULL; if (order > thp_order(page)) xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), order, gfp); xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; if (!xa_is_value(entry)) { xas_set_err(&xas, -EEXIST); goto unlock; } } if (old) { if (shadowp) *shadowp = old; /* entry may have been split before we acquired lock */ order = xa_get_order(xas.xa, xas.xa_index); if (order > thp_order(page)) { xas_split(&xas, old, order); xas_reset(&xas); } } xas_store(&xas, page); if (xas_error(&xas)) goto unlock; if (old) mapping->nrexceptional--; mapping->nrpages++; /* hugetlb pages do not participate in page cache accounting */ if (!huge) __inc_lruvec_page_state(page, NR_FILE_PAGES); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { error = xas_error(&xas); if (charged) mem_cgroup_uncharge(page); goto error; } trace_mm_filemap_add_to_page_cache(page); return 0; error: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ put_page(page); return error; } ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); /** * add_to_page_cache_locked - add a locked page to the pagecache * @page: page to add * @mapping: the page's address_space * @offset: page index * @gfp_mask: page allocation mode * * This function is used to add a page to the pagecache. It must be locked. * This function does not add the page to the LRU. The caller must do that. * * Return: %0 on success, negative error code otherwise. */ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { return __add_to_page_cache_locked(page, mapping, offset, gfp_mask, NULL); } EXPORT_SYMBOL(add_to_page_cache_locked); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { void *shadow = NULL; int ret; __SetPageLocked(page); ret = __add_to_page_cache_locked(page, mapping, offset, gfp_mask, &shadow); if (unlikely(ret)) __ClearPageLocked(page); else { /* * The page might have been evicted from cache only * recently, in which case it should be activated like * any other repeatedly accessed page. * The exception is pages getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ WARN_ON_ONCE(PageActive(page)); if (!(gfp_mask & __GFP_WRITE) && shadow) workingset_refault(page, shadow); lru_cache_add(page); } return ret; } EXPORT_SYMBOL_GPL(add_to_page_cache_lru); #ifdef CONFIG_NUMA struct page *__page_cache_alloc(gfp_t gfp) { int n; struct page *page; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); page = __alloc_pages_node(n, gfp, 0); } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); return page; } return alloc_pages(gfp, 0); } EXPORT_SYMBOL(__page_cache_alloc); #endif /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all * waiters on the same queue and wake all when any of the pages * become available, and for the woken contexts to check to be * sure the appropriate page became available, this saves space * at a cost of "thundering herd" phenomena during rare hash * collisions. */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; static wait_queue_head_t *page_waitqueue(struct page *page) { return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)]; } void __init pagecache_init(void) { int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) init_waitqueue_head(&page_wait_table[i]); page_writeback_init(); } /* * The page wait code treats the "wait->flags" somewhat unusually, because * we have multiple different kinds of waits, not just the usual "exclusive" * one. * * We have: * * (a) no special bits set: * * We're just waiting for the bit to be released, and when a waker * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, * and remove it from the wait queue. * * Simple and straightforward. * * (b) WQ_FLAG_EXCLUSIVE: * * The waiter is waiting to get the lock, and only one waiter should * be woken up to avoid any thundering herd behavior. We'll set the * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. * * This is the traditional exclusive wait. * * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: * * The waiter is waiting to get the bit, and additionally wants the * lock to be transferred to it for fair lock behavior. If the lock * cannot be taken, we stop walking the wait queue without waking * the waiter. * * This is the "fair lock handoff" case, and in addition to setting * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see * that it now has the lock. */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); if (!wake_page_match(wait_page, key)) return 0; /* * If it's a lock handoff wait, we get the bit for it, and * stop walking (and do not wake it up) if we can't. */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { if (test_bit(key->bit_nr, &key->page->flags)) return -1; if (flags & WQ_FLAG_CUSTOM) { if (test_and_set_bit(key->bit_nr, &key->page->flags)) return -1; flags |= WQ_FLAG_DONE; } } /* * We are holding the wait-queue lock, but the waiter that * is waiting for this will be checking the flags without * any locking. * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs * with the load-acquire in wait_on_page_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); /* * Ok, we have successfully done what we're waiting for, * and we can unconditionally remove the wait entry. * * Note that this pairs with the "finish_wait()" in the * waiter, and has to be the absolute last thing we do. * After this list_del_init(&wait->entry) the wait entry * might be de-allocated and the process might even have * exited. */ list_del_init_careful(&wait->entry); return (flags & WQ_FLAG_EXCLUSIVE) != 0; } static void wake_up_page_bit(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); struct wait_page_key key; unsigned long flags; wait_queue_entry_t bookmark; key.page = page; key.bit_nr = bit_nr; key.page_match = 0; bookmark.flags = 0; bookmark.private = NULL; bookmark.func = NULL; INIT_LIST_HEAD(&bookmark.entry); spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark); while (bookmark.flags & WQ_FLAG_BOOKMARK) { /* * Take a breather from holding the lock, * allow pages that finish wake up asynchronously * to acquire the lock and remove themselves * from wait queue */ spin_unlock_irqrestore(&q->lock, flags); cpu_relax(); spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key_bookmark(q, TASK_NORMAL, &key, &bookmark); } /* * It is possible for other pages to have collided on the waitqueue * hash, so in that case check for a page match. That prevents a long- * term waiter * * It is still possible to miss a case here, when we woke page waiters * and removed them from the waitqueue, but there are still other * page waiters. */ if (!waitqueue_active(q) || !key.page_match) { ClearPageWaiters(page); /* * It's possible to miss clearing Waiters here, when we woke * our page waiters, but the hashed waitqueue has waiters for * other pages on it. * * That's okay, it's a rare case. The next waker will clear it. */ } spin_unlock_irqrestore(&q->lock, flags); } static void wake_up_page(struct page *page, int bit) { if (!PageWaiters(page)) return; wake_up_page_bit(page, bit); } /* * A choice of three behaviors for wait_on_page_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like * __lock_page() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * wait_on_page_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, * like put_and_wait_on_page_locked() on PG_locked. */ }; /* * Attempt to check (or get) the page bit, and mark us done * if successful. */ static inline bool trylock_page_bit_common(struct page *page, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { if (test_and_set_bit(bit_nr, &page->flags)) return false; } else if (test_bit(bit_nr, &page->flags)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; return true; } /* How many times do we accept lock stealing from under a waiter? */ int sysctl_page_lock_unfairness = 5; static inline int wait_on_page_bit_common(wait_queue_head_t *q, struct page *page, int bit_nr, int state, enum behavior behavior) { int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; bool delayacct = false; unsigned long pflags; if (bit_nr == PG_locked && !PageUptodate(page) && PageWorkingset(page)) { if (!PageSwapBacked(page)) { delayacct_thrashing_start(); delayacct = true; } psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.page = page; wait_page.bit_nr = bit_nr; repeat: wait->flags = 0; if (behavior == EXCLUSIVE) { wait->flags = WQ_FLAG_EXCLUSIVE; if (--unfairness < 0) wait->flags |= WQ_FLAG_CUSTOM; } /* * Do one last check whether we can get the * page bit synchronously. * * Do the SetPageWaiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the * page queue), and add ourselves to the wait * queue if we need to sleep. * * This part needs to be done under the queue * lock to avoid races. */ spin_lock_irq(&q->lock); SetPageWaiters(page); if (!trylock_page_bit_common(page, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * From now on, all the logic will be based on * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to * see whether the page bit testing has already * been done by the wake function. * * We can drop our reference to the page. */ if (behavior == DROP) put_page(page); /* * Note that until the "finish_wait()", or until * we see the WQ_FLAG_WOKEN flag, we need to * be very careful with the 'wait->flags', because * we may race with a waker that sets them. */ for (;;) { unsigned int flags; set_current_state(state); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(state, current)) break; io_schedule(); continue; } /* If we were non-exclusive, we're done */ if (behavior != EXCLUSIVE) break; /* If the waker got the lock for us, we're done */ if (flags & WQ_FLAG_DONE) break; /* * Otherwise, if we're getting the lock, we need to * try to get it ourselves. * * And if that fails, we'll have to retry this all. */ if (unlikely(test_and_set_bit(bit_nr, &page->flags))) goto repeat; wait->flags |= WQ_FLAG_DONE; break; } /* * If a signal happened, this 'finish_wait()' may remove the last * waiter from the wait-queues, but the PageWaiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ finish_wait(q, wait); if (thrashing) { if (delayacct) delayacct_thrashing_end(); psi_memstall_leave(&pflags); } /* * NOTE! The wait->flags weren't stable until we've done the * 'finish_wait()', and we could have exited the loop above due * to a signal, and had a wakeup event happen after the signal * test but before the 'finish_wait()'. * * So only after the finish_wait() can we reliably determine * if we got woken up or not, so we can now figure out the final * return value based on that state without races. * * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive * waiter, but an exclusive one requires WQ_FLAG_DONE. */ if (behavior == EXCLUSIVE) return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } void wait_on_page_bit(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } EXPORT_SYMBOL(wait_on_page_bit); int wait_on_page_bit_killable(struct page *page, int bit_nr) { wait_queue_head_t *q = page_waitqueue(page); return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED); } EXPORT_SYMBOL(wait_on_page_bit_killable); static int __wait_on_page_locked_async(struct page *page, struct wait_page_queue *wait, bool set) { struct wait_queue_head *q = page_waitqueue(page); int ret = 0; wait->page = page; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); SetPageWaiters(page); if (set) ret = !trylock_page(page); else ret = PageLocked(page); /* * If we were succesful now, we know we're still on the * waitqueue as we're still under the lock. This means it's * safe to remove and return success, we know the callback * isn't going to trigger. */ if (!ret) __remove_wait_queue(q, &wait->wait); else ret = -EIOCBQUEUED; spin_unlock_irq(&q->lock); return ret; } static int wait_on_page_locked_async(struct page *page, struct wait_page_queue *wait) { if (!PageLocked(page)) return 0; return __wait_on_page_locked_async(compound_head(page), wait, false); } /** * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked * @page: The page to wait for. * * The caller should hold a reference on @page. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration * (for example) by holding the reference while waiting for the page to * come unlocked. After this function returns, the caller should not * dereference @page. */ void put_and_wait_on_page_locked(struct page *page) { wait_queue_head_t *q; page = compound_head(page); q = page_waitqueue(page); wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP); } /** * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue * @page: Page defining the wait queue of interest * @waiter: Waiter to add to the queue * * Add an arbitrary @waiter to the wait queue for the nominated @page. */ void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter) { wait_queue_head_t *q = page_waitqueue(page); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue_entry_tail(q, waiter); SetPageWaiters(page); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL_GPL(add_page_wait_queue); #ifndef clear_bit_unlock_is_negative_byte /* * PG_waiters is the high bit in the same byte as PG_lock. * * On x86 (and on many other architectures), we can clear PG_lock and * test the sign bit at the same time. But if the architecture does * not support that special operation, we just do this all by hand * instead. * * The read of PG_waiters has to be after (or concurrently with) PG_locked * being cleared, but a memory barrier should be unnecessary since it is * in the same byte as PG_locked. */ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem) { clear_bit_unlock(nr, mem); /* smp_mb__after_atomic(); */ return test_bit(PG_waiters, mem); } #endif /** * unlock_page - unlock a locked page * @page: the page * * Unlocks the page and wakes up sleepers in wait_on_page_locked(). * Also wakes sleepers in wait_on_page_writeback() because the wakeup * mechanism between PageLocked pages and PageWriteback pages is shared. * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep. * * Note that this depends on PG_waiters being the sign bit in the byte * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to * clear the PG_locked bit and test PG_waiters at the same time fairly * portably (architectures that do LL/SC can test any bit, while x86 can * test the sign bit). */ void unlock_page(struct page *page) { BUILD_BUG_ON(PG_waiters != 7); page = compound_head(page); VM_BUG_ON_PAGE(!PageLocked(page), page); if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags)) wake_up_page_bit(page, PG_locked); } EXPORT_SYMBOL(unlock_page); /** * end_page_writeback - end writeback against a page * @page: the page */ void end_page_writeback(struct page *page) { /* * TestClearPageReclaim could be used here but it is an atomic * operation and overkill in this particular case. Failing to * shuffle a page marked for immediate reclaim is too mild to * justify taking an atomic operation penalty at the end of * ever page writeback. */ if (PageReclaim(page)) { ClearPageReclaim(page); rotate_reclaimable_page(page); } /* * Writeback does not hold a page reference of its own, relying * on truncation to wait for the clearing of PG_writeback. * But here we must make sure that the page is not freed and * reused before the wake_up_page(). */ get_page(page); if (!test_clear_page_writeback(page)) BUG(); smp_mb__after_atomic(); wake_up_page(page, PG_writeback); put_page(page); } EXPORT_SYMBOL(end_page_writeback); /* * After completing I/O on a page, call this routine to update the page * flags appropriately */ void page_endio(struct page *page, bool is_write, int err) { if (!is_write) { if (!err) { SetPageUptodate(page); } else { ClearPageUptodate(page); SetPageError(page); } unlock_page(page); } else { if (err) { struct address_space *mapping; SetPageError(page); mapping = page_mapping(page); if (mapping) mapping_set_error(mapping, err); } end_page_writeback(page); } } EXPORT_SYMBOL_GPL(page_endio); /** * __lock_page - get a lock on the page, assuming we need to sleep to get it * @__page: the page to lock */ void __lock_page(struct page *__page) { struct page *page = compound_head(__page); wait_queue_head_t *q = page_waitqueue(page); wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } EXPORT_SYMBOL(__lock_page); int __lock_page_killable(struct page *__page) { struct page *page = compound_head(__page); wait_queue_head_t *q = page_waitqueue(page); return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, EXCLUSIVE); } EXPORT_SYMBOL_GPL(__lock_page_killable); int __lock_page_async(struct page *page, struct wait_page_queue *wait) { return __wait_on_page_locked_async(page, wait, true); } /* * Return values: * 1 - page is locked; mmap_lock is still held. * 0 - page is not locked. * mmap_lock has been released (mmap_read_unlock(), unless flags had both * FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in * which case mmap_lock is still held. * * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1 * with the page locked and the mmap_lock unperturbed. */ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock is not released * even though return 0. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) return 0; mmap_read_unlock(mm); if (flags & FAULT_FLAG_KILLABLE) wait_on_page_locked_killable(page); else wait_on_page_locked(page); return 0; } else { if (flags & FAULT_FLAG_KILLABLE) { int ret; ret = __lock_page_killable(page); if (ret) { mmap_read_unlock(mm); return 0; } } else __lock_page(page); return 1; } } /** * page_cache_next_miss() - Find the next gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the * gap with the lowest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 5, then subsequently a gap is * created at index 10, page_cache_next_miss covering both indices may * return 10 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). * In the rare case of index wrap-around, 0 will be returned. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == 0) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_next_miss); /** * page_cache_prev_miss() - Find the previous gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [max(index - max_scan + 1, 0), index] for the * gap with the highest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 10, then subsequently a gap is * created at index 5, page_cache_prev_miss() covering both indices may * return 5 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). * In the rare case of wrap-around, ULONG_MAX will be returned. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == ULONG_MAX) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_prev_miss); /** * find_get_entry - find and get a page cache entry * @mapping: the address_space to search * @index: The page cache index. * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, the head page is returned with an increased refcount. * * If the slot holds a shadow entry of a previously evicted page, or a * swap entry from shmem/tmpfs, it is returned. * * Return: The head page or shadow entry, %NULL if nothing is found. */ struct page *find_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct page *page; rcu_read_lock(); repeat: xas_reset(&xas); page = xas_load(&xas); if (xas_retry(&xas, page)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ if (!page || xa_is_value(page)) goto out; if (!page_cache_get_speculative(page)) goto repeat; /* * Has the page moved or been split? * This is part of the lockless pagecache protocol. See * include/linux/pagemap.h for details. */ if (unlikely(page != xas_reload(&xas))) { put_page(page); goto repeat; } out: rcu_read_unlock(); return page; } /** * find_lock_entry - Locate and lock a page cache entry. * @mapping: The address_space to search. * @index: The page cache index. * * Looks up the page at @mapping & @index. If there is a page in the * cache, the head page is returned locked and with an increased refcount. * * If the slot holds a shadow entry of a previously evicted page, or a * swap entry from shmem/tmpfs, it is returned. * * Context: May sleep. * Return: The head page or shadow entry, %NULL if nothing is found. */ struct page *find_lock_entry(struct address_space *mapping, pgoff_t index) { struct page *page; repeat: page = find_get_entry(mapping, index); if (page && !xa_is_value(page)) { lock_page(page); /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); put_page(page); goto repeat; } VM_BUG_ON_PAGE(!thp_contains(page, index), page); } return page; } /** * pagecache_get_page - Find and get a reference to a page. * @mapping: The address_space to search. * @index: The page index. * @fgp_flags: %FGP flags modify how the page is returned. * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified. * * Looks up the page cache entry at @mapping & @index. * * @fgp_flags can be zero or more of these flags: * * * %FGP_ACCESSED - The page will be marked accessed. * * %FGP_LOCK - The page is returned locked. * * %FGP_HEAD - If the page is present and a THP, return the head page * rather than the exact page specified by the index. * * %FGP_CREAT - If no page is present then a new page is allocated using * @gfp_mask and added to the page cache and the VM's LRU list. * The page is returned locked and with an increased refcount. * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the * page is already in cache. If the page was allocated, unlock it before * returning so the caller can do the same dance. * * %FGP_WRITE - The page will be written * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask * * %FGP_NOWAIT - Don't get blocked by page lock * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If there is a page cache page, it is returned with an increased refcount. * * Return: The found page or %NULL otherwise. */ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, int fgp_flags, gfp_t gfp_mask) { struct page *page; repeat: page = find_get_entry(mapping, index); if (xa_is_value(page)) page = NULL; if (!page) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!trylock_page(page)) { put_page(page); return NULL; } } else { lock_page(page); } /* Has the page been truncated? */ if (unlikely(page->mapping != mapping)) { unlock_page(page); put_page(page); goto repeat; } VM_BUG_ON_PAGE(!thp_contains(page, index), page); } if (fgp_flags & FGP_ACCESSED) mark_page_accessed(page); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ if (page_is_idle(page)) clear_page_idle(page); } if (!(fgp_flags & FGP_HEAD)) page = find_subpage(page, index); no_page: if (!page && (fgp_flags & FGP_CREAT)) { int err; if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp_mask |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) gfp_mask &= ~__GFP_FS; page = __page_cache_alloc(gfp_mask); if (!page) return NULL; if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __SetPageReferenced(page); err = add_to_page_cache_lru(page, mapping, index, gfp_mask); if (unlikely(err)) { put_page(page); page = NULL; if (err == -EEXIST) goto repeat; } /* * add_to_page_cache_lru locks the page, and for mmap we expect * an unlocked page. */ if (page && (fgp_flags & FGP_FOR_MMAP)) unlock_page(page); } return page; } EXPORT_SYMBOL(pagecache_get_page); /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index * @nr_entries: The maximum number of entries * @entries: Where the resulting entries are placed * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a group of up to * @nr_entries entries in the mapping. The entries are placed at * @entries. find_get_entries() takes a reference against any actual * pages it returns. * * The search returns a group of mapping-contiguous page cache entries * with ascending indexes. There may be holes in the indices due to * not-present pages. * * Any shadow entries of evicted pages, or swap entries from * shmem/tmpfs, are included in the returned array. * * If it finds a Transparent Huge Page, head or tail, find_get_entries() * stops at that page: the caller is likely to have a better way to handle * the compound page as a whole, and then skip its extent, than repeatedly * calling find_get_entries() to return all its tails. * * Return: the number of pages and shadow entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned int ret = 0; if (!nr_entries) return 0; rcu_read_lock(); xas_for_each(&xas, page, ULONG_MAX) { if (xas_retry(&xas, page)) continue; /* * A shadow entry of a recently evicted page, a swap * entry from shmem/tmpfs or a DAX entry. Return it * without attempting to raise page count. */ if (xa_is_value(page)) goto export; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; /* * Terminate early on finding a THP, to allow the caller to * handle it all at once; but continue if this is hugetlbfs. */ if (PageTransHuge(page) && !PageHuge(page)) { page = find_subpage(page, xas.xa_index); nr_entries = ret + 1; } export: indices[ret] = xas.xa_index; entries[ret] = page; if (++ret == nr_entries) break; continue; put_page: put_page(page); retry: xas_reset(&xas); } rcu_read_unlock(); return ret; } /** * find_get_pages_range - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @nr_pages: The maximum number of pages * @pages: Where the resulting pages are placed * * find_get_pages_range() will search for and return a group of up to @nr_pages * pages in the mapping starting at index @start and up to index @end * (inclusive). The pages are placed at @pages. find_get_pages_range() takes * a reference against the returned pages. * * The search returns a group of mapping-contiguous pages with ascending * indexes. There may be holes in the indices due to not-present pages. * We also update @start to index the next page for the traversal. * * Return: the number of pages which were found. If this number is * smaller than @nr_pages, the end of specified range has been * reached. */ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, *start); struct page *page; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); xas_for_each(&xas, page, end) { if (xas_retry(&xas, page)) continue; /* Skip over shadow, swap and DAX entries */ if (xa_is_value(page)) continue; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) { *start = xas.xa_index + 1; goto out; } continue; put_page: put_page(page); retry: xas_reset(&xas); } /* * We come here when there is no page beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a page at index -1 but that is * already broken anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return ret; } /** * find_get_pages_contig - gang contiguous pagecache lookup * @mapping: The address_space to search * @index: The starting page index * @nr_pages: The maximum number of pages * @pages: Where the resulting pages are placed * * find_get_pages_contig() works exactly like find_get_pages(), except * that the returned number of pages are guaranteed to be contiguous. * * Return: the number of pages which were found. */ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, index); struct page *page; unsigned int ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); for (page = xas_load(&xas); page; page = xas_next(&xas)) { if (xas_retry(&xas, page)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ if (xa_is_value(page)) break; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) break; continue; put_page: put_page(page); retry: xas_reset(&xas); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(find_get_pages_contig); /** * find_get_pages_range_tag - find and return pages in given range matching @tag * @mapping: the address_space to search * @index: the starting page index * @end: The final page index (inclusive) * @tag: the tag index * @nr_pages: the maximum number of pages * @pages: where the resulting pages are placed * * Like find_get_pages, except we only return pages which are tagged with * @tag. We update @index to index the next page for the traversal. * * Return: the number of pages which were found. */ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages) { XA_STATE(xas, &mapping->i_pages, *index); struct page *page; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); xas_for_each_marked(&xas, page, end, tag) { if (xas_retry(&xas, page)) continue; /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ if (xa_is_value(page)) continue; if (!page_cache_get_speculative(page)) goto retry; /* Has the page moved or been split? */ if (unlikely(page != xas_reload(&xas))) goto put_page; pages[ret] = find_subpage(page, xas.xa_index); if (++ret == nr_pages) { *index = xas.xa_index + 1; goto out; } continue; put_page: put_page(page); retry: xas_reset(&xas); } /* * We come here when we got to @end. We take care to not overflow the * index @index as it confuses some of the callers. This breaks the * iteration when there is a page at index -1 but that is already * broken anyway. */ if (end == (pgoff_t)-1) *index = (pgoff_t)-1; else *index = end + 1; out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL(find_get_pages_range_tag); /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: * * ---R__________________________________________B__________ * ^ reading here ^ bad block(assume 4k) * * read(R) => miss => readahead(R...B) => media error => frustrating retries * => failing the whole request => read(R) => read(R+1) => * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... * * It is going insane. Fix it by quickly scaling down the readahead size. */ static void shrink_readahead_size_eio(struct file_ra_state *ra) { ra->ra_pages /= 4; } /** * generic_file_buffered_read - generic file read routine * @iocb: the iocb to read * @iter: data destination * @written: already copied * * This is a generic file read routine, and uses the * mapping->a_ops->readpage() function for the actual low-level stuff. * * This is really ugly. But the goto's actually try to clarify some * of the logic when it comes to error handling etc. * * Return: * * total number of bytes copied, including those the were already @written * * negative error code if nothing was copied */ ssize_t generic_file_buffered_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t written) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct file_ra_state *ra = &filp->f_ra; loff_t *ppos = &iocb->ki_pos; pgoff_t index; pgoff_t last_index; pgoff_t prev_index; unsigned long offset; /* offset into pagecache page */ unsigned int prev_offset; int error = 0; if (unlikely(*ppos >= inode->i_sb->s_maxbytes)) return 0; if (unlikely(!iov_iter_count(iter))) return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes); index = *ppos >> PAGE_SHIFT; prev_index = ra->prev_pos >> PAGE_SHIFT; prev_offset = ra->prev_pos & (PAGE_SIZE-1); last_index = (*ppos + iter->count + PAGE_SIZE-1) >> PAGE_SHIFT; offset = *ppos & ~PAGE_MASK; /* * If we've already successfully copied some data, then we * can no longer safely return -EIOCBQUEUED. Hence mark * an async read NOWAIT at that point. */ if (written && (iocb->ki_flags & IOCB_WAITQ)) iocb->ki_flags |= IOCB_NOWAIT; for (;;) { struct page *page; pgoff_t end_index; loff_t isize; unsigned long nr, ret; cond_resched(); find_page: if (fatal_signal_pending(current)) { error = -EINTR; goto out; } page = find_get_page(mapping, index); if (!page) { if (iocb->ki_flags & IOCB_NOIO) goto would_block; page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); page = find_get_page(mapping, index); if (unlikely(page == NULL)) goto no_cached_page; } if (PageReadahead(page)) { if (iocb->ki_flags & IOCB_NOIO) { put_page(page); goto out; } page_cache_async_readahead(mapping, ra, filp, page, index, last_index - index); } if (!PageUptodate(page)) { /* * See comment in do_read_cache_page on why * wait_on_page_locked is used to avoid unnecessarily * serialisations and why it's safe. */ if (iocb->ki_flags & IOCB_WAITQ) { if (written) { put_page(page); goto out; } error = wait_on_page_locked_async(page, iocb->ki_waitq); } else { if (iocb->ki_flags & IOCB_NOWAIT) { put_page(page); goto would_block; } error = wait_on_page_locked_killable(page); } if (unlikely(error)) goto readpage_error; if (PageUptodate(page)) goto page_ok; if (inode->i_blkbits == PAGE_SHIFT || !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; /* pipes can't handle partially uptodate pages */ if (unlikely(iov_iter_is_pipe(iter))) goto page_not_up_to_date; if (!trylock_page(page)) goto page_not_up_to_date; /* Did it get truncated before we got the lock? */ if (!page->mapping) goto page_not_up_to_date_locked; if (!mapping->a_ops->is_partially_uptodate(page, offset, iter->count)) goto page_not_up_to_date_locked; unlock_page(page); } page_ok: /* * i_size must be checked after we know the page is Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); end_index = (isize - 1) >> PAGE_SHIFT; if (unlikely(!isize || index > end_index)) { put_page(page); goto out; } /* nr is the maximum number of bytes to copy from this page */ nr = PAGE_SIZE; if (index == end_index) { nr = ((isize - 1) & ~PAGE_MASK) + 1; if (nr <= offset) { put_page(page); goto out; } } nr = nr - offset; /* If users can be writing to this page using arbitrary * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ if (mapping_writably_mapped(mapping)) flush_dcache_page(page); /* * When a sequential read accesses a page several times, * only mark it as accessed the first time. */ if (prev_index != index || offset != prev_offset) mark_page_accessed(page); prev_index = index; /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... */ ret = copy_page_to_iter(page, offset, nr, iter); offset += ret; index += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; prev_offset = offset; put_page(page); written += ret; if (!iov_iter_count(iter)) goto out; if (ret < nr) { error = -EFAULT; goto out; } continue; page_not_up_to_date: /* Get exclusive access to the page ... */ if (iocb->ki_flags & IOCB_WAITQ) { if (written) { put_page(page); goto out; } error = lock_page_async(page, iocb->ki_waitq); } else { error = lock_page_killable(page); } if (unlikely(error)) goto readpage_error; page_not_up_to_date_locked: /* Did it get truncated before we got the lock? */ if (!page->mapping) { unlock_page(page); put_page(page); continue; } /* Did somebody else fill it already? */ if (PageUptodate(page)) { unlock_page(page); goto page_ok; } readpage: if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT)) { unlock_page(page); put_page(page); goto would_block; } /* * A previous I/O error may have been due to temporary * failures, eg. multipath errors. * PG_error will be set again if readpage fails. */ ClearPageError(page); /* Start the actual read. The read will unlock the page. */ error = mapping->a_ops->readpage(filp, page); if (unlikely(error)) { if (error == AOP_TRUNCATED_PAGE) { put_page(page); error = 0; goto find_page; } goto readpage_error; } if (!PageUptodate(page)) { if (iocb->ki_flags & IOCB_WAITQ) { if (written) { put_page(page); goto out; } error = lock_page_async(page, iocb->ki_waitq); } else { error = lock_page_killable(page); } if (unlikely(error)) goto readpage_error; if (!PageUptodate(page)) { if (page->mapping == NULL) { /* * invalidate_mapping_pages got it */ unlock_page(page); put_page(page); goto find_page; } unlock_page(page); shrink_readahead_size_eio(ra); error = -EIO; goto readpage_error; } unlock_page(page); } goto page_ok; readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ put_page(page); goto out; no_cached_page: /* * Ok, it wasn't cached, so we need to create a new * page.. */ page = page_cache_alloc(mapping); if (!page) { error = -ENOMEM; goto out; } error = add_to_page_cache_lru(page, mapping, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error) { put_page(page); if (error == -EEXIST) { error = 0; goto find_page; } goto out; } goto readpage; } would_block: error = -EAGAIN; out: ra->prev_pos = prev_index; ra->prev_pos <<= PAGE_SHIFT; ra->prev_pos |= prev_offset; *ppos = ((loff_t)index << PAGE_SHIFT) + offset; file_accessed(filp); return written ? written : error; } EXPORT_SYMBOL_GPL(generic_file_buffered_read); /** * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block * @iter: destination for the data read * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. * * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall * be returned when no data can be read without waiting for I/O requests * to complete; it doesn't prevent readahead. * * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O * requests shall be made for the read or for readahead. When no data * can be read, -EAGAIN shall be returned. When readahead would be * triggered, a partial, possibly empty read shall be returned. * * Return: * * number of bytes copied, even for partial reads * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { size_t count = iov_iter_count(iter); ssize_t retval = 0; if (!count) goto out; /* skip atime */ if (iocb->ki_flags & IOCB_DIRECT) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; loff_t size; size = i_size_read(inode); if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_has_page(mapping, iocb->ki_pos, iocb->ki_pos + count - 1)) return -EAGAIN; } else { retval = filemap_write_and_wait_range(mapping, iocb->ki_pos, iocb->ki_pos + count - 1); if (retval < 0) goto out; } file_accessed(file); retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; count -= retval; } iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter * compressed extents, so if there was an error, or if * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ if (retval < 0 || !count || iocb->ki_pos >= size || IS_DAX(inode)) goto out; } retval = generic_file_buffered_read(iocb, iter, retval); out: return retval; } EXPORT_SYMBOL(generic_file_read_iter); #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. * @page - the page to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * * This works similar to lock_page_or_retry in that it can drop the mmap_lock. * It differs in that it actually returns the page locked if it returns 1 and 0 * if it couldn't lock the page. If we did have to drop the mmap_lock then fpin * will point to the pinned file and needs to be fput()'ed at a later point. */ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, struct file **fpin) { if (trylock_page(page)) return 1; /* * NOTE! This will make us return with VM_FAULT_RETRY, but with * the mmap_lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) return 0; *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { if (__lock_page_killable(page)) { /* * We didn't have the right flags to drop the mmap_lock, * but all fault_handlers only check for fatal signals * if we return VM_FAULT_RETRY, so we need to drop the * mmap_lock here and return 0 if we don't have a fpin. */ if (*fpin == NULL) mmap_read_unlock(vmf->vma->vm_mm); return 0; } } else __lock_page(page); return 1; } /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have * to drop the mmap sem we return the file that was pinned in order for us to do * that. If we didn't pin a file then we return NULL. The file that is * returned needs to be fput()'ed when we're done with it. */ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; DEFINE_READAHEAD(ractl, file, mapping, vmf->pgoff); struct file *fpin = NULL; unsigned int mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ) return fpin; if (!ra->ra_pages) return fpin; if (vmf->vma->vm_flags & VM_SEQ_READ) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_sync_ra(&ractl, ra, ra->ra_pages); return fpin; } /* Avoid banging the cache line if not needed */ mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss < MMAP_LOTSAMISS * 10) WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (mmap_miss > MMAP_LOTSAMISS) return fpin; /* * mmap read-around */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ractl._index = ra->start; do_page_cache_ra(&ractl, ra->size, ra->async_size); return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further. We return the file that * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct page *page) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; struct file *fpin = NULL; unsigned int mmap_miss; pgoff_t offset = vmf->pgoff; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); if (PageReadahead(page)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_readahead(mapping, ra, file, page, offset, ra->ra_pages); } return fpin; } /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * * The goto's are kind of ugly, but this streamlines the normal case of having * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. * * vma->vm_mm->mmap_lock must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock * may be dropped before doing I/O or by lock_page_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. * * Return: bitwise-OR of %VM_FAULT_ codes. */ vm_fault_t filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct file_ra_state *ra = &file->f_ra; struct inode *inode = mapping->host; pgoff_t offset = vmf->pgoff; pgoff_t max_off; struct page *page; vm_fault_t ret = 0; max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) return VM_FAULT_SIGBUS; /* * Do we have something in the page cache already? */ page = find_get_page(mapping, offset); if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) { /* * We found the page, so try async readahead before * waiting for the lock. */ fpin = do_async_mmap_readahead(vmf, page); } else if (!page) { /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: page = pagecache_get_page(mapping, offset, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); if (!page) { if (fpin) goto out_retry; return VM_FAULT_OOM; } } if (!lock_page_maybe_drop_mmap(vmf, page, &fpin)) goto out_retry; /* Did it get truncated? */ if (unlikely(compound_head(page)->mapping != mapping)) { unlock_page(page); put_page(page); goto retry_find; } VM_BUG_ON_PAGE(page_to_pgoff(page) != offset, page); /* * We have a locked page in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error. */ if (unlikely(!PageUptodate(page))) goto page_not_uptodate; /* * We've made it this far and we had to drop our mmap_lock, now is the * time to return to the upper layer and have it re-find the vma and * redo the fault. */ if (fpin) { unlock_page(page); goto out_retry; } /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) { unlock_page(page); put_page(page); return VM_FAULT_SIGBUS; } vmf->page = page; return ret | VM_FAULT_LOCKED; page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, * because there really aren't any performance issues here * and we need to check for errors. */ ClearPageError(page); fpin = maybe_unlock_mmap_for_io(vmf, fpin); error = mapping->a_ops->readpage(file, page); if (!error) { wait_on_page_locked(page); if (!PageUptodate(page)) error = -EIO; } if (fpin) goto out_retry; put_page(page); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; shrink_readahead_size_eio(ra); return VM_FAULT_SIGBUS; out_retry: /* * We dropped the mmap_lock, we need to return to the fault handler to * re-find the vma and come back and find our hopefully still populated * page. */ if (page) put_page(page); if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); void filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct file *file = vmf->vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t last_pgoff = start_pgoff; unsigned long max_idx; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct page *head, *page; unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss); rcu_read_lock(); xas_for_each(&xas, head, end_pgoff) { if (xas_retry(&xas, head)) continue; if (xa_is_value(head)) goto next; /* * Check for a locked page first, as a speculative * reference may adversely influence page migration. */ if (PageLocked(head)) goto next; if (!page_cache_get_speculative(head)) goto next; /* Has the page moved or been split? */ if (unlikely(head != xas_reload(&xas))) goto skip; page = find_subpage(head, xas.xa_index); if (!PageUptodate(head) || PageReadahead(page) || PageHWPoison(page)) goto skip; if (!trylock_page(head)) goto skip; if (head->mapping != mapping || !PageUptodate(head)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (xas.xa_index >= max_idx) goto unlock; if (mmap_miss > 0) mmap_miss--; vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT; if (vmf->pte) vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; if (alloc_set_pte(vmf, page)) goto unlock; unlock_page(head); goto next; unlock: unlock_page(head); skip: put_page(head); next: /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) break; } rcu_read_unlock(); WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss); } EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(inode->i_sb); file_update_time(vmf->vma->vm_file); lock_page(page); if (page->mapping != inode->i_mapping) { unlock_page(page); ret = VM_FAULT_NOPAGE; goto out; } /* * We mark the page dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will * see the dirty page and writeprotect it again. */ set_page_dirty(page); wait_for_stable_page(page); out: sb_end_pagefault(inode->i_sb); return ret; } const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, }; /* This is used for a general mmap of a disk file */ int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->readpage) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; return 0; } /* * This is for filesystems which do not implement ->writepage. */ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { if (vma_is_shared_maywrite(vma)) return -EINVAL; return generic_file_mmap(file, vma); } #else vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { return -ENOSYS; } int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) { return -ENOSYS; } #endif /* CONFIG_MMU */ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); static struct page *wait_on_page_read(struct page *page) { if (!IS_ERR(page)) { wait_on_page_locked(page); if (!PageUptodate(page)) { put_page(page); page = ERR_PTR(-EIO); } } return page; } static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data, gfp_t gfp) { struct page *page; int err; repeat: page = find_get_page(mapping, index); if (!page) { page = __page_cache_alloc(gfp); if (!page) return ERR_PTR(-ENOMEM); err = add_to_page_cache_lru(page, mapping, index, gfp); if (unlikely(err)) { put_page(page); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ return ERR_PTR(err); } filler: if (filler) err = filler(data, page); else err = mapping->a_ops->readpage(data, page); if (err < 0) { put_page(page); return ERR_PTR(err); } page = wait_on_page_read(page); if (IS_ERR(page)) return page; goto out; } if (PageUptodate(page)) goto out; /* * Page is not up to date and may be locked due to one of the following * case a: Page is being filled and the page lock is held * case b: Read/write error clearing the page uptodate status * case c: Truncation in progress (page locked) * case d: Reclaim in progress * * Case a, the page will be up to date when the page is unlocked. * There is no need to serialise on the page lock here as the page * is pinned so the lock gives no additional protection. Even if the * page is truncated, the data is still valid if PageUptodate as * it's a race vs truncate race. * Case b, the page will not be up to date * Case c, the page may be truncated but in itself, the data may still * be valid after IO completes as it's a read vs truncate race. The * operation must restart if the page is not uptodate on unlock but * otherwise serialising on page lock to stabilise the mapping gives * no additional guarantees to the caller as the page lock is * released before return. * Case d, similar to truncation. If reclaim holds the page lock, it * will be a race with remove_mapping that determines if the mapping * is valid on unlock but otherwise the data is valid and there is * no need to serialise with page lock. * * As the page lock gives no additional guarantee, we optimistically * wait on the page to be unlocked and check if it's up to date and * use the page if it is. Otherwise, the page lock is required to * distinguish between the different cases. The motivation is that we * avoid spurious serialisations and wakeups when multiple processes * wait on the same page for IO to complete. */ wait_on_page_locked(page); if (PageUptodate(page)) goto out; /* Distinguish between all the cases under the safety of the lock */ lock_page(page); /* Case c or d, restart the operation */ if (!page->mapping) { unlock_page(page); put_page(page); goto repeat; } /* Someone else locked and filled the page in a very small window */ if (PageUptodate(page)) { unlock_page(page); goto out; } /* * A previous I/O error may have been due to temporary * failures. * Clear page error before actual read, PG_error will be * set again if read page fails. */ ClearPageError(page); goto filler; out: mark_page_accessed(page); return page; } /** * read_cache_page - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read * @data: first arg to filler(data, page) function, often left as NULL * * Read into the page cache. If a page already exists, and PageUptodate() is * not set, try to fill the page and wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with * any new page allocations done using the specified allocation flags. * * If the page does not get brought uptodate, return -EIO. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_page(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { const struct address_space_operations *aops = mapping->a_ops; return aops->write_begin(file, mapping, pos, len, flags, pagep, fsdata); } EXPORT_SYMBOL(pagecache_write_begin); int pagecache_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { const struct address_space_operations *aops = mapping->a_ops; return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); /* * Warn about a page cache invalidation failure during a direct I/O write. */ void dio_warn_stale_pagecache(struct file *filp) { static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); char pathname[128]; struct inode *inode = file_inode(filp); char *path; errseq_set(&inode->i_mapping->wb_err, -EIO); if (__ratelimit(&_rs)) { path = file_path(filp, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, current->comm); } } ssize_t generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; ssize_t written; size_t write_len; pgoff_t end; write_len = iov_iter_count(from); end = (pos + write_len - 1) >> PAGE_SHIFT; if (iocb->ki_flags & IOCB_NOWAIT) { /* If there are pages to writeback, return */ if (filemap_range_has_page(inode->i_mapping, pos, pos + write_len - 1)) return -EAGAIN; } else { written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1); if (written) goto out; } /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ written = invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end); /* * If a page can not be invalidated, return 0 to fall back * to buffered write. */ if (written) { if (written == -EBUSY) return 0; goto out; } written = mapping->a_ops->direct_IO(iocb, from); /* * Finally, try again to invalidate clean pages which might have been * cached by non-direct readahead, or faulted in by get_user_pages() * if the source of the write was an mmap'ed region of the file * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... * * Most of the time we do not need this since dio_complete() will do * the invalidation for us. However there are some file systems that * do not end up with dio_complete() being called, so let's not break * them by removing it completely. * * Noticeable example is a blkdev_direct_IO(). * * Skip invalidation for async writes or if mapping has no pages. */ if (written > 0 && mapping->nrpages && invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end)) dio_warn_stale_pagecache(file); if (written > 0) { pos += written; write_len -= written; if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } iocb->ki_pos = pos; } iov_iter_revert(from, write_len - iov_iter_count(from)); out: return written; } EXPORT_SYMBOL(generic_file_direct_write); /* * Find or create a page at the given pagecache position. Return the locked * page. This function is specifically for buffered writes. */ struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags) { struct page *page; int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT; if (flags & AOP_FLAG_NOFS) fgp_flags |= FGP_NOFS; page = pagecache_get_page(mapping, index, fgp_flags, mapping_gfp_mask(mapping)); if (page) wait_for_stable_page(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; long status = 0; ssize_t written = 0; unsigned int flags = 0; do { struct page *page; unsigned long offset; /* Offset into pagecache page */ unsigned long bytes; /* Bytes to write to page */ size_t copied; /* Bytes copied from user */ void *fsdata = NULL; offset = (pos & (PAGE_SIZE - 1)); bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_count(i)); again: /* * Bring in the user page that we will copy from _first_. * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. * * Not only is this an optimisation, but it is also required * to check that the address is actually valid, when atomic * usercopies are used, below. */ if (unlikely(iov_iter_fault_in_readable(i, bytes))) { status = -EFAULT; break; } if (fatal_signal_pending(current)) { status = -EINTR; break; } status = a_ops->write_begin(file, mapping, pos, bytes, flags, &page, &fsdata); if (unlikely(status < 0)) break; if (mapping_writably_mapped(mapping)) flush_dcache_page(page); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); flush_dcache_page(page); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status < 0)) break; copied = status; cond_resched(); iov_iter_advance(i, copied); if (unlikely(copied == 0)) { /* * If we were unable to copy any data at all, we must * fall back to a single segment length write. * * If we didn't fallback here, we could livelock * because not all segments in the iov can be copied at * once without a pagefault. */ bytes = min_t(unsigned long, PAGE_SIZE - offset, iov_iter_single_seg_count(i)); goto again; } pos += copied; written += copied; balance_dirty_pages_ratelimited(mapping); } while (iov_iter_count(i)); return written ? written : status; } EXPORT_SYMBOL(generic_perform_write); /** * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates * modification times and calls proper subroutines depending on whether we * do direct IO or a standard buffered write. * * It expects i_mutex to be grabbed unless we work on a block device or similar * object which does not need locking at all. * * This function does *not* take care of syncing data in case of O_SYNC write. * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_mutex. * * Return: * * number of bytes written, even for truncated writes * * negative error code if no data has been written at all */ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t written = 0; ssize_t err; ssize_t status; /* We can write back this queue in page reclaim */ current->backing_dev_info = inode_to_bdi(inode); err = file_remove_privs(file); if (err) goto out; err = file_update_time(file); if (err) goto out; if (iocb->ki_flags & IOCB_DIRECT) { loff_t pos, endbyte; written = generic_file_direct_write(iocb, from); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to * holes, for example. For DAX files, a buffered write will * not succeed (even if it did, DAX does not handle dirty * page-cache pages correctly). */ if (written < 0 || !iov_iter_count(from) || IS_DAX(inode)) goto out; status = generic_perform_write(file, from, pos = iocb->ki_pos); /* * If generic_perform_write() returned a synchronous error * then we want to return the number of bytes which were * direct-written, or the error code if that was zero. Note * that this differs from normal direct-io semantics, which * will return -EFOO even if some bytes were written. */ if (unlikely(status < 0)) { err = status; goto out; } /* * We need to ensure that the page cache pages are written to * disk and invalidated to preserve the expected O_DIRECT * semantics. */ endbyte = pos + status - 1; err = filemap_write_and_wait_range(mapping, pos, endbyte); if (err == 0) { iocb->ki_pos = endbyte + 1; written += status; invalidate_mapping_pages(mapping, pos >> PAGE_SHIFT, endbyte >> PAGE_SHIFT); } else { /* * We don't know how much we wrote, so just return * the number of bytes which were direct-written */ } } else { written = generic_perform_write(file, from, iocb->ki_pos); if (likely(written > 0)) iocb->ki_pos += written; } out: current->backing_dev_info = NULL; return written ? written : err; } EXPORT_SYMBOL(__generic_file_write_iter); /** * generic_file_write_iter - write data to a file * @iocb: IO state structure * @from: iov_iter with data to write * * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_mutex as needed. * Return: * * negative error code if no data has been written at all of * vfs_fsync_range() failed for a synchronous write * * number of bytes written, even for truncated writes */ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; } EXPORT_SYMBOL(generic_file_write_iter); /** * try_to_release_page() - release old fs-specific metadata on a page * * @page: the page which the kernel is trying to free * @gfp_mask: memory allocation flags (and I/O mode) * * The address_space is to try to release any data against the page * (presumably at page->private). * * This may also be called if PG_fscache is set on a page, indicating that the * page is known to the local caching routines. * * The @gfp_mask argument specifies whether I/O may be performed to release * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS). * * Return: %1 if the release was successful, otherwise return zero. */ int try_to_release_page(struct page *page, gfp_t gfp_mask) { struct address_space * const mapping = page->mapping; BUG_ON(!PageLocked(page)); if (PageWriteback(page)) return 0; if (mapping && mapping->a_ops->releasepage) return mapping->a_ops->releasepage(page, gfp_mask); return try_to_free_buffers(page); } EXPORT_SYMBOL(try_to_release_page); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef LLIST_H #define LLIST_H /* * Lock-less NULL terminated single linked list * * Cases where locking is not needed: * If there are multiple producers and multiple consumers, llist_add can be * used in producers and llist_del_all can be used in consumers simultaneously * without locking. Also a single consumer can use llist_del_first while * multiple producers simultaneously use llist_add, without any locking. * * Cases where locking is needed: * If we have multiple consumers with llist_del_first used in one consumer, and * llist_del_first or llist_del_all used in other consumers, then a lock is * needed. This is because llist_del_first depends on list->first->next not * changing, but without lock protection, there's no way to be sure about that * if a preemption happens in the middle of the delete operation and on being * preempted back, the list->first is the same as before causing the cmpxchg in * llist_del_first to succeed. For example, while a llist_del_first operation * is in progress in one consumer, then a llist_del_first, llist_add, * llist_add (or llist_del_all, llist_add, llist_add) sequence in another * consumer may cause violations. * * This can be summarized as follows: * * | add | del_first | del_all * add | - | - | - * del_first | | L | L * del_all | | | - * * Where, a particular row's operation can happen concurrently with a column's * operation, with "-" being no lock needed, while "L" being lock is needed. * * The list entries deleted via llist_del_all can be traversed with * traversing function such as llist_for_each etc. But the list * entries can not be traversed safely before deleted from the list. * The order of deleted entries is from the newest to the oldest added * one. If you want to traverse from the oldest to the newest, you * must reverse the order by yourself before traversing. * * The basic atomic operation of this list is cmpxchg on long. On * architectures that don't have NMI-safe cmpxchg implementation, the * list can NOT be used in NMI handlers. So code that uses the list in * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * Copyright 2010,2011 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> */ #include <linux/atomic.h> #include <linux/kernel.h> struct llist_head { struct llist_node *first; }; struct llist_node { struct llist_node *next; }; #define LLIST_HEAD_INIT(name) { NULL } #define LLIST_HEAD(name) struct llist_head name = LLIST_HEAD_INIT(name) /** * init_llist_head - initialize lock-less list head * @head: the head for your lock-less list */ static inline void init_llist_head(struct llist_head *list) { list->first = NULL; } /** * llist_entry - get the struct of this entry * @ptr: the &struct llist_node pointer. * @type: the type of the struct this is embedded in. * @member: the name of the llist_node within the struct. */ #define llist_entry(ptr, type, member) \ container_of(ptr, type, member) /** * member_address_is_nonnull - check whether the member address is not NULL * @ptr: the object pointer (struct type * that contains the llist_node) * @member: the name of the llist_node within the struct. * * This macro is conceptually the same as * &ptr->member != NULL * but it works around the fact that compilers can decide that taking a member * address is never a NULL pointer. * * Real objects that start at a high address and have a member at NULL are * unlikely to exist, but such pointers may be returned e.g. by the * container_of() macro. */ #define member_address_is_nonnull(ptr, member) \ ((uintptr_t)(ptr) + offsetof(typeof(*(ptr)), member) != 0) /** * llist_for_each - iterate over some deleted entries of a lock-less list * @pos: the &struct llist_node to use as a loop cursor * @node: the first entry of deleted list entries * * In general, some entries of the lock-less list can be traversed * safely only after being deleted from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each(pos, node) \ for ((pos) = (node); pos; (pos) = (pos)->next) /** * llist_for_each_safe - iterate over some deleted entries of a lock-less list * safe against removal of list entry * @pos: the &struct llist_node to use as a loop cursor * @n: another &struct llist_node to use as temporary storage * @node: the first entry of deleted list entries * * In general, some entries of the lock-less list can be traversed * safely only after being deleted from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_safe(pos, n, node) \ for ((pos) = (node); (pos) && ((n) = (pos)->next, true); (pos) = (n)) /** * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type * @pos: the type * to use as a loop cursor. * @node: the fist entry of deleted list entries. * @member: the name of the llist_node with the struct. * * In general, some entries of the lock-less list can be traversed * safely only after being removed from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_entry(pos, node, member) \ for ((pos) = llist_entry((node), typeof(*(pos)), member); \ member_address_is_nonnull(pos, member); \ (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) /** * llist_for_each_entry_safe - iterate over some deleted entries of lock-less list of given type * safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @node: the first entry of deleted list entries. * @member: the name of the llist_node with the struct. * * In general, some entries of the lock-less list can be traversed * safely only after being removed from list, so start with an entry * instead of list head. * * If being used on entries deleted from lock-less list directly, the * traverse order is from the newest to the oldest added entry. If * you want to traverse from the oldest to the newest, you must * reverse the order by yourself before traversing. */ #define llist_for_each_entry_safe(pos, n, node, member) \ for (pos = llist_entry((node), typeof(*pos), member); \ member_address_is_nonnull(pos, member) && \ (n = llist_entry(pos->member.next, typeof(*n), member), true); \ pos = n) /** * llist_empty - tests whether a lock-less list is empty * @head: the list to test * * Not guaranteed to be accurate or up to date. Just a quick way to * test whether the list is empty without deleting something from the * list. */ static inline bool llist_empty(const struct llist_head *head) { return READ_ONCE(head->first) == NULL; } static inline struct llist_node *llist_next(struct llist_node *node) { return node->next; } extern bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_head *head); /** * llist_add - add a new entry * @new: new entry to be added * @head: the head for your lock-less list * * Returns true if the list was empty prior to adding this entry. */ static inline bool llist_add(struct llist_node *new, struct llist_head *head) { return llist_add_batch(new, new, head); } /** * llist_del_all - delete all entries from lock-less list * @head: the head of lock-less list to delete all entries * * If list is empty, return NULL, otherwise, delete all entries and * return the pointer to the first entry. The order of entries * deleted is from the newest to the oldest added one. */ static inline struct llist_node *llist_del_all(struct llist_head *head) { return xchg(&head->first, NULL); } extern struct llist_node *llist_del_first(struct llist_head *head); struct llist_node *llist_reverse_order(struct llist_node *head); #endif /* LLIST_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIME64_H #define _LINUX_TIME64_H #include <linux/math64.h> #include <vdso/time64.h> typedef __s64 time64_t; typedef __u64 timeu64_t; #include <uapi/linux/time.h> struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; struct itimerspec64 { struct timespec64 it_interval; struct timespec64 it_value; }; /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) /* * Limits for settimeofday(): * * To prevent setting the time close to the wraparound point time setting * is limited so a reasonable uptime can be accomodated. Uptime of 30 years * should be really sufficient, which means the cutoff is 2232. At that * point the cutoff is just a small part of the larger problem. */ #define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) #define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } /* * lhs < rhs: return <0 * lhs == rhs: return 0 * lhs > rhs: return >0 */ static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; if (lhs->tv_sec > rhs->tv_sec) return 1; return lhs->tv_nsec - rhs->tv_nsec; } extern void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec); static inline struct timespec64 timespec64_add(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); return ts_delta; } /* * sub = lhs - rhs, in normalized form */ static inline struct timespec64 timespec64_sub(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec - rhs.tv_sec, lhs.tv_nsec - rhs.tv_nsec); return ts_delta; } /* * Returns true if the timespec64 is norm, false if denorm: */ static inline bool timespec64_valid(const struct timespec64 *ts) { /* Dates before 1970 are bogus */ if (ts->tv_sec < 0) return false; /* Can't have more nanoseconds then a second */ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return false; return true; } static inline bool timespec64_valid_strict(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values that could overflow ktime_t */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return false; return true; } static inline bool timespec64_valid_settod(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) return false; return true; } /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted * * Returns the scalar nanosecond representation of the timespec64 * parameter. */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { /* Prevent multiplication overflow */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Returns the timespec64 representation of the nsec parameter. */ extern struct timespec64 ns_to_timespec64(const s64 nsec); /** * timespec64_add_ns - Adds nanoseconds to a timespec64 * @a: pointer to timespec64 to be incremented * @ns: unsigned nanoseconds value to be added * * This must always be inlined because its used from the x86-64 vdso, * which cannot call other kernel functions. */ static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) { a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } /* * timespec64_add_safe assumes both values are positive and checks for * overflow. It will return TIME64_MAX in case of overflow. */ extern struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs); #endif /* _LINUX_TIME64_H */ |
| 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGEMAP_H #define _LINUX_PAGEMAP_H /* * Copyright 1995 Linus Torvalds */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/list.h> #include <linux/highmem.h> #include <linux/compiler.h> #include <linux/uaccess.h> #include <linux/gfp.h> #include <linux/bitops.h> #include <linux/hardirq.h> /* for in_interrupt() */ #include <linux/hugetlb_inline.h> struct pagevec; /* * Bits in mapping->flags. */ enum mapping_flags { AS_EIO = 0, /* IO error on async write */ AS_ENOSPC = 1, /* ENOSPC on async write */ AS_MM_ALL_LOCKS = 2, /* under mm_take_all_locks() */ AS_UNEVICTABLE = 3, /* e.g., ramdisk, SHM_LOCK */ AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, AS_THP_SUPPORT = 6, /* THPs supported */ }; /** * mapping_set_error - record a writeback error in the address_space * @mapping: the mapping in which an error should be set * @error: the error to set in the mapping * * When writeback fails in some way, we must record that error so that * userspace can be informed when fsync and the like are called. We endeavor * to report errors on any file that was open at the time of the error. Some * internal callers also need to know when writeback errors have occurred. * * When a writeback error occurs, most filesystems will want to call * mapping_set_error to record the error in the mapping so that it can be * reported when the application calls fsync(2). */ static inline void mapping_set_error(struct address_space *mapping, int error) { if (likely(!error)) return; /* Record in wb_err for checkers using errseq_t based tracking */ __filemap_set_wb_err(mapping, error); /* Record it in superblock */ if (mapping->host) errseq_set(&mapping->host->i_sb->s_wb_err, error); /* Record it in flags for now, for legacy callers */ if (error == -ENOSPC) set_bit(AS_ENOSPC, &mapping->flags); else set_bit(AS_EIO, &mapping->flags); } static inline void mapping_set_unevictable(struct address_space *mapping) { set_bit(AS_UNEVICTABLE, &mapping->flags); } static inline void mapping_clear_unevictable(struct address_space *mapping) { clear_bit(AS_UNEVICTABLE, &mapping->flags); } static inline bool mapping_unevictable(struct address_space *mapping) { return mapping && test_bit(AS_UNEVICTABLE, &mapping->flags); } static inline void mapping_set_exiting(struct address_space *mapping) { set_bit(AS_EXITING, &mapping->flags); } static inline int mapping_exiting(struct address_space *mapping) { return test_bit(AS_EXITING, &mapping->flags); } static inline void mapping_set_no_writeback_tags(struct address_space *mapping) { set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } static inline int mapping_use_writeback_tags(struct address_space *mapping) { return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return mapping->gfp_mask; } /* Restricts the given gfp_mask to what the mapping allows. */ static inline gfp_t mapping_gfp_constraint(struct address_space *mapping, gfp_t gfp_mask) { return mapping_gfp_mask(mapping) & gfp_mask; } /* * This is non-atomic. Only to be used before the mapping is activated. * Probably needs a barrier... */ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) { m->gfp_mask = mask; } static inline bool mapping_thp_support(struct address_space *mapping) { return test_bit(AS_THP_SUPPORT, &mapping->flags); } static inline int filemap_nr_thps(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS return atomic_read(&mapping->nr_thps); #else return 0; #endif } static inline void filemap_nr_thps_inc(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS if (!mapping_thp_support(mapping)) atomic_inc(&mapping->nr_thps); #else WARN_ON_ONCE(1); #endif } static inline void filemap_nr_thps_dec(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS if (!mapping_thp_support(mapping)) atomic_dec(&mapping->nr_thps); #else WARN_ON_ONCE(1); #endif } void release_pages(struct page **pages, int nr); /* * speculatively take a reference to a page. * If the page is free (_refcount == 0), then _refcount is untouched, and 0 * is returned. Otherwise, _refcount is incremented by 1 and 1 is returned. * * This function must be called inside the same rcu_read_lock() section as has * been used to lookup the page in the pagecache radix-tree (or page table): * this allows allocators to use a synchronize_rcu() to stabilize _refcount. * * Unless an RCU grace period has passed, the count of all pages coming out * of the allocator must be considered unstable. page_count may return higher * than expected, and put_page must be able to do the right thing when the * page has been finished with, no matter what it is subsequently allocated * for (because put_page is what is used here to drop an invalid speculative * reference). * * This is the interesting part of the lockless pagecache (and lockless * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page) * has the following pattern: * 1. find page in radix tree * 2. conditionally increment refcount * 3. check the page is still in pagecache (if no, goto 1) * * Remove-side that cares about stability of _refcount (eg. reclaim) has the * following (with the i_pages lock held): * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg) * B. remove page from pagecache * C. free the page * * There are 2 critical interleavings that matter: * - 2 runs before A: in this case, A sees elevated refcount and bails out * - A runs before 2: in this case, 2 sees zero refcount and retries; * subsequently, B will complete and 1 will find no page, causing the * lookup to return NULL. * * It is possible that between 1 and 2, the page is removed then the exact same * page is inserted into the same position in pagecache. That's OK: the * old find_get_page using a lock could equally have run before or after * such a re-insertion, depending on order that locks are granted. * * Lookups racing against pagecache insertion isn't a big problem: either 1 * will find the page or it will not. Likewise, the old find_get_page could run * either before the insertion or afterwards, depending on timing. */ static inline int __page_cache_add_speculative(struct page *page, int count) { #ifdef CONFIG_TINY_RCU # ifdef CONFIG_PREEMPT_COUNT VM_BUG_ON(!in_atomic() && !irqs_disabled()); # endif /* * Preempt must be disabled here - we rely on rcu_read_lock doing * this for us. * * Pagecache won't be truncated from interrupt context, so if we have * found a page in the radix tree here, we have pinned its refcount by * disabling preempt, and hence no need for the "speculative get" that * SMP requires. */ VM_BUG_ON_PAGE(page_count(page) == 0, page); page_ref_add(page, count); #else if (unlikely(!page_ref_add_unless(page, count, 0))) { /* * Either the page has been freed, or will be freed. * In either case, retry here and the caller should * do the right thing (see comments above). */ return 0; } #endif VM_BUG_ON_PAGE(PageTail(page), page); return 1; } static inline int page_cache_get_speculative(struct page *page) { return __page_cache_add_speculative(page, 1); } static inline int page_cache_add_speculative(struct page *page, int count) { return __page_cache_add_speculative(page, count); } /** * attach_page_private - Attach private data to a page. * @page: Page to attach data to. * @data: Data to attach to page. * * Attaching private data to a page increments the page's reference count. * The data must be detached before the page will be freed. */ static inline void attach_page_private(struct page *page, void *data) { get_page(page); set_page_private(page, (unsigned long)data); SetPagePrivate(page); } /** * detach_page_private - Detach private data from a page. * @page: Page to detach data from. * * Removes the data that was previously attached to the page and decrements * the refcount on the page. * * Return: Data that was attached to the page. */ static inline void *detach_page_private(struct page *page) { void *data = (void *)page_private(page); if (!PagePrivate(page)) return NULL; ClearPagePrivate(page); set_page_private(page, 0); put_page(page); return data; } #ifdef CONFIG_NUMA extern struct page *__page_cache_alloc(gfp_t gfp); #else static inline struct page *__page_cache_alloc(gfp_t gfp) { return alloc_pages(gfp, 0); } #endif static inline struct page *page_cache_alloc(struct address_space *x) { return __page_cache_alloc(mapping_gfp_mask(x)); } static inline gfp_t readahead_gfp_mask(struct address_space *x) { return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; } typedef int filler_t(void *, struct page *); pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); #define FGP_ACCESSED 0x00000001 #define FGP_LOCK 0x00000002 #define FGP_CREAT 0x00000004 #define FGP_WRITE 0x00000008 #define FGP_NOFS 0x00000010 #define FGP_NOWAIT 0x00000020 #define FGP_FOR_MMAP 0x00000040 #define FGP_HEAD 0x00000080 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, int fgp_flags, gfp_t cache_gfp_mask); /** * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned with an increased refcount. * * Otherwise, %NULL is returned. */ static inline struct page *find_get_page(struct address_space *mapping, pgoff_t offset) { return pagecache_get_page(mapping, offset, 0, 0); } static inline struct page *find_get_page_flags(struct address_space *mapping, pgoff_t offset, int fgp_flags) { return pagecache_get_page(mapping, offset, fgp_flags, 0); } /** * find_lock_page - locate, pin and lock a pagecache page * @mapping: the address_space to search * @index: the page index * * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, it is returned locked and with an increased * refcount. * * Context: May sleep. * Return: A struct page or %NULL if there is no page in the cache for this * index. */ static inline struct page *find_lock_page(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK, 0); } /** * find_lock_head - Locate, pin and lock a pagecache page. * @mapping: The address_space to search. * @index: The page index. * * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, its head page is returned locked and with an increased * refcount. * * Context: May sleep. * Return: A struct page which is !PageTail, or %NULL if there is no page * in the cache for this index. */ static inline struct page *find_lock_head(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK | FGP_HEAD, 0); } /** * find_or_create_page - locate or add a pagecache page * @mapping: the page's address_space * @index: the page's index into the mapping * @gfp_mask: page allocation mode * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned locked and with an increased * refcount. * * If the page is not present, a new page is allocated using @gfp_mask * and added to the page cache and the VM's LRU list. The page is * returned locked and with an increased refcount. * * On memory exhaustion, %NULL is returned. * * find_or_create_page() may sleep, even if @gfp_flags specifies an * atomic allocation! */ static inline struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask) { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_ACCESSED|FGP_CREAT, gfp_mask); } /** * grab_cache_page_nowait - returns locked page at given index in given cache * @mapping: target address_space * @index: the page index * * Same as grab_cache_page(), but do not wait if the page is unavailable. * This is intended for speculative data generators, where the data can * be regenerated if the page couldn't be grabbed. This routine should * be safe to call while holding the lock for another page. * * Clear __GFP_FS when allocating the page to avoid recursion into the fs * and deadlock against the caller's locked page. */ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, mapping_gfp_mask(mapping)); } /* Does this page contain this index? */ static inline bool thp_contains(struct page *head, pgoff_t index) { /* HugeTLBfs indexes the page cache in units of hpage_size */ if (PageHuge(head)) return head->index == index; return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL)); } /* * Given the page we found in the page cache, return the page corresponding * to this index in the file */ static inline struct page *find_subpage(struct page *head, pgoff_t index) { /* HugeTLBfs wants the head page regardless */ if (PageHuge(head)) return head; return head + (index & (thp_nr_pages(head) - 1)); } unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices); unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages); static inline unsigned find_get_pages(struct address_space *mapping, pgoff_t *start, unsigned int nr_pages, struct page **pages) { return find_get_pages_range(mapping, start, (pgoff_t)-1, nr_pages, pages); } unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages); static inline unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, xa_mark_t tag, unsigned int nr_pages, struct page **pages) { return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag, nr_pages, pages); } struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index, unsigned flags); /* * Returns locked page at given index in given cache, creating it if needed. */ static inline struct page *grab_cache_page(struct address_space *mapping, pgoff_t index) { return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } extern struct page * read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, void *data) { return read_cache_page(mapping, index, NULL, data); } /* * Get index of the page within radix-tree (but not for hugetlb pages). * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) */ static inline pgoff_t page_to_index(struct page *page) { pgoff_t pgoff; if (likely(!PageTransTail(page))) return page->index; /* * We don't initialize ->index for tail pages: calculate based on * head page */ pgoff = compound_head(page)->index; pgoff += page - compound_head(page); return pgoff; } extern pgoff_t hugetlb_basepage_index(struct page *page); /* * Get the offset in PAGE_SIZE (even for hugetlb pages). * (TODO: hugetlb pages should have ->index in PAGE_SIZE) */ static inline pgoff_t page_to_pgoff(struct page *page) { if (unlikely(PageHuge(page))) return hugetlb_basepage_index(page); return page_to_index(page); } /* * Return byte-offset into filesystem object for page. */ static inline loff_t page_offset(struct page *page) { return ((loff_t)page->index) << PAGE_SHIFT; } static inline loff_t page_file_offset(struct page *page) { return ((loff_t)page_index(page)) << PAGE_SHIFT; } extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, unsigned long address); static inline pgoff_t linear_page_index(struct vm_area_struct *vma, unsigned long address) { pgoff_t pgoff; if (unlikely(is_vm_hugetlb_page(vma))) return linear_hugepage_index(vma, address); pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; return pgoff; } struct wait_page_key { struct page *page; int bit_nr; int page_match; }; struct wait_page_queue { struct page *page; int bit_nr; wait_queue_entry_t wait; }; static inline bool wake_page_match(struct wait_page_queue *wait_page, struct wait_page_key *key) { if (wait_page->page != key->page) return false; key->page_match = 1; if (wait_page->bit_nr != key->bit_nr) return false; return true; } extern void __lock_page(struct page *page); extern int __lock_page_killable(struct page *page); extern int __lock_page_async(struct page *page, struct wait_page_queue *wait); extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags); extern void unlock_page(struct page *page); /* * Return true if the page was successfully locked */ static inline int trylock_page(struct page *page) { page = compound_head(page); return (likely(!test_and_set_bit_lock(PG_locked, &page->flags))); } /* * lock_page may only be called if we have the page's inode pinned. */ static inline void lock_page(struct page *page) { might_sleep(); if (!trylock_page(page)) __lock_page(page); } /* * lock_page_killable is like lock_page but can be interrupted by fatal * signals. It returns 0 if it locked the page and -EINTR if it was * killed while waiting. */ static inline int lock_page_killable(struct page *page) { might_sleep(); if (!trylock_page(page)) return __lock_page_killable(page); return 0; } /* * lock_page_async - Lock the page, unless this would block. If the page * is already locked, then queue a callback when the page becomes unlocked. * This callback can then retry the operation. * * Returns 0 if the page is locked successfully, or -EIOCBQUEUED if the page * was already locked and the callback defined in 'wait' was queued. */ static inline int lock_page_async(struct page *page, struct wait_page_queue *wait) { if (!trylock_page(page)) return __lock_page_async(page, wait); return 0; } /* * lock_page_or_retry - Lock the page, unless this would block and the * caller indicated that it can handle a retry. * * Return value and mmap_lock implications depend on flags; see * __lock_page_or_retry(). */ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { might_sleep(); return trylock_page(page) || __lock_page_or_retry(page, mm, flags); } /* * This is exported only for wait_on_page_locked/wait_on_page_writeback, etc., * and should not be used directly. */ extern void wait_on_page_bit(struct page *page, int bit_nr); extern int wait_on_page_bit_killable(struct page *page, int bit_nr); /* * Wait for a page to be unlocked. * * This must be called with the caller "holding" the page, * ie with increased "page->count" so that the page won't * go away during the wait.. */ static inline void wait_on_page_locked(struct page *page) { if (PageLocked(page)) wait_on_page_bit(compound_head(page), PG_locked); } static inline int wait_on_page_locked_killable(struct page *page) { if (!PageLocked(page)) return 0; return wait_on_page_bit_killable(compound_head(page), PG_locked); } extern void put_and_wait_on_page_locked(struct page *page); void wait_on_page_writeback(struct page *page); extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); void page_endio(struct page *page, bool is_write, int err); /* * Add an arbitrary waiter to a page's wait queue */ extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter); /* * Fault everything in given userspace address range in. */ static inline int fault_in_pages_writeable(char __user *uaddr, int size) { char __user *end = uaddr + size - 1; if (unlikely(size == 0)) return 0; if (unlikely(uaddr > end)) return -EFAULT; /* * Writing zeroes into userspace here is OK, because we know that if * the zero gets there, we'll be overwriting it. */ do { if (unlikely(__put_user(0, uaddr) != 0)) return -EFAULT; uaddr += PAGE_SIZE; } while (uaddr <= end); /* Check whether the range spilled into the next page. */ if (((unsigned long)uaddr & PAGE_MASK) == ((unsigned long)end & PAGE_MASK)) return __put_user(0, end); return 0; } static inline int fault_in_pages_readable(const char __user *uaddr, int size) { volatile char c; const char __user *end = uaddr + size - 1; if (unlikely(size == 0)) return 0; if (unlikely(uaddr > end)) return -EFAULT; do { if (unlikely(__get_user(c, uaddr) != 0)) return -EFAULT; uaddr += PAGE_SIZE; } while (uaddr <= end); /* Check whether the range spilled into the next page. */ if (((unsigned long)uaddr & PAGE_MASK) == ((unsigned long)end & PAGE_MASK)) { return __get_user(c, end); } (void)c; return 0; } int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void delete_from_page_cache(struct page *page); extern void __delete_from_page_cache(struct page *page, void *shadow); int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec); /* * Like add_to_page_cache_locked, but used to add newly allocated pages: * the page is new, so we can just run __SetPageLocked() against it. */ static inline int add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { int error; __SetPageLocked(page); error = add_to_page_cache_locked(page, mapping, offset, gfp_mask); if (unlikely(error)) __ClearPageLocked(page); return error; } /** * struct readahead_control - Describes a readahead request. * * A readahead request is for consecutive pages. Filesystems which * implement the ->readahead method should call readahead_page() or * readahead_page_batch() in a loop and attempt to start I/O against * each page in the request. * * Most of the fields in this struct are private and should be accessed * by the functions below. * * @file: The file, used primarily by network filesystems for authentication. * May be NULL if invoked internally by the filesystem. * @mapping: Readahead this filesystem object. */ struct readahead_control { struct file *file; struct address_space *mapping; /* private: use the readahead_* accessors instead */ pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; }; #define DEFINE_READAHEAD(rac, f, m, i) \ struct readahead_control rac = { \ .file = f, \ .mapping = m, \ ._index = i, \ } #define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) void page_cache_ra_unbounded(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_count); void page_cache_sync_ra(struct readahead_control *, struct file_ra_state *, unsigned long req_count); void page_cache_async_ra(struct readahead_control *, struct file_ra_state *, struct page *, unsigned long req_count); /** * page_cache_sync_readahead - generic file readahead * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * * page_cache_sync_readahead() should be called when a cache miss happened: * it will submit the read. The readahead logic may decide to piggyback more * pages onto the read request if access patterns suggest it will improve * performance. */ static inline void page_cache_sync_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, mapping, index); page_cache_sync_ra(&ractl, ra, req_count); } /** * page_cache_async_readahead - file readahead for marked pages * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. * @page: The page at @index which triggered the readahead call. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * * page_cache_async_readahead() should be called when a page is used which * is marked as PageReadahead; this is a marker to suggest that the application * has used up enough of the readahead window that we should start pulling in * more pages. */ static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, struct page *page, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, mapping, index); page_cache_async_ra(&ractl, ra, page, req_count); } /** * readahead_page - Get the next page to read. * @rac: The current readahead request. * * Context: The page is locked and has an elevated refcount. The caller * should decreases the refcount once the page has been submitted for I/O * and unlock the page once all I/O to that page has completed. * Return: A pointer to the next page, or %NULL if we are done. */ static inline struct page *readahead_page(struct readahead_control *rac) { struct page *page; BUG_ON(rac->_batch_count > rac->_nr_pages); rac->_nr_pages -= rac->_batch_count; rac->_index += rac->_batch_count; if (!rac->_nr_pages) { rac->_batch_count = 0; return NULL; } page = xa_load(&rac->mapping->i_pages, rac->_index); VM_BUG_ON_PAGE(!PageLocked(page), page); rac->_batch_count = thp_nr_pages(page); return page; } static inline unsigned int __readahead_batch(struct readahead_control *rac, struct page **array, unsigned int array_sz) { unsigned int i = 0; XA_STATE(xas, &rac->mapping->i_pages, 0); struct page *page; BUG_ON(rac->_batch_count > rac->_nr_pages); rac->_nr_pages -= rac->_batch_count; rac->_index += rac->_batch_count; rac->_batch_count = 0; xas_set(&xas, rac->_index); rcu_read_lock(); xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) { if (xas_retry(&xas, page)) continue; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; rac->_batch_count += thp_nr_pages(page); /* * The page cache isn't using multi-index entries yet, * so the xas cursor needs to be manually moved to the * next index. This can be removed once the page cache * is converted. */ if (PageHead(page)) xas_set(&xas, rac->_index + rac->_batch_count); if (i == array_sz) break; } rcu_read_unlock(); return i; } /** * readahead_page_batch - Get a batch of pages to read. * @rac: The current readahead request. * @array: An array of pointers to struct page. * * Context: The pages are locked and have an elevated refcount. The caller * should decreases the refcount once the page has been submitted for I/O * and unlock the page once all I/O to that page has completed. * Return: The number of pages placed in the array. 0 indicates the request * is complete. */ #define readahead_page_batch(rac, array) \ __readahead_batch(rac, array, ARRAY_SIZE(array)) /** * readahead_pos - The byte offset into the file of this readahead request. * @rac: The readahead request. */ static inline loff_t readahead_pos(struct readahead_control *rac) { return (loff_t)rac->_index * PAGE_SIZE; } /** * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */ static inline loff_t readahead_length(struct readahead_control *rac) { return (loff_t)rac->_nr_pages * PAGE_SIZE; } /** * readahead_index - The index of the first page in this readahead request. * @rac: The readahead request. */ static inline pgoff_t readahead_index(struct readahead_control *rac) { return rac->_index; } /** * readahead_count - The number of pages in this readahead request. * @rac: The readahead request. */ static inline unsigned int readahead_count(struct readahead_control *rac) { return rac->_nr_pages; } static inline unsigned long dir_pages(struct inode *inode) { return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; } /** * page_mkwrite_check_truncate - check if page was truncated * @page: the page to check * @inode: the inode to check the page against * * Returns the number of bytes in the page up to EOF, * or -EFAULT if the page was truncated. */ static inline int page_mkwrite_check_truncate(struct page *page, struct inode *inode) { loff_t size = i_size_read(inode); pgoff_t index = size >> PAGE_SHIFT; int offset = offset_in_page(size); if (page->mapping != inode->i_mapping) return -EFAULT; /* page is wholly inside EOF */ if (page->index < index) return PAGE_SIZE; /* page is wholly past EOF */ if (page->index > index || !offset) return -EFAULT; /* page is partially inside EOF */ return offset; } /** * i_blocks_per_page - How many blocks fit in this page. * @inode: The inode which contains the blocks. * @page: The page (head page if the page is a THP). * * If the block size is larger than the size of this page, return zero. * * Context: The caller should hold a refcount on the page to prevent it * from being split. * Return: The number of filesystem blocks covered by this page. */ static inline unsigned int i_blocks_per_page(struct inode *inode, struct page *page) { return thp_size(page) >> inode->i_blkbits; } #endif /* _LINUX_PAGEMAP_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BITMAP_H #define __LINUX_BITMAP_H #ifndef __ASSEMBLY__ #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/types.h> struct device; /* * bitmaps provide bit arrays that consume one or more unsigned * longs. The bitmap interface and available operations are listed * here, in bitmap.h * * Function implementations generic to all architectures are in * lib/bitmap.c. Functions implementations that are architecture * specific are in various include/asm-<arch>/bitops.h headers * and other arch/<arch> specific files. * * See lib/bitmap.c for more details. */ /** * DOC: bitmap overview * * The available bitmap operations and their rough meaning in the * case that the bitmap is a single unsigned long are thus: * * The generated code is more efficient when nbits is known at * compile-time and at most BITS_PER_LONG. * * :: * * bitmap_zero(dst, nbits) *dst = 0UL * bitmap_fill(dst, nbits) *dst = ~0UL * bitmap_copy(dst, src, nbits) *dst = *src * bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2 * bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2 * bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2 * bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2) * bitmap_complement(dst, src, nbits) *dst = ~(*src) * bitmap_equal(src1, src2, nbits) Are *src1 and *src2 equal? * bitmap_intersects(src1, src2, nbits) Do *src1 and *src2 overlap? * bitmap_subset(src1, src2, nbits) Is *src1 a subset of *src2? * bitmap_empty(src, nbits) Are all bits zero in *src? * bitmap_full(src, nbits) Are all bits set in *src? * bitmap_weight(src, nbits) Hamming Weight: number set bits * bitmap_set(dst, pos, nbits) Set specified bit area * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area * bitmap_find_next_zero_area_off(buf, len, pos, n, mask, mask_off) as above * bitmap_next_clear_region(map, &start, &end, nbits) Find next clear region * bitmap_next_set_region(map, &start, &end, nbits) Find next set region * bitmap_for_each_clear_region(map, rs, re, start, end) * Iterate over all clear regions * bitmap_for_each_set_region(map, rs, re, start, end) * Iterate over all set regions * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n * bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest * bitmap_replace(dst, old, new, mask, nbits) *dst = (*old & ~(*mask)) | (*new & *mask) * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) * bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap * bitmap_fold(dst, orig, sz, nbits) dst bits = orig bits mod sz * bitmap_parse(buf, buflen, dst, nbits) Parse bitmap dst from kernel buf * bitmap_parse_user(ubuf, ulen, dst, nbits) Parse bitmap dst from user buf * bitmap_parselist(buf, dst, nbits) Parse bitmap dst from kernel buf * bitmap_parselist_user(buf, dst, nbits) Parse bitmap dst from user buf * bitmap_find_free_region(bitmap, bits, order) Find and allocate bit region * bitmap_release_region(bitmap, pos, order) Free specified bit region * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region * bitmap_from_arr32(dst, buf, nbits) Copy nbits from u32[] buf to dst * bitmap_to_arr32(buf, src, nbits) Copy nbits from buf to u32[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start * * Note, bitmap_zero() and bitmap_fill() operate over the region of * unsigned longs, that is, bits behind bitmap till the unsigned long * boundary will be zeroed or filled as well. Consider to use * bitmap_clear() or bitmap_set() to make explicit zeroing or filling * respectively. */ /** * DOC: bitmap bitops * * Also the following operations in asm/bitops.h apply to bitmaps.:: * * set_bit(bit, addr) *addr |= bit * clear_bit(bit, addr) *addr &= ~bit * change_bit(bit, addr) *addr ^= bit * test_bit(bit, addr) Is bit set in *addr? * test_and_set_bit(bit, addr) Set bit and return old value * test_and_clear_bit(bit, addr) Clear bit and return old value * test_and_change_bit(bit, addr) Change bit and return old value * find_first_zero_bit(addr, nbits) Position first zero bit in *addr * find_first_bit(addr, nbits) Position first set bit in *addr * find_next_zero_bit(addr, nbits, bit) * Position next zero bit in *addr >= bit * find_next_bit(addr, nbits, bit) Position next set bit in *addr >= bit * find_next_and_bit(addr1, addr2, nbits, bit) * Same as find_next_bit, but in * (*addr1 & *addr2) * */ /** * DOC: declare bitmap * The DECLARE_BITMAP(name,bits) macro, in linux/types.h, can be used * to declare an array named 'name' of just enough unsigned longs to * contain all bit positions from 0 to 'bits' - 1. */ /* * Allocation and deallocation of bitmap. * Provided in lib/bitmap.c to avoid circular dependency. */ extern unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags); extern unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags); extern void bitmap_free(const unsigned long *bitmap); /* Managed variants of the above. */ unsigned long *devm_bitmap_alloc(struct device *dev, unsigned int nbits, gfp_t flags); unsigned long *devm_bitmap_zalloc(struct device *dev, unsigned int nbits, gfp_t flags); /* * lib/bitmap.c provides these functions: */ extern int __bitmap_empty(const unsigned long *bitmap, unsigned int nbits); extern int __bitmap_full(const unsigned long *bitmap, unsigned int nbits); extern int __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern bool __pure __bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, const unsigned long *src3, unsigned int nbits); extern void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits); extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); extern void bitmap_cut(unsigned long *dst, const unsigned long *src, unsigned int first, unsigned int cut, unsigned int nbits); extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits); extern int __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); extern void __bitmap_set(unsigned long *map, unsigned int start, int len); extern void __bitmap_clear(unsigned long *map, unsigned int start, int len); extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask, unsigned long align_offset); /** * bitmap_find_next_zero_area - find a contiguous aligned zero area * @map: The address to base the search on * @size: The bitmap size in bits * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @align_mask: Alignment mask for zero area * * The @align_mask should be one less than a power of 2; the effect is that * the bit offset of all zero areas this function finds is multiples of that * power of 2. A @align_mask of 0 means no alignment is required. */ static inline unsigned long bitmap_find_next_zero_area(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask) { return bitmap_find_next_zero_area_off(map, size, start, nr, align_mask, 0); } extern int bitmap_parse(const char *buf, unsigned int buflen, unsigned long *dst, int nbits); extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); extern int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits); extern int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits); extern void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits); extern int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits); extern void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits); extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, unsigned int sz, unsigned int nbits); extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); #ifdef __BIG_ENDIAN extern void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits); #else #define bitmap_copy_le bitmap_copy #endif extern unsigned int bitmap_ord_to_pos(const unsigned long *bitmap, unsigned int ord, unsigned int nbits); extern int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) /* * The static inlines below do not handle constant nbits==0 correctly, * so make such users (should any ever turn up) call the out-of-line * versions. */ #define small_const_nbits(nbits) \ (__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG && (nbits) > 0) #define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { unsigned int len = bitmap_size(nbits); memset(dst, 0, len); } static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { unsigned int len = bitmap_size(nbits); memset(dst, 0xff, len); } static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { unsigned int len = bitmap_size(nbits); memcpy(dst, src, len); } /* * Copy bitmap and clear tail bits in last word. */ static inline void bitmap_copy_clear_tail(unsigned long *dst, const unsigned long *src, unsigned int nbits) { bitmap_copy(dst, src, nbits); if (nbits % BITS_PER_LONG) dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); } static inline void bitmap_copy_and_extend(unsigned long *to, const unsigned long *from, unsigned int count, unsigned int size) { unsigned int copy = BITS_TO_LONGS(count); memcpy(to, from, copy * sizeof(long)); if (count % BITS_PER_LONG) to[copy - 1] &= BITMAP_LAST_WORD_MASK(count); memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long)); } /* * On 32-bit systems bitmaps are represented as u32 arrays internally, and * therefore conversion is not needed when copying data from/to arrays of u32. */ #if BITS_PER_LONG == 64 extern void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits); extern void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits); #else #define bitmap_from_arr32(bitmap, buf, nbits) \ bitmap_copy_clear_tail((unsigned long *) (bitmap), \ (const unsigned long *) (buf), (nbits)) #define bitmap_to_arr32(buf, bitmap, nbits) \ bitmap_copy_clear_tail((unsigned long *) (buf), \ (const unsigned long *) (bitmap), (nbits)) #endif static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_and(dst, src1, src2, nbits); } static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 | *src2; else __bitmap_or(dst, src1, src2, nbits); } static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 ^ *src2; else __bitmap_xor(dst, src1, src2, nbits); } static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_andnot(dst, src1, src2, nbits); } static inline void bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = ~(*src); else __bitmap_complement(dst, src, nbits); } #ifdef __LITTLE_ENDIAN #define BITMAP_MEM_ALIGNMENT 8 #else #define BITMAP_MEM_ALIGNMENT (8 * sizeof(unsigned long)) #endif #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1) static inline int bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); if (__builtin_constant_p(nbits & BITMAP_MEM_MASK) && IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) return !memcmp(src1, src2, nbits / 8); return __bitmap_equal(src1, src2, nbits); } /** * bitmap_or_equal - Check whether the or of two bitmaps is equal to a third * @src1: Pointer to bitmap 1 * @src2: Pointer to bitmap 2 will be or'ed with bitmap 1 * @src3: Pointer to bitmap 3. Compare to the result of *@src1 | *@src2 * @nbits: number of bits in each of these bitmaps * * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise */ static inline bool bitmap_or_equal(const unsigned long *src1, const unsigned long *src2, const unsigned long *src3, unsigned int nbits) { if (!small_const_nbits(nbits)) return __bitmap_or_equal(src1, src2, src3, nbits); return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits)); } static inline int bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; else return __bitmap_intersects(src1, src2, nbits); } static inline int bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits)); else return __bitmap_subset(src1, src2, nbits); } static inline int bitmap_empty(const unsigned long *src, unsigned nbits) { if (small_const_nbits(nbits)) return ! (*src & BITMAP_LAST_WORD_MASK(nbits)); return find_first_bit(src, nbits) == nbits; } static inline int bitmap_full(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits)); return find_first_zero_bit(src, nbits) == nbits; } static __always_inline int bitmap_weight(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits)); return __bitmap_weight(src, nbits); } static __always_inline void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __set_bit(start, map); else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && __builtin_constant_p(nbits & BITMAP_MEM_MASK) && IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) memset((char *)map + start / 8, 0xff, nbits / 8); else __bitmap_set(map, start, nbits); } static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, unsigned int nbits) { if (__builtin_constant_p(nbits) && nbits == 1) __clear_bit(start, map); else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && __builtin_constant_p(nbits & BITMAP_MEM_MASK) && IS_ALIGNED(nbits, BITMAP_MEM_ALIGNMENT)) memset((char *)map + start / 8, 0, nbits / 8); else __bitmap_clear(map, start, nbits); } static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift; else __bitmap_shift_right(dst, src, shift, nbits); } static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits); else __bitmap_shift_left(dst, src, shift, nbits); } static inline void bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = (*old & ~(*mask)) | (*new & *mask); else __bitmap_replace(dst, old, new, mask, nbits); } static inline void bitmap_next_clear_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) { *rs = find_next_zero_bit(bitmap, end, *rs); *re = find_next_bit(bitmap, end, *rs + 1); } static inline void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) { *rs = find_next_bit(bitmap, end, *rs); *re = find_next_zero_bit(bitmap, end, *rs + 1); } /* * Bitmap region iterators. Iterates over the bitmap between [@start, @end). * @rs and @re should be integer variables and will be set to start and end * index of the current clear or set region. */ #define bitmap_for_each_clear_region(bitmap, rs, re, start, end) \ for ((rs) = (start), \ bitmap_next_clear_region((bitmap), &(rs), &(re), (end)); \ (rs) < (re); \ (rs) = (re) + 1, \ bitmap_next_clear_region((bitmap), &(rs), &(re), (end))) #define bitmap_for_each_set_region(bitmap, rs, re, start, end) \ for ((rs) = (start), \ bitmap_next_set_region((bitmap), &(rs), &(re), (end)); \ (rs) < (re); \ (rs) = (re) + 1, \ bitmap_next_set_region((bitmap), &(rs), &(re), (end))) /** * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap. * @n: u64 value * * Linux bitmaps are internally arrays of unsigned longs, i.e. 32-bit * integers in 32-bit environment, and 64-bit integers in 64-bit one. * * There are four combinations of endianness and length of the word in linux * ABIs: LE64, BE64, LE32 and BE32. * * On 64-bit kernels 64-bit LE and BE numbers are naturally ordered in * bitmaps and therefore don't require any special handling. * * On 32-bit kernels 32-bit LE ABI orders lo word of 64-bit number in memory * prior to hi, and 32-bit BE orders hi word prior to lo. The bitmap on the * other hand is represented as an array of 32-bit words and the position of * bit N may therefore be calculated as: word #(N/32) and bit #(N%32) in that * word. For example, bit #42 is located at 10th position of 2nd word. * It matches 32-bit LE ABI, and we can simply let the compiler store 64-bit * values in memory as it usually does. But for BE we need to swap hi and lo * words manually. * * With all that, the macro BITMAP_FROM_U64() does explicit reordering of hi and * lo parts of u64. For LE32 it does nothing, and for BE environment it swaps * hi and lo words, as is expected by bitmap. */ #if __BITS_PER_LONG == 64 #define BITMAP_FROM_U64(n) (n) #else #define BITMAP_FROM_U64(n) ((unsigned long) ((u64)(n) & ULONG_MAX)), \ ((unsigned long) ((u64)(n) >> 32)) #endif /** * bitmap_from_u64 - Check and swap words within u64. * @mask: source bitmap * @dst: destination bitmap * * In 32-bit Big Endian kernel, when using ``(u32 *)(&val)[*]`` * to read u64 mask, we will get the wrong word. * That is ``(u32 *)(&val)[0]`` gets the upper 32 bits, * but we expect the lower 32-bits of u64. */ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) { dst[0] = mask & ULONG_MAX; if (sizeof(mask) > sizeof(unsigned long)) dst[1] = mask >> 32; } /** * bitmap_get_value8 - get an 8-bit value within a memory region * @map: address to the bitmap memory region * @start: bit offset of the 8-bit value; must be a multiple of 8 * * Returns the 8-bit value located at the @start bit offset within the @src * memory region. */ static inline unsigned long bitmap_get_value8(const unsigned long *map, unsigned long start) { const size_t index = BIT_WORD(start); const unsigned long offset = start % BITS_PER_LONG; return (map[index] >> offset) & 0xFF; } /** * bitmap_set_value8 - set an 8-bit value within a memory region * @map: address to the bitmap memory region * @value: the 8-bit value; values wider than 8 bits may clobber bitmap * @start: bit offset of the 8-bit value; must be a multiple of 8 */ static inline void bitmap_set_value8(unsigned long *map, unsigned long value, unsigned long start) { const size_t index = BIT_WORD(start); const unsigned long offset = start % BITS_PER_LONG; map[index] &= ~(0xFFUL << offset); map[index] |= value << offset; } #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _LINUX_KPROBES_H #define _LINUX_KPROBES_H /* * Kernel Probes (KProbes) * include/linux/kprobes.h * * Copyright (C) IBM Corporation, 2002, 2004 * * 2002-Oct Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel * Probes initial implementation ( includes suggestions from * Rusty Russell). * 2004-July Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes * interface to access function arguments. * 2005-May Hien Nguyen <hien@us.ibm.com> and Jim Keniston * <jkenisto@us.ibm.com> and Prasanna S Panchamukhi * <prasanna@in.ibm.com> added function-return probes. */ #include <linux/compiler.h> #include <linux/linkage.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/smp.h> #include <linux/bug.h> #include <linux/percpu.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/mutex.h> #include <linux/ftrace.h> #include <asm/kprobes.h> #ifdef CONFIG_KPROBES /* kprobe_status settings */ #define KPROBE_HIT_ACTIVE 0x00000001 #define KPROBE_HIT_SS 0x00000002 #define KPROBE_REENTER 0x00000004 #define KPROBE_HIT_SSDONE 0x00000008 #else /* CONFIG_KPROBES */ #include <asm-generic/kprobes.h> typedef int kprobe_opcode_t; struct arch_specific_insn { int dummy; }; #endif /* CONFIG_KPROBES */ struct kprobe; struct pt_regs; struct kretprobe; struct kretprobe_instance; typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *); typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *, unsigned long flags); typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *, int trapnr); typedef int (*kretprobe_handler_t) (struct kretprobe_instance *, struct pt_regs *); struct kprobe { struct hlist_node hlist; /* list of kprobes for multi-handler support */ struct list_head list; /*count the number of times this probe was temporarily disarmed */ unsigned long nmissed; /* location of the probe point */ kprobe_opcode_t *addr; /* Allow user to indicate symbol name of the probe point */ const char *symbol_name; /* Offset into the symbol */ unsigned int offset; /* Called before addr is executed. */ kprobe_pre_handler_t pre_handler; /* Called after addr is executed, unless... */ kprobe_post_handler_t post_handler; /* * ... called if executing addr causes a fault (eg. page fault). * Return 1 if it handled fault, otherwise kernel will see it. */ kprobe_fault_handler_t fault_handler; /* Saved opcode (which has been replaced with breakpoint) */ kprobe_opcode_t opcode; /* copy of the original instruction */ struct arch_specific_insn ainsn; /* * Indicates various status flags. * Protected by kprobe_mutex after this kprobe is registered. */ u32 flags; }; /* Kprobe status flags */ #define KPROBE_FLAG_GONE 1 /* breakpoint has already gone */ #define KPROBE_FLAG_DISABLED 2 /* probe is temporarily disabled */ #define KPROBE_FLAG_OPTIMIZED 4 /* * probe is really optimized. * NOTE: * this flag is only for optimized_kprobe. */ #define KPROBE_FLAG_FTRACE 8 /* probe is using ftrace */ /* Has this kprobe gone ? */ static inline int kprobe_gone(struct kprobe *p) { return p->flags & KPROBE_FLAG_GONE; } /* Is this kprobe disabled ? */ static inline int kprobe_disabled(struct kprobe *p) { return p->flags & (KPROBE_FLAG_DISABLED | KPROBE_FLAG_GONE); } /* Is this kprobe really running optimized path ? */ static inline int kprobe_optimized(struct kprobe *p) { return p->flags & KPROBE_FLAG_OPTIMIZED; } /* Is this kprobe uses ftrace ? */ static inline int kprobe_ftrace(struct kprobe *p) { return p->flags & KPROBE_FLAG_FTRACE; } /* * Function-return probe - * Note: * User needs to provide a handler function, and initialize maxactive. * maxactive - The maximum number of instances of the probed function that * can be active concurrently. * nmissed - tracks the number of times the probed function's return was * ignored, due to maxactive being too low. * */ struct kretprobe { struct kprobe kp; kretprobe_handler_t handler; kretprobe_handler_t entry_handler; int maxactive; int nmissed; size_t data_size; struct hlist_head free_instances; raw_spinlock_t lock; }; #define KRETPROBE_MAX_DATA_SIZE 4096 struct kretprobe_instance { union { struct hlist_node hlist; struct rcu_head rcu; }; struct kretprobe *rp; kprobe_opcode_t *ret_addr; struct task_struct *task; void *fp; char data[]; }; struct kretprobe_blackpoint { const char *name; void *addr; }; struct kprobe_blacklist_entry { struct list_head list; unsigned long start_addr; unsigned long end_addr; }; #ifdef CONFIG_KPROBES DECLARE_PER_CPU(struct kprobe *, current_kprobe); DECLARE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); /* * For #ifdef avoidance: */ static inline int kprobes_built_in(void) { return 1; } extern void kprobe_busy_begin(void); extern void kprobe_busy_end(void); #ifdef CONFIG_KRETPROBES extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs); extern int arch_trampoline_kprobe(struct kprobe *p); /* If the trampoline handler called from a kprobe, use this version */ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, void *trampoline_address, void *frame_pointer); static nokprobe_inline unsigned long kretprobe_trampoline_handler(struct pt_regs *regs, void *trampoline_address, void *frame_pointer) { unsigned long ret; /* * Set a dummy kprobe for avoiding kretprobe recursion. * Since kretprobe never runs in kprobe handler, no kprobe must * be running at this point. */ kprobe_busy_begin(); ret = __kretprobe_trampoline_handler(regs, trampoline_address, frame_pointer); kprobe_busy_end(); return ret; } #else /* CONFIG_KRETPROBES */ static inline void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) { } static inline int arch_trampoline_kprobe(struct kprobe *p) { return 0; } #endif /* CONFIG_KRETPROBES */ extern struct kretprobe_blackpoint kretprobe_blacklist[]; #ifdef CONFIG_KPROBES_SANITY_TEST extern int init_test_probes(void); #else static inline int init_test_probes(void) { return 0; } #endif /* CONFIG_KPROBES_SANITY_TEST */ extern int arch_prepare_kprobe(struct kprobe *p); extern void arch_arm_kprobe(struct kprobe *p); extern void arch_disarm_kprobe(struct kprobe *p); extern int arch_init_kprobes(void); extern void kprobes_inc_nmissed_count(struct kprobe *p); extern bool arch_within_kprobe_blacklist(unsigned long addr); extern int arch_populate_kprobe_blacklist(void); extern bool arch_kprobe_on_func_entry(unsigned long offset); extern int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset); extern bool within_kprobe_blacklist(unsigned long addr); extern int kprobe_add_ksym_blacklist(unsigned long entry); extern int kprobe_add_area_blacklist(unsigned long start, unsigned long end); struct kprobe_insn_cache { struct mutex mutex; void *(*alloc)(void); /* allocate insn page */ void (*free)(void *); /* free insn page */ const char *sym; /* symbol for insn pages */ struct list_head pages; /* list of kprobe_insn_page */ size_t insn_size; /* size of instruction slot */ int nr_garbage; }; #ifdef __ARCH_WANT_KPROBES_INSN_SLOT extern kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c); extern void __free_insn_slot(struct kprobe_insn_cache *c, kprobe_opcode_t *slot, int dirty); /* sleep-less address checking routine */ extern bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr); #define DEFINE_INSN_CACHE_OPS(__name) \ extern struct kprobe_insn_cache kprobe_##__name##_slots; \ \ static inline kprobe_opcode_t *get_##__name##_slot(void) \ { \ return __get_insn_slot(&kprobe_##__name##_slots); \ } \ \ static inline void free_##__name##_slot(kprobe_opcode_t *slot, int dirty)\ { \ __free_insn_slot(&kprobe_##__name##_slots, slot, dirty); \ } \ \ static inline bool is_kprobe_##__name##_slot(unsigned long addr) \ { \ return __is_insn_slot_addr(&kprobe_##__name##_slots, addr); \ } #define KPROBE_INSN_PAGE_SYM "kprobe_insn_page" #define KPROBE_OPTINSN_PAGE_SYM "kprobe_optinsn_page" int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum, unsigned long *value, char *type, char *sym); #else /* __ARCH_WANT_KPROBES_INSN_SLOT */ #define DEFINE_INSN_CACHE_OPS(__name) \ static inline bool is_kprobe_##__name##_slot(unsigned long addr) \ { \ return 0; \ } #endif DEFINE_INSN_CACHE_OPS(insn); #ifdef CONFIG_OPTPROBES /* * Internal structure for direct jump optimized probe */ struct optimized_kprobe { struct kprobe kp; struct list_head list; /* list for optimizing queue */ struct arch_optimized_insn optinsn; }; /* Architecture dependent functions for direct jump optimization */ extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn); extern int arch_check_optimized_kprobe(struct optimized_kprobe *op); extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *orig); extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op); extern void arch_optimize_kprobes(struct list_head *oplist); extern void arch_unoptimize_kprobes(struct list_head *oplist, struct list_head *done_list); extern void arch_unoptimize_kprobe(struct optimized_kprobe *op); extern int arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr); extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs); DEFINE_INSN_CACHE_OPS(optinsn); #ifdef CONFIG_SYSCTL extern int sysctl_kprobes_optimization; extern int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); #endif extern void wait_for_kprobe_optimizer(void); bool optprobe_queued_unopt(struct optimized_kprobe *op); bool kprobe_disarmed(struct kprobe *p); #else static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ #ifdef CONFIG_KPROBES_ON_FTRACE extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct pt_regs *regs); extern int arch_prepare_kprobe_ftrace(struct kprobe *p); #endif int arch_check_ftrace_location(struct kprobe *p); /* Get the kprobe at this addr (if any) - called with preemption disabled */ struct kprobe *get_kprobe(void *addr); /* kprobe_running() will just return the current_kprobe on this CPU */ static inline struct kprobe *kprobe_running(void) { return (__this_cpu_read(current_kprobe)); } static inline void reset_current_kprobe(void) { __this_cpu_write(current_kprobe, NULL); } static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void) { return this_cpu_ptr(&kprobe_ctlblk); } kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset); int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); void unregister_kprobes(struct kprobe **kps, int num); unsigned long arch_deref_entry_point(void *); int register_kretprobe(struct kretprobe *rp); void unregister_kretprobe(struct kretprobe *rp); int register_kretprobes(struct kretprobe **rps, int num); void unregister_kretprobes(struct kretprobe **rps, int num); void kprobe_flush_task(struct task_struct *tk); void kprobe_free_init_mem(void); int disable_kprobe(struct kprobe *kp); int enable_kprobe(struct kprobe *kp); void dump_kprobe(struct kprobe *kp); void *alloc_insn_page(void); void free_insn_page(void *page); int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value, char *type, char *sym); #else /* !CONFIG_KPROBES: */ static inline int kprobes_built_in(void) { return 0; } static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) { return 0; } static inline struct kprobe *get_kprobe(void *addr) { return NULL; } static inline struct kprobe *kprobe_running(void) { return NULL; } static inline int register_kprobe(struct kprobe *p) { return -ENOSYS; } static inline int register_kprobes(struct kprobe **kps, int num) { return -ENOSYS; } static inline void unregister_kprobe(struct kprobe *p) { } static inline void unregister_kprobes(struct kprobe **kps, int num) { } static inline int register_kretprobe(struct kretprobe *rp) { return -ENOSYS; } static inline int register_kretprobes(struct kretprobe **rps, int num) { return -ENOSYS; } static inline void unregister_kretprobe(struct kretprobe *rp) { } static inline void unregister_kretprobes(struct kretprobe **rps, int num) { } static inline void kprobe_flush_task(struct task_struct *tk) { } static inline void kprobe_free_init_mem(void) { } static inline int disable_kprobe(struct kprobe *kp) { return -ENOSYS; } static inline int enable_kprobe(struct kprobe *kp) { return -ENOSYS; } static inline bool within_kprobe_blacklist(unsigned long addr) { return true; } static inline int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { return -ERANGE; } #endif /* CONFIG_KPROBES */ static inline int disable_kretprobe(struct kretprobe *rp) { return disable_kprobe(&rp->kp); } static inline int enable_kretprobe(struct kretprobe *rp) { return enable_kprobe(&rp->kp); } #ifndef CONFIG_KPROBES static inline bool is_kprobe_insn_slot(unsigned long addr) { return false; } #endif #ifndef CONFIG_OPTPROBES static inline bool is_kprobe_optinsn_slot(unsigned long addr) { return false; } #endif /* Returns true if kprobes handled the fault */ static nokprobe_inline bool kprobe_page_fault(struct pt_regs *regs, unsigned int trap) { if (!kprobes_built_in()) return false; if (user_mode(regs)) return false; /* * To be potentially processing a kprobe fault and to be allowed * to call kprobe_running(), we have to be non-preemptible. */ if (preemptible()) return false; if (!kprobe_running()) return false; return kprobe_fault_handler(regs, trap); } #endif /* _LINUX_KPROBES_H */ |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ /* * fsnotify inode mark locking/lifetime/and refcnting * * REFCNT: * The group->recnt and mark->refcnt tell how many "things" in the kernel * currently are referencing the objects. Both kind of objects typically will * live inside the kernel with a refcnt of 2, one for its creation and one for * the reference a group and a mark hold to each other. * If you are holding the appropriate locks, you can take a reference and the * object itself is guaranteed to survive until the reference is dropped. * * LOCKING: * There are 3 locks involved with fsnotify inode marks and they MUST be taken * in order as follows: * * group->mark_mutex * mark->lock * mark->connector->lock * * group->mark_mutex protects the marks_list anchored inside a given group and * each mark is hooked via the g_list. It also protects the groups private * data (i.e group limits). * mark->lock protects the marks attributes like its masks and flags. * Furthermore it protects the access to a reference of the group that the mark * is assigned to as well as the access to a reference of the inode/vfsmount * that is being watched by the mark. * * mark->connector->lock protects the list of marks anchored inside an * inode / vfsmount and each mark is hooked via the i_list. * * A list of notification marks relating to inode / mnt is contained in * fsnotify_mark_connector. That structure is alive as long as there are any * marks in the list and is also protected by fsnotify_mark_srcu. A mark gets * detached from fsnotify_mark_connector when last reference to the mark is * dropped. Thus having mark reference is enough to protect mark->connector * pointer and to make sure fsnotify_mark_connector cannot disappear. Also * because we remove mark from g_list before dropping mark reference associated * with that, any mark found through g_list is guaranteed to have * mark->connector set until we drop group->mark_mutex. * * LIFETIME: * Inode marks survive between when they are added to an inode and when their * refcnt==0. Marks are also protected by fsnotify_mark_srcu. * * The inode mark can be cleared for a number of different reasons including: * - The inode is unlinked for the last time. (fsnotify_inode_remove) * - The inode is being evicted from cache. (fsnotify_inode_delete) * - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes) * - Something explicitly requests that it be removed. (fsnotify_destroy_mark) * - The fsnotify_group associated with the mark is going away and all such marks * need to be cleaned up. (fsnotify_clear_marks_by_group) * * This has the very interesting property of being able to run concurrently with * any (or all) other directions. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/srcu.h> #include <linux/ratelimit.h> #include <linux/atomic.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" #define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */ struct srcu_struct fsnotify_mark_srcu; struct kmem_cache *fsnotify_mark_connector_cachep; static DEFINE_SPINLOCK(destroy_lock); static LIST_HEAD(destroy_list); static struct fsnotify_mark_connector *connector_destroy_list; static void fsnotify_mark_destroy_workfn(struct work_struct *work); static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn); static void fsnotify_connector_destroy_workfn(struct work_struct *work); static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn); void fsnotify_get_mark(struct fsnotify_mark *mark) { WARN_ON_ONCE(!refcount_read(&mark->refcnt)); refcount_inc(&mark->refcnt); } static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn) { if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) return &fsnotify_conn_inode(conn)->i_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) return &fsnotify_conn_sb(conn)->s_fsnotify_mask; return NULL; } __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn) { if (WARN_ON(!fsnotify_valid_obj_type(conn->type))) return 0; return *fsnotify_conn_mask_p(conn); } static void fsnotify_get_inode_ref(struct inode *inode) { ihold(inode); atomic_long_inc(&inode->i_sb->s_fsnotify_connectors); } /* * Grab or drop inode reference for the connector if needed. * * When it's time to drop the reference, we only clear the HAS_IREF flag and * return the inode object. fsnotify_drop_object() will be resonsible for doing * iput() outside of spinlocks. This happens when last mark that wanted iref is * detached. */ static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn, bool want_iref) { bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF; struct inode *inode = NULL; if (conn->type != FSNOTIFY_OBJ_TYPE_INODE || want_iref == has_iref) return NULL; if (want_iref) { /* Pin inode if any mark wants inode refcount held */ fsnotify_get_inode_ref(fsnotify_conn_inode(conn)); conn->flags |= FSNOTIFY_CONN_FLAG_HAS_IREF; } else { /* Unpin inode after detach of last mark that wanted iref */ inode = fsnotify_conn_inode(conn); conn->flags &= ~FSNOTIFY_CONN_FLAG_HAS_IREF; } return inode; } static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { u32 new_mask = 0; bool want_iref = false; struct fsnotify_mark *mark; assert_spin_locked(&conn->lock); /* We can get detached connector here when inode is getting unlinked. */ if (!fsnotify_valid_obj_type(conn->type)) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) continue; new_mask |= fsnotify_calc_mask(mark); if (conn->type == FSNOTIFY_OBJ_TYPE_INODE && !(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) want_iref = true; } *fsnotify_conn_mask_p(conn) = new_mask; return fsnotify_update_iref(conn, want_iref); } static bool fsnotify_conn_watches_children( struct fsnotify_mark_connector *conn) { if (conn->type != FSNOTIFY_OBJ_TYPE_INODE) return false; return fsnotify_inode_watches_children(fsnotify_conn_inode(conn)); } static void fsnotify_conn_set_children_dentry_flags( struct fsnotify_mark_connector *conn) { if (conn->type != FSNOTIFY_OBJ_TYPE_INODE) return; fsnotify_set_children_dentry_flags(fsnotify_conn_inode(conn)); } /* * Calculate mask of events for a list of marks. The caller must make sure * connector and connector->obj cannot disappear under us. Callers achieve * this by holding a mark->lock or mark->group->mark_mutex for a mark on this * list. */ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { bool update_children; if (!conn) return; spin_lock(&conn->lock); update_children = !fsnotify_conn_watches_children(conn); __fsnotify_recalc_mask(conn); update_children &= fsnotify_conn_watches_children(conn); spin_unlock(&conn->lock); /* * Set children's PARENT_WATCHED flags only if parent started watching. * When parent stops watching, we clear false positive PARENT_WATCHED * flags lazily in __fsnotify_parent(). */ if (update_children) fsnotify_conn_set_children_dentry_flags(conn); } /* Free all connectors queued for freeing once SRCU period ends */ static void fsnotify_connector_destroy_workfn(struct work_struct *work) { struct fsnotify_mark_connector *conn, *free; spin_lock(&destroy_lock); conn = connector_destroy_list; connector_destroy_list = NULL; spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); while (conn) { free = conn; conn = conn->destroy_next; kmem_cache_free(fsnotify_mark_connector_cachep, free); } } static void fsnotify_put_inode_ref(struct inode *inode) { struct super_block *sb = inode->i_sb; iput(inode); if (atomic_long_dec_and_test(&sb->s_fsnotify_connectors)) wake_up_var(&sb->s_fsnotify_connectors); } static void fsnotify_get_sb_connectors(struct fsnotify_mark_connector *conn) { struct super_block *sb = fsnotify_connector_sb(conn); if (sb) atomic_long_inc(&sb->s_fsnotify_connectors); } static void fsnotify_put_sb_connectors(struct fsnotify_mark_connector *conn) { struct super_block *sb = fsnotify_connector_sb(conn); if (sb && atomic_long_dec_and_test(&sb->s_fsnotify_connectors)) wake_up_var(&sb->s_fsnotify_connectors); } static void *fsnotify_detach_connector_from_object( struct fsnotify_mark_connector *conn, unsigned int *type) { struct inode *inode = NULL; *type = conn->type; if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) return NULL; if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) { inode = fsnotify_conn_inode(conn); inode->i_fsnotify_mask = 0; /* Unpin inode when detaching from connector */ if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF)) inode = NULL; } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0; } else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) { fsnotify_conn_sb(conn)->s_fsnotify_mask = 0; } fsnotify_put_sb_connectors(conn); rcu_assign_pointer(*(conn->obj), NULL); conn->obj = NULL; conn->type = FSNOTIFY_OBJ_TYPE_DETACHED; return inode; } static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; if (WARN_ON_ONCE(!group)) return; group->ops->free_mark(mark); fsnotify_put_group(group); } /* Drop object reference originally held by a connector */ static void fsnotify_drop_object(unsigned int type, void *objp) { if (!objp) return; /* Currently only inode references are passed to be dropped */ if (WARN_ON_ONCE(type != FSNOTIFY_OBJ_TYPE_INODE)) return; fsnotify_put_inode_ref(objp); } void fsnotify_put_mark(struct fsnotify_mark *mark) { struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector); void *objp = NULL; unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED; bool free_conn = false; /* Catch marks that were actually never attached to object */ if (!conn) { if (refcount_dec_and_test(&mark->refcnt)) fsnotify_final_mark_destroy(mark); return; } /* * We have to be careful so that traversals of obj_list under lock can * safely grab mark reference. */ if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock)) return; hlist_del_init_rcu(&mark->obj_list); if (hlist_empty(&conn->list)) { objp = fsnotify_detach_connector_from_object(conn, &type); free_conn = true; } else { objp = __fsnotify_recalc_mask(conn); type = conn->type; } WRITE_ONCE(mark->connector, NULL); spin_unlock(&conn->lock); fsnotify_drop_object(type, objp); if (free_conn) { spin_lock(&destroy_lock); conn->destroy_next = connector_destroy_list; connector_destroy_list = conn; spin_unlock(&destroy_lock); queue_work(system_unbound_wq, &connector_reaper_work); } /* * Note that we didn't update flags telling whether inode cares about * what's happening with children. We update these flags from * __fsnotify_parent() lazily when next event happens on one of our * children. */ spin_lock(&destroy_lock); list_add(&mark->g_list, &destroy_list); spin_unlock(&destroy_lock); queue_delayed_work(system_unbound_wq, &reaper_work, FSNOTIFY_REAPER_DELAY); } EXPORT_SYMBOL_GPL(fsnotify_put_mark); /* * Get mark reference when we found the mark via lockless traversal of object * list. Mark can be already removed from the list by now and on its way to be * destroyed once SRCU period ends. * * Also pin the group so it doesn't disappear under us. */ static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark) { if (!mark) return true; if (refcount_inc_not_zero(&mark->refcnt)) { spin_lock(&mark->lock); if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) { /* mark is attached, group is still alive then */ atomic_inc(&mark->group->user_waits); spin_unlock(&mark->lock); return true; } spin_unlock(&mark->lock); fsnotify_put_mark(mark); } return false; } /* * Puts marks and wakes up group destruction if necessary. * * Pairs with fsnotify_get_mark_safe() */ static void fsnotify_put_mark_wake(struct fsnotify_mark *mark) { if (mark) { struct fsnotify_group *group = mark->group; fsnotify_put_mark(mark); /* * We abuse notification_waitq on group shutdown for waiting for * all marks pinned when waiting for userspace. */ if (atomic_dec_and_test(&group->user_waits) && group->shutdown) wake_up(&group->notification_waitq); } } bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info) __releases(&fsnotify_mark_srcu) { int type; fsnotify_foreach_iter_type(type) { /* This can fail if mark is being removed */ if (!fsnotify_get_mark_safe(iter_info->marks[type])) { __release(&fsnotify_mark_srcu); goto fail; } } /* * Now that both marks are pinned by refcount in the inode / vfsmount * lists, we can drop SRCU lock, and safely resume the list iteration * once userspace returns. */ srcu_read_unlock(&fsnotify_mark_srcu, iter_info->srcu_idx); return true; fail: for (type--; type >= 0; type--) fsnotify_put_mark_wake(iter_info->marks[type]); return false; } void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info) __acquires(&fsnotify_mark_srcu) { int type; iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); fsnotify_foreach_iter_type(type) fsnotify_put_mark_wake(iter_info->marks[type]); } /* * Mark mark as detached, remove it from group list. Mark still stays in object * list until its last reference is dropped. Note that we rely on mark being * removed from group list before corresponding reference to it is dropped. In * particular we rely on mark->connector being valid while we hold * group->mark_mutex if we found the mark through g_list. * * Must be called with group->mark_mutex held. The caller must either hold * reference to the mark or be protected by fsnotify_mark_srcu. */ void fsnotify_detach_mark(struct fsnotify_mark *mark) { fsnotify_group_assert_locked(mark->group); WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) && refcount_read(&mark->refcnt) < 1 + !!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)); spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED; list_del_init(&mark->g_list); spin_unlock(&mark->lock); /* Drop mark reference acquired in fsnotify_add_mark_locked() */ fsnotify_put_mark(mark); } /* * Free fsnotify mark. The mark is actually only marked as being freed. The * freeing is actually happening only once last reference to the mark is * dropped from a workqueue which first waits for srcu period end. * * Caller must have a reference to the mark or be protected by * fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE; spin_unlock(&mark->lock); /* * Some groups like to know that marks are being freed. This is a * callback to the group function to let it know that this mark * is being freed. */ if (group->ops->freeing_mark) group->ops->freeing_mark(mark, group); } void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { fsnotify_group_lock(group); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); } EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); /* * Sorting function for lists of fsnotify marks. * * Fanotify supports different notification classes (reflected as priority of * notification group). Events shall be passed to notification groups in * decreasing priority order. To achieve this marks in notification lists for * inodes and vfsmounts are sorted so that priorities of corresponding groups * are descending. * * Furthermore correct handling of the ignore mask requires processing inode * and vfsmount marks of each group together. Using the group address as * further sort criterion provides a unique sorting order and thus we can * merge inode and vfsmount lists of marks in linear time and find groups * present in both lists. * * A return value of 1 signifies that b has priority over a. * A return value of 0 signifies that the two marks have to be handled together. * A return value of -1 signifies that a has priority over b. */ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) { if (a == b) return 0; if (!a) return 1; if (!b) return -1; if (a->priority < b->priority) return 1; if (a->priority > b->priority) return -1; if (a < b) return 1; return -1; } static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, unsigned int obj_type, __kernel_fsid_t *fsid) { struct fsnotify_mark_connector *conn; conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL); if (!conn) return -ENOMEM; spin_lock_init(&conn->lock); INIT_HLIST_HEAD(&conn->list); conn->flags = 0; conn->type = obj_type; conn->obj = connp; /* Cache fsid of filesystem containing the object */ if (fsid) { conn->fsid = *fsid; conn->flags = FSNOTIFY_CONN_FLAG_HAS_FSID; } else { conn->fsid.val[0] = conn->fsid.val[1] = 0; conn->flags = 0; } fsnotify_get_sb_connectors(conn); /* * cmpxchg() provides the barrier so that readers of *connp can see * only initialized structure */ if (cmpxchg(connp, NULL, conn)) { /* Someone else created list structure for us */ fsnotify_put_sb_connectors(conn); kmem_cache_free(fsnotify_mark_connector_cachep, conn); } return 0; } /* * Get mark connector, make sure it is alive and return with its lock held. * This is for users that get connector pointer from inode or mount. Users that * hold reference to a mark on the list may directly lock connector->lock as * they are sure list cannot go away under them. */ static struct fsnotify_mark_connector *fsnotify_grab_connector( fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; int idx; idx = srcu_read_lock(&fsnotify_mark_srcu); conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (!conn) goto out; spin_lock(&conn->lock); if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) { spin_unlock(&conn->lock); srcu_read_unlock(&fsnotify_mark_srcu, idx); return NULL; } out: srcu_read_unlock(&fsnotify_mark_srcu, idx); return conn; } /* * Add mark into proper place in given list of marks. These marks may be used * for the fsnotify backend to determine which event types should be delivered * to which group and for which inodes. These marks are ordered according to * priority, highest number first, and then by the group's location in memory. */ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid) { struct fsnotify_mark *lmark, *last = NULL; struct fsnotify_mark_connector *conn; int cmp; int err = 0; if (WARN_ON(!fsnotify_valid_obj_type(obj_type))) return -EINVAL; /* Backend is expected to check for zero fsid (e.g. tmpfs) */ if (fsid && WARN_ON_ONCE(!fsid->val[0] && !fsid->val[1])) return -ENODEV; restart: spin_lock(&mark->lock); conn = fsnotify_grab_connector(connp); if (!conn) { spin_unlock(&mark->lock); err = fsnotify_attach_connector_to_object(connp, obj_type, fsid); if (err) return err; goto restart; } else if (fsid && !(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID)) { conn->fsid = *fsid; /* Pairs with smp_rmb() in fanotify_get_fsid() */ smp_wmb(); conn->flags |= FSNOTIFY_CONN_FLAG_HAS_FSID; } else if (fsid && (conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID) && (fsid->val[0] != conn->fsid.val[0] || fsid->val[1] != conn->fsid.val[1])) { /* * Backend is expected to check for non uniform fsid * (e.g. btrfs), but maybe we missed something? * Only allow setting conn->fsid once to non zero fsid. * inotify and non-fid fanotify groups do not set nor test * conn->fsid. */ pr_warn_ratelimited("%s: fsid mismatch on object of type %u: " "%x.%x != %x.%x\n", __func__, conn->type, fsid->val[0], fsid->val[1], conn->fsid.val[0], conn->fsid.val[1]); err = -EXDEV; goto out_err; } /* is mark the first mark? */ if (hlist_empty(&conn->list)) { hlist_add_head_rcu(&mark->obj_list, &conn->list); goto added; } /* should mark be in the middle of the current list? */ hlist_for_each_entry(lmark, &conn->list, obj_list) { last = lmark; if ((lmark->group == mark->group) && (lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) && !(mark->group->flags & FSNOTIFY_GROUP_DUPS)) { err = -EEXIST; goto out_err; } cmp = fsnotify_compare_groups(lmark->group, mark->group); if (cmp >= 0) { hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list); goto added; } } BUG_ON(last == NULL); /* mark should be the last entry. last is the current last entry */ hlist_add_behind_rcu(&mark->obj_list, &last->obj_list); added: /* * Since connector is attached to object using cmpxchg() we are * guaranteed that connector initialization is fully visible by anyone * seeing mark->connector set. */ WRITE_ONCE(mark->connector, conn); out_err: spin_unlock(&conn->lock); spin_unlock(&mark->lock); return err; } /* * Attach an initialized mark to a given group and fs object. * These marks may be used for the fsnotify backend to determine which * event types should be delivered to which group. */ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid) { struct fsnotify_group *group = mark->group; int ret = 0; fsnotify_group_assert_locked(group); /* * LOCKING ORDER!!!! * group->mark_mutex * mark->lock * mark->connector->lock */ spin_lock(&mark->lock); mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED; list_add(&mark->g_list, &group->marks_list); fsnotify_get_mark(mark); /* for g_list */ spin_unlock(&mark->lock); ret = fsnotify_add_mark_list(mark, connp, obj_type, add_flags, fsid); if (ret) goto err; fsnotify_recalc_mask(mark->connector); return ret; err: spin_lock(&mark->lock); mark->flags &= ~(FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED); list_del_init(&mark->g_list); spin_unlock(&mark->lock); fsnotify_put_mark(mark); return ret; } int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid) { int ret; struct fsnotify_group *group = mark->group; fsnotify_group_lock(group); ret = fsnotify_add_mark_locked(mark, connp, obj_type, add_flags, fsid); fsnotify_group_unlock(group); return ret; } EXPORT_SYMBOL_GPL(fsnotify_add_mark); /* * Given a list of marks, find the mark associated with given group. If found * take a reference to that mark and return it, else return NULL. */ struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, struct fsnotify_group *group) { struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark; conn = fsnotify_grab_connector(connp); if (!conn) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (mark->group == group && (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { fsnotify_get_mark(mark); spin_unlock(&conn->lock); return mark; } } spin_unlock(&conn->lock); return NULL; } EXPORT_SYMBOL_GPL(fsnotify_find_mark); /* Clear any marks in a group with given type mask */ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type) { struct fsnotify_mark *lmark, *mark; LIST_HEAD(to_free); struct list_head *head = &to_free; /* Skip selection step if we want to clear all marks. */ if (obj_type == FSNOTIFY_OBJ_TYPE_ANY) { head = &group->marks_list; goto clear; } /* * We have to be really careful here. Anytime we drop mark_mutex, e.g. * fsnotify_clear_marks_by_inode() can come and free marks. Even in our * to_free list so we have to use mark_mutex even when accessing that * list. And freeing mark requires us to drop mark_mutex. So we can * reliably free only the first mark in the list. That's why we first * move marks to free to to_free list in one go and then free marks in * to_free list one by one. */ fsnotify_group_lock(group); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { if (mark->connector->type == obj_type) list_move(&mark->g_list, &to_free); } fsnotify_group_unlock(group); clear: while (1) { fsnotify_group_lock(group); if (list_empty(head)) { fsnotify_group_unlock(group); break; } mark = list_first_entry(head, struct fsnotify_mark, g_list); fsnotify_get_mark(mark); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); fsnotify_put_mark(mark); } } /* Destroy all marks attached to an object via connector */ void fsnotify_destroy_marks(fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark, *old_mark = NULL; void *objp; unsigned int type; conn = fsnotify_grab_connector(connp); if (!conn) return; /* * We have to be careful since we can race with e.g. * fsnotify_clear_marks_by_group() and once we drop the conn->lock, the * list can get modified. However we are holding mark reference and * thus our mark cannot be removed from obj_list so we can continue * iteration after regaining conn->lock. */ hlist_for_each_entry(mark, &conn->list, obj_list) { fsnotify_get_mark(mark); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); old_mark = mark; fsnotify_destroy_mark(mark, mark->group); spin_lock(&conn->lock); } /* * Detach list from object now so that we don't pin inode until all * mark references get dropped. It would lead to strange results such * as delaying inode deletion or blocking unmount. */ objp = fsnotify_detach_connector_from_object(conn, &type); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); fsnotify_drop_object(type, objp); } /* * Nothing fancy, just initialize lists and locks and counters. */ void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { memset(mark, 0, sizeof(*mark)); spin_lock_init(&mark->lock); refcount_set(&mark->refcnt, 1); fsnotify_get_group(group); mark->group = group; WRITE_ONCE(mark->connector, NULL); } EXPORT_SYMBOL_GPL(fsnotify_init_mark); /* * Destroy all marks in destroy_list, waits for SRCU period to finish before * actually freeing marks. */ static void fsnotify_mark_destroy_workfn(struct work_struct *work) { struct fsnotify_mark *mark, *next; struct list_head private_destroy_list; spin_lock(&destroy_lock); /* exchange the list head */ list_replace_init(&destroy_list, &private_destroy_list); spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { list_del_init(&mark->g_list); fsnotify_final_mark_destroy(mark); } } /* Wait for all marks queued for destruction to be actually destroyed */ void fsnotify_wait_marks_destroyed(void) { flush_delayed_work(&reaper_work); } EXPORT_SYMBOL_GPL(fsnotify_wait_marks_destroyed); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/namespace.c * * (C) Copyright Al Viro 2000, 2001 * * Based on code from fs/super.c, copyright Linus Torvalds and others. * Heavily rewritten. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/capability.h> #include <linux/mnt_namespace.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/idr.h> #include <linux/init.h> /* init_rootfs */ #include <linux/fs_struct.h> /* get_fs_root et.al. */ #include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */ #include <linux/file.h> #include <linux/uaccess.h> #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/memblock.h> #include <linux/task_work.h> #include <linux/sched/task.h> #include <uapi/linux/mount.h> #include <linux/fs_context.h> #include <linux/shmem_fs.h> #include "pnode.h" #include "internal.h" /* Maximum number of mounts in a mount namespace */ unsigned int sysctl_mount_max __read_mostly = 100000; static unsigned int m_hash_mask __read_mostly; static unsigned int m_hash_shift __read_mostly; static unsigned int mp_hash_mask __read_mostly; static unsigned int mp_hash_shift __read_mostly; static __initdata unsigned long mhash_entries; static int __init set_mhash_entries(char *str) { if (!str) return 0; mhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mhash_entries=", set_mhash_entries); static __initdata unsigned long mphash_entries; static int __init set_mphash_entries(char *str) { if (!str) return 0; mphash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("mphash_entries=", set_mphash_entries); static u64 event; static DEFINE_IDA(mnt_id_ida); static DEFINE_IDA(mnt_group_ida); static struct hlist_head *mount_hashtable __read_mostly; static struct hlist_head *mountpoint_hashtable __read_mostly; static struct kmem_cache *mnt_cache __read_mostly; static DECLARE_RWSEM(namespace_sem); static HLIST_HEAD(unmounted); /* protected by namespace_sem */ static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ /* /sys/fs */ struct kobject *fs_kobj; EXPORT_SYMBOL_GPL(fs_kobj); /* * vfsmount lock may be taken for read to prevent changes to the * vfsmount hash, ie. during mountpoint lookups or walking back * up the tree. * * It should be taken for write in all cases where the vfsmount * tree or hash is modified or when a vfsmount structure is modified. */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry) { unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES); tmp += ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> m_hash_shift); return &mount_hashtable[tmp & m_hash_mask]; } static inline struct hlist_head *mp_hash(struct dentry *dentry) { unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES); tmp = tmp + (tmp >> mp_hash_shift); return &mountpoint_hashtable[tmp & mp_hash_mask]; } static int mnt_alloc_id(struct mount *mnt) { int res = ida_alloc(&mnt_id_ida, GFP_KERNEL); if (res < 0) return res; mnt->mnt_id = res; return 0; } static void mnt_free_id(struct mount *mnt) { ida_free(&mnt_id_ida, mnt->mnt_id); } /* * Allocate a new peer group ID */ static int mnt_alloc_group_id(struct mount *mnt) { int res = ida_alloc_min(&mnt_group_ida, 1, GFP_KERNEL); if (res < 0) return res; mnt->mnt_group_id = res; return 0; } /* * Release a peer group ID */ void mnt_release_group_id(struct mount *mnt) { ida_free(&mnt_group_ida, mnt->mnt_group_id); mnt->mnt_group_id = 0; } /* * vfsmount lock must be held for read */ static inline void mnt_add_count(struct mount *mnt, int n) { #ifdef CONFIG_SMP this_cpu_add(mnt->mnt_pcp->mnt_count, n); #else preempt_disable(); mnt->mnt_count += n; preempt_enable(); #endif } /* * vfsmount lock must be held for write */ int mnt_get_count(struct mount *mnt) { #ifdef CONFIG_SMP int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count; } return count; #else return mnt->mnt_count; #endif } static struct mount *alloc_vfsmnt(const char *name) { struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); if (mnt) { int err; err = mnt_alloc_id(mnt); if (err) goto out_free_cache; if (name) { mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL); if (!mnt->mnt_devname) goto out_free_id; } #ifdef CONFIG_SMP mnt->mnt_pcp = alloc_percpu(struct mnt_pcp); if (!mnt->mnt_pcp) goto out_free_devname; this_cpu_add(mnt->mnt_pcp->mnt_count, 1); #else mnt->mnt_count = 1; mnt->mnt_writers = 0; #endif INIT_HLIST_NODE(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); INIT_LIST_HEAD(&mnt->mnt_mounts); INIT_LIST_HEAD(&mnt->mnt_list); INIT_LIST_HEAD(&mnt->mnt_expire); INIT_LIST_HEAD(&mnt->mnt_share); INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); } return mnt; #ifdef CONFIG_SMP out_free_devname: kfree_const(mnt->mnt_devname); #endif out_free_id: mnt_free_id(mnt); out_free_cache: kmem_cache_free(mnt_cache, mnt); return NULL; } /* * Most r/o checks on a fs are for operations that take * discrete amounts of time, like a write() or unlink(). * We must keep track of when those operations start * (for permission checks) and when they end, so that * we can determine when writes are able to occur to * a filesystem. */ /* * __mnt_is_readonly: check whether a mount is read-only * @mnt: the mount to check for its write status * * This shouldn't be used directly ouside of the VFS. * It does not guarantee that the filesystem will stay * r/w, just that it is right *now*. This can not and * should not be used in place of IS_RDONLY(inode). * mnt_want/drop_write() will _keep_ the filesystem * r/w. */ bool __mnt_is_readonly(struct vfsmount *mnt) { return (mnt->mnt_flags & MNT_READONLY) || sb_rdonly(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(__mnt_is_readonly); static inline void mnt_inc_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_inc(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers++; #endif } static inline void mnt_dec_writers(struct mount *mnt) { #ifdef CONFIG_SMP this_cpu_dec(mnt->mnt_pcp->mnt_writers); #else mnt->mnt_writers--; #endif } static unsigned int mnt_get_writers(struct mount *mnt) { #ifdef CONFIG_SMP unsigned int count = 0; int cpu; for_each_possible_cpu(cpu) { count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers; } return count; #else return mnt->mnt_writers; #endif } static int mnt_is_readonly(struct vfsmount *mnt) { if (mnt->mnt_sb->s_readonly_remount) return 1; /* Order wrt setting s_flags/s_readonly_remount in do_remount() */ smp_rmb(); return __mnt_is_readonly(mnt); } /* * Most r/o & frozen checks on a fs are for operations that take discrete * amounts of time, like a write() or unlink(). We must keep track of when * those operations start (for permission checks) and when they end, so that we * can determine when writes are able to occur to a filesystem. */ /** * __mnt_want_write - get write access to a mount without freeze protection * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mnt it read-write) before * returning success. This operation does not protect against filesystem being * frozen. When the write operation is finished, __mnt_drop_write() must be * called. This is effectively a refcount. */ int __mnt_want_write(struct vfsmount *m) { struct mount *mnt = real_mount(m); int ret = 0; preempt_disable(); mnt_inc_writers(mnt); /* * The store to mnt_inc_writers must be visible before we pass * MNT_WRITE_HOLD loop below, so that the slowpath can see our * incremented count after it has set MNT_WRITE_HOLD. */ smp_mb(); while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) cpu_relax(); /* * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will * be set to match its requirements. So we must not load that until * MNT_WRITE_HOLD is cleared. */ smp_rmb(); if (mnt_is_readonly(m)) { mnt_dec_writers(mnt); ret = -EROFS; } preempt_enable(); return ret; } /** * mnt_want_write - get write access to a mount * @m: the mount on which to take a write * * This tells the low-level filesystem that a write is about to be performed to * it, and makes sure that writes are allowed (mount is read-write, filesystem * is not frozen) before returning success. When the write operation is * finished, mnt_drop_write() must be called. This is effectively a refcount. */ int mnt_want_write(struct vfsmount *m) { int ret; sb_start_write(m->mnt_sb); ret = __mnt_want_write(m); if (ret) sb_end_write(m->mnt_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write); /** * mnt_clone_write - get write access to a mount * @mnt: the mount on which to take a write * * This is effectively like mnt_want_write, except * it must only be used to take an extra write reference * on a mountpoint that we already know has a write reference * on it. This allows some optimisation. * * After finished, mnt_drop_write must be called as usual to * drop the reference. */ int mnt_clone_write(struct vfsmount *mnt) { /* superblock may be r/o */ if (__mnt_is_readonly(mnt)) return -EROFS; preempt_disable(); mnt_inc_writers(real_mount(mnt)); preempt_enable(); return 0; } EXPORT_SYMBOL_GPL(mnt_clone_write); /** * __mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like __mnt_want_write, but it takes a file and can * do some optimisations if the file is open for write already */ int __mnt_want_write_file(struct file *file) { if (!(file->f_mode & FMODE_WRITER)) return __mnt_want_write(file->f_path.mnt); else return mnt_clone_write(file->f_path.mnt); } /** * mnt_want_write_file - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_want_write, but it takes a file and can * do some optimisations if the file is open for write already */ int mnt_want_write_file(struct file *file) { int ret; sb_start_write(file_inode(file)->i_sb); ret = __mnt_want_write_file(file); if (ret) sb_end_write(file_inode(file)->i_sb); return ret; } EXPORT_SYMBOL_GPL(mnt_want_write_file); /** * __mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done * performing writes to it. Must be matched with * __mnt_want_write() call above. */ void __mnt_drop_write(struct vfsmount *mnt) { preempt_disable(); mnt_dec_writers(real_mount(mnt)); preempt_enable(); } /** * mnt_drop_write - give up write access to a mount * @mnt: the mount on which to give up write access * * Tells the low-level filesystem that we are done performing writes to it and * also allows filesystem to be frozen again. Must be matched with * mnt_want_write() call above. */ void mnt_drop_write(struct vfsmount *mnt) { __mnt_drop_write(mnt); sb_end_write(mnt->mnt_sb); } EXPORT_SYMBOL_GPL(mnt_drop_write); void __mnt_drop_write_file(struct file *file) { __mnt_drop_write(file->f_path.mnt); } void mnt_drop_write_file(struct file *file) { __mnt_drop_write_file(file); sb_end_write(file_inode(file)->i_sb); } EXPORT_SYMBOL(mnt_drop_write_file); static int mnt_make_readonly(struct mount *mnt) { int ret = 0; lock_mount_hash(); mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; /* * After storing MNT_WRITE_HOLD, we'll read the counters. This store * should be visible before we do. */ smp_mb(); /* * With writers on hold, if this value is zero, then there are * definitely no active writers (although held writers may subsequently * increment the count, they'll have to wait, and decrement it after * seeing MNT_READONLY). * * It is OK to have counter incremented on one CPU and decremented on * another: the sum will add up correctly. The danger would be when we * sum up each counter, if we read a counter before it is incremented, * but then read another CPU's count which it has been subsequently * decremented from -- we would see more decrements than we should. * MNT_WRITE_HOLD protects against this scenario, because * mnt_want_write first increments count, then smp_mb, then spins on * MNT_WRITE_HOLD, so it can't be decremented by another CPU while * we're counting up here. */ if (mnt_get_writers(mnt) > 0) ret = -EBUSY; else mnt->mnt.mnt_flags |= MNT_READONLY; /* * MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers * that become unheld will see MNT_READONLY. */ smp_wmb(); mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; unlock_mount_hash(); return ret; } static int __mnt_unmake_readonly(struct mount *mnt) { lock_mount_hash(); mnt->mnt.mnt_flags &= ~MNT_READONLY; unlock_mount_hash(); return 0; } int sb_prepare_remount_readonly(struct super_block *sb) { struct mount *mnt; int err = 0; /* Racy optimization. Recheck the counter under MNT_WRITE_HOLD */ if (atomic_long_read(&sb->s_remove_count)) return -EBUSY; lock_mount_hash(); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (!(mnt->mnt.mnt_flags & MNT_READONLY)) { mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; smp_mb(); if (mnt_get_writers(mnt) > 0) { err = -EBUSY; break; } } } if (!err && atomic_long_read(&sb->s_remove_count)) err = -EBUSY; if (!err) { sb->s_readonly_remount = 1; smp_wmb(); } list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } unlock_mount_hash(); return err; } static void free_vfsmnt(struct mount *mnt) { kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); #endif kmem_cache_free(mnt_cache, mnt); } static void delayed_free_vfsmnt(struct rcu_head *head) { free_vfsmnt(container_of(head, struct mount, mnt_rcu)); } /* call under rcu_read_lock */ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) { struct mount *mnt; if (read_seqretry(&mount_lock, seq)) return 1; if (bastard == NULL) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); smp_mb(); // see mntput_no_expire() and do_umount() if (likely(!read_seqretry(&mount_lock, seq))) return 0; lock_mount_hash(); if (unlikely(bastard->mnt_flags & (MNT_SYNC_UMOUNT | MNT_DOOMED))) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; } unlock_mount_hash(); /* caller will mntput() */ return -1; } /* call under rcu_read_lock */ bool legitimize_mnt(struct vfsmount *bastard, unsigned seq) { int res = __legitimize_mnt(bastard, seq); if (likely(!res)) return true; if (unlikely(res < 0)) { rcu_read_unlock(); mntput(bastard); rcu_read_lock(); } return false; } /* * find the first mount at @dentry on vfsmount @mnt. * call under rcu_read_lock() */ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry) { struct hlist_head *head = m_hash(mnt, dentry); struct mount *p; hlist_for_each_entry_rcu(p, head, mnt_hash) if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry) return p; return NULL; } /* * lookup_mnt - Return the first child mount mounted at path * * "First" means first mounted chronologically. If you create the * following mounts: * * mount /dev/sda1 /mnt * mount /dev/sda2 /mnt * mount /dev/sda3 /mnt * * Then lookup_mnt() on the base /mnt dentry in the root mount will * return successively the root dentry and vfsmount of /dev/sda1, then * /dev/sda2, then /dev/sda3, then NULL. * * lookup_mnt takes a reference to the found vfsmount. */ struct vfsmount *lookup_mnt(const struct path *path) { struct mount *child_mnt; struct vfsmount *m; unsigned seq; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); child_mnt = __lookup_mnt(path->mnt, path->dentry); m = child_mnt ? &child_mnt->mnt : NULL; } while (!legitimize_mnt(m, seq)); rcu_read_unlock(); return m; } static inline void lock_ns_list(struct mnt_namespace *ns) { spin_lock(&ns->ns_lock); } static inline void unlock_ns_list(struct mnt_namespace *ns) { spin_unlock(&ns->ns_lock); } static inline bool mnt_is_cursor(struct mount *mnt) { return mnt->mnt.mnt_flags & MNT_CURSOR; } /* * __is_local_mountpoint - Test to see if dentry is a mountpoint in the * current mount namespace. * * The common case is dentries are not mountpoints at all and that * test is handled inline. For the slow case when we are actually * dealing with a mountpoint of some kind, walk through all of the * mounts in the current mount namespace and test to see if the dentry * is a mountpoint. * * The mount_hashtable is not usable in the context because we * need to identify all mounts that may be in the current mount * namespace not just a mount that happens to have some specified * parent mount. */ bool __is_local_mountpoint(struct dentry *dentry) { struct mnt_namespace *ns = current->nsproxy->mnt_ns; struct mount *mnt; bool is_covered = false; down_read(&namespace_sem); lock_ns_list(ns); list_for_each_entry(mnt, &ns->list, mnt_list) { if (mnt_is_cursor(mnt)) continue; is_covered = (mnt->mnt_mountpoint == dentry); if (is_covered) break; } unlock_ns_list(ns); up_read(&namespace_sem); return is_covered; } static struct mountpoint *lookup_mountpoint(struct dentry *dentry) { struct hlist_head *chain = mp_hash(dentry); struct mountpoint *mp; hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { mp->m_count++; return mp; } } return NULL; } static struct mountpoint *get_mountpoint(struct dentry *dentry) { struct mountpoint *mp, *new = NULL; int ret; if (d_mountpoint(dentry)) { /* might be worth a WARN_ON() */ if (d_unlinked(dentry)) return ERR_PTR(-ENOENT); mountpoint: read_seqlock_excl(&mount_lock); mp = lookup_mountpoint(dentry); read_sequnlock_excl(&mount_lock); if (mp) goto done; } if (!new) new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* Exactly one processes may set d_mounted */ ret = d_set_mounted(dentry); /* Someone else set d_mounted? */ if (ret == -EBUSY) goto mountpoint; /* The dentry is not available as a mountpoint? */ mp = ERR_PTR(ret); if (ret) goto done; /* Add the new mountpoint to the hash table */ read_seqlock_excl(&mount_lock); new->m_dentry = dget(dentry); new->m_count = 1; hlist_add_head(&new->m_hash, mp_hash(dentry)); INIT_HLIST_HEAD(&new->m_list); read_sequnlock_excl(&mount_lock); mp = new; new = NULL; done: kfree(new); return mp; } /* * vfsmount lock must be held. Additionally, the caller is responsible * for serializing calls for given disposal list. */ static void __put_mountpoint(struct mountpoint *mp, struct list_head *list) { if (!--mp->m_count) { struct dentry *dentry = mp->m_dentry; BUG_ON(!hlist_empty(&mp->m_list)); spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); dput_to_list(dentry, list); hlist_del(&mp->m_hash); kfree(mp); } } /* called with namespace_lock and vfsmount lock */ static void put_mountpoint(struct mountpoint *mp) { __put_mountpoint(mp, &ex_mountpoints); } static inline int check_mnt(struct mount *mnt) { return mnt->mnt_ns == current->nsproxy->mnt_ns; } /* * vfsmount lock must be held for write */ static void touch_mnt_namespace(struct mnt_namespace *ns) { if (ns) { ns->event = ++event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static void __touch_mnt_namespace(struct mnt_namespace *ns) { if (ns && ns->event != event) { ns->event = event; wake_up_interruptible(&ns->poll); } } /* * vfsmount lock must be held for write */ static struct mountpoint *unhash_mnt(struct mount *mnt) { struct mountpoint *mp; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); hlist_del_init_rcu(&mnt->mnt_hash); hlist_del_init(&mnt->mnt_mp_list); mp = mnt->mnt_mp; mnt->mnt_mp = NULL; return mp; } /* * vfsmount lock must be held for write */ static void umount_mnt(struct mount *mnt) { put_mountpoint(unhash_mnt(mnt)); } /* * vfsmount lock must be held for write */ void mnt_set_mountpoint(struct mount *mnt, struct mountpoint *mp, struct mount *child_mnt) { mp->m_count++; mnt_add_count(mnt, 1); /* essentially, that's mntget */ child_mnt->mnt_mountpoint = mp->m_dentry; child_mnt->mnt_parent = mnt; child_mnt->mnt_mp = mp; hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); } static void __attach_mnt(struct mount *mnt, struct mount *parent) { hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mnt->mnt_mountpoint)); list_add_tail(&mnt->mnt_child, &parent->mnt_mounts); } /* * vfsmount lock must be held for write */ static void attach_mnt(struct mount *mnt, struct mount *parent, struct mountpoint *mp) { mnt_set_mountpoint(parent, mp, mnt); __attach_mnt(mnt, parent); } void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { struct mountpoint *old_mp = mnt->mnt_mp; struct mount *old_parent = mnt->mnt_parent; list_del_init(&mnt->mnt_child); hlist_del_init(&mnt->mnt_mp_list); hlist_del_init_rcu(&mnt->mnt_hash); attach_mnt(mnt, parent, mp); put_mountpoint(old_mp); mnt_add_count(old_parent, -1); } /* * vfsmount lock must be held for write */ static void commit_tree(struct mount *mnt) { struct mount *parent = mnt->mnt_parent; struct mount *m; LIST_HEAD(head); struct mnt_namespace *n = parent->mnt_ns; BUG_ON(parent == mnt); list_add_tail(&head, &mnt->mnt_list); list_for_each_entry(m, &head, mnt_list) m->mnt_ns = n; list_splice(&head, n->list.prev); n->mounts += n->pending_mounts; n->pending_mounts = 0; __attach_mnt(mnt, parent); touch_mnt_namespace(n); } static struct mount *next_mnt(struct mount *p, struct mount *root) { struct list_head *next = p->mnt_mounts.next; if (next == &p->mnt_mounts) { while (1) { if (p == root) return NULL; next = p->mnt_child.next; if (next != &p->mnt_parent->mnt_mounts) break; p = p->mnt_parent; } } return list_entry(next, struct mount, mnt_child); } static struct mount *skip_mnt_tree(struct mount *p) { struct list_head *prev = p->mnt_mounts.prev; while (prev != &p->mnt_mounts) { p = list_entry(prev, struct mount, mnt_child); prev = p->mnt_mounts.prev; } return p; } /** * vfs_create_mount - Create a mount for a configured superblock * @fc: The configuration context with the superblock attached * * Create a mount to an already configured superblock. If necessary, the * caller should invoke vfs_get_tree() before calling this. * * Note that this does not attach the mount to anything. */ struct vfsmount *vfs_create_mount(struct fs_context *fc) { struct mount *mnt; if (!fc->root) return ERR_PTR(-EINVAL); mnt = alloc_vfsmnt(fc->source ?: "none"); if (!mnt) return ERR_PTR(-ENOMEM); if (fc->sb_flags & SB_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; atomic_inc(&fc->root->d_sb->s_active); mnt->mnt.mnt_sb = fc->root->d_sb; mnt->mnt.mnt_root = dget(fc->root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); unlock_mount_hash(); return &mnt->mnt; } EXPORT_SYMBOL(vfs_create_mount); struct vfsmount *fc_mount(struct fs_context *fc) { int err = vfs_get_tree(fc); if (!err) { up_write(&fc->root->d_sb->s_umount); return vfs_create_mount(fc); } return ERR_PTR(err); } EXPORT_SYMBOL(fc_mount); struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { struct fs_context *fc; struct vfsmount *mnt; int ret = 0; if (!type) return ERR_PTR(-EINVAL); fc = fs_context_for_mount(type, flags); if (IS_ERR(fc)) return ERR_CAST(fc); if (name) ret = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!ret) ret = parse_monolithic_mount_data(fc, data); if (!ret) mnt = fc_mount(fc); else mnt = ERR_PTR(ret); put_fs_context(fc); return mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); struct vfsmount * vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, const char *name, void *data) { /* Until it is worked out how to pass the user namespace * through from the parent mount to the submount don't support * unprivileged mounts with submounts. */ if (mountpoint->d_sb->s_user_ns != &init_user_ns) return ERR_PTR(-EPERM); return vfs_kern_mount(type, SB_SUBMOUNT, name, data); } EXPORT_SYMBOL_GPL(vfs_submount); static struct mount *clone_mnt(struct mount *old, struct dentry *root, int flag) { struct super_block *sb = old->mnt.mnt_sb; struct mount *mnt; int err; mnt = alloc_vfsmnt(old->mnt_devname); if (!mnt) return ERR_PTR(-ENOMEM); if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE)) mnt->mnt_group_id = 0; /* not a peer of original */ else mnt->mnt_group_id = old->mnt_group_id; if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) { err = mnt_alloc_group_id(mnt); if (err) goto out_free; } mnt->mnt.mnt_flags = old->mnt.mnt_flags; mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &sb->s_mounts); unlock_mount_hash(); if ((flag & CL_SLAVE) || ((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) { list_add(&mnt->mnt_slave, &old->mnt_slave_list); mnt->mnt_master = old; CLEAR_MNT_SHARED(mnt); } else if (!(flag & CL_PRIVATE)) { if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old)) list_add(&mnt->mnt_share, &old->mnt_share); if (IS_MNT_SLAVE(old)) list_add(&mnt->mnt_slave, &old->mnt_slave); mnt->mnt_master = old->mnt_master; } else { CLEAR_MNT_SHARED(mnt); } if (flag & CL_MAKE_SHARED) set_mnt_shared(mnt); /* stick the duplicate mount on the same expiry list * as the original if that was on one */ if (flag & CL_EXPIRE) { if (!list_empty(&old->mnt_expire)) list_add(&mnt->mnt_expire, &old->mnt_expire); } return mnt; out_free: mnt_free_id(mnt); free_vfsmnt(mnt); return ERR_PTR(err); } static void cleanup_mnt(struct mount *mnt) { struct hlist_node *p; struct mount *m; /* * The warning here probably indicates that somebody messed * up a mnt_want/drop_write() pair. If this happens, the * filesystem was probably unable to make r/w->r/o transitions. * The locking used to deal with mnt_count decrement provides barriers, * so mnt_get_writers() below is safe. */ WARN_ON(mnt_get_writers(mnt)); if (unlikely(mnt->mnt_pins.first)) mnt_pin_kill(mnt); hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } fsnotify_vfsmount_delete(&mnt->mnt); dput(mnt->mnt.mnt_root); deactivate_super(mnt->mnt.mnt_sb); mnt_free_id(mnt); call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt); } static void __cleanup_mnt(struct rcu_head *head) { cleanup_mnt(container_of(head, struct mount, mnt_rcu)); } static LLIST_HEAD(delayed_mntput_list); static void delayed_mntput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_mntput_list); struct mount *m, *t; llist_for_each_entry_safe(m, t, node, mnt_llist) cleanup_mnt(m); } static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { LIST_HEAD(list); int count; rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { /* * Since we don't do lock_mount_hash() here, * ->mnt_ns can change under us. However, if it's * non-NULL, then there's a reference that won't * be dropped until after an RCU delay done after * turning ->mnt_ns NULL. So if we observe it * non-NULL under rcu_read_lock(), the reference * we are dropping is not the final one. */ mnt_add_count(mnt, -1); rcu_read_unlock(); return; } lock_mount_hash(); /* * make sure that if __legitimize_mnt() has not seen us grab * mount_lock, we'll see their refcount increment here. */ smp_mb(); mnt_add_count(mnt, -1); count = mnt_get_count(mnt); if (count != 0) { WARN_ON(count < 0); rcu_read_unlock(); unlock_mount_hash(); return; } if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) { rcu_read_unlock(); unlock_mount_hash(); return; } mnt->mnt.mnt_flags |= MNT_DOOMED; rcu_read_unlock(); list_del(&mnt->mnt_instance); if (unlikely(!list_empty(&mnt->mnt_mounts))) { struct mount *p, *tmp; list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { __put_mountpoint(unhash_mnt(p), &list); hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children); } } unlock_mount_hash(); shrink_dentry_list(&list); if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) { struct task_struct *task = current; if (likely(!(task->flags & PF_KTHREAD))) { init_task_work(&mnt->mnt_rcu, __cleanup_mnt); if (!task_work_add(task, &mnt->mnt_rcu, TWA_RESUME)) return; } if (llist_add(&mnt->mnt_llist, &delayed_mntput_list)) schedule_delayed_work(&delayed_mntput_work, 1); return; } cleanup_mnt(mnt); } void mntput(struct vfsmount *mnt) { if (mnt) { struct mount *m = real_mount(mnt); /* avoid cacheline pingpong, hope gcc doesn't get "smart" */ if (unlikely(m->mnt_expiry_mark)) m->mnt_expiry_mark = 0; mntput_no_expire(m); } } EXPORT_SYMBOL(mntput); struct vfsmount *mntget(struct vfsmount *mnt) { if (mnt) mnt_add_count(real_mount(mnt), 1); return mnt; } EXPORT_SYMBOL(mntget); /* path_is_mountpoint() - Check if path is a mount in the current * namespace. * * d_mountpoint() can only be used reliably to establish if a dentry is * not mounted in any namespace and that common case is handled inline. * d_mountpoint() isn't aware of the possibility there may be multiple * mounts using a given dentry in a different namespace. This function * checks if the passed in path is a mountpoint rather than the dentry * alone. */ bool path_is_mountpoint(const struct path *path) { unsigned seq; bool res; if (!d_mountpoint(path->dentry)) return false; rcu_read_lock(); do { seq = read_seqbegin(&mount_lock); res = __path_is_mountpoint(path); } while (read_seqretry(&mount_lock, seq)); rcu_read_unlock(); return res; } EXPORT_SYMBOL(path_is_mountpoint); struct vfsmount *mnt_clone_internal(const struct path *path) { struct mount *p; p = clone_mnt(real_mount(path->mnt), path->dentry, CL_PRIVATE); if (IS_ERR(p)) return ERR_CAST(p); p->mnt.mnt_flags |= MNT_INTERNAL; return &p->mnt; } #ifdef CONFIG_PROC_FS static struct mount *mnt_list_next(struct mnt_namespace *ns, struct list_head *p) { struct mount *mnt, *ret = NULL; lock_ns_list(ns); list_for_each_continue(p, &ns->list) { mnt = list_entry(p, typeof(*mnt), mnt_list); if (!mnt_is_cursor(mnt)) { ret = mnt; break; } } unlock_ns_list(ns); return ret; } /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) { struct proc_mounts *p = m->private; struct list_head *prev; down_read(&namespace_sem); if (!*pos) { prev = &p->ns->list; } else { prev = &p->cursor.mnt_list; /* Read after we'd reached the end? */ if (list_empty(prev)) return NULL; } return mnt_list_next(p->ns, prev); } static void *m_next(struct seq_file *m, void *v, loff_t *pos) { struct proc_mounts *p = m->private; struct mount *mnt = v; ++*pos; return mnt_list_next(p->ns, &mnt->mnt_list); } static void m_stop(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *mnt = v; lock_ns_list(p->ns); if (mnt) list_move_tail(&p->cursor.mnt_list, &mnt->mnt_list); else list_del_init(&p->cursor.mnt_list); unlock_ns_list(p->ns); up_read(&namespace_sem); } static int m_show(struct seq_file *m, void *v) { struct proc_mounts *p = m->private; struct mount *r = v; return p->show(m, &r->mnt); } const struct seq_operations mounts_op = { .start = m_start, .next = m_next, .stop = m_stop, .show = m_show, }; void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor) { down_read(&namespace_sem); lock_ns_list(ns); list_del(&cursor->mnt_list); unlock_ns_list(ns); up_read(&namespace_sem); } #endif /* CONFIG_PROC_FS */ /** * may_umount_tree - check if a mount tree is busy * @mnt: root of mount tree * * This is called to check if a tree of mounts has any * open files, pwds, chroots or sub mounts that are * busy. */ int may_umount_tree(struct vfsmount *m) { struct mount *mnt = real_mount(m); int actual_refs = 0; int minimum_refs = 0; struct mount *p; BUG_ON(!m); /* write lock needed for mnt_get_count */ lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { actual_refs += mnt_get_count(p); minimum_refs += 2; } unlock_mount_hash(); if (actual_refs > minimum_refs) return 0; return 1; } EXPORT_SYMBOL(may_umount_tree); /** * may_umount - check if a mount point is busy * @mnt: root of mount * * This is called to check if a mount point has any * open files, pwds, chroots or sub mounts. If the * mount has sub mounts this will return busy * regardless of whether the sub mounts are busy. * * Doesn't take quota and stuff into account. IOW, in some cases it will * give false negatives. The main reason why it's here is that we need * a non-destructive way to look for easily umountable filesystems. */ int may_umount(struct vfsmount *mnt) { int ret = 1; down_read(&namespace_sem); lock_mount_hash(); if (propagate_mount_busy(real_mount(mnt), 2)) ret = 0; unlock_mount_hash(); up_read(&namespace_sem); return ret; } EXPORT_SYMBOL(may_umount); static void namespace_unlock(void) { struct hlist_head head; struct hlist_node *p; struct mount *m; LIST_HEAD(list); hlist_move_list(&unmounted, &head); list_splice_init(&ex_mountpoints, &list); up_write(&namespace_sem); shrink_dentry_list(&list); if (likely(hlist_empty(&head))) return; synchronize_rcu_expedited(); hlist_for_each_entry_safe(m, p, &head, mnt_umount) { hlist_del(&m->mnt_umount); mntput(&m->mnt); } } static inline void namespace_lock(void) { down_write(&namespace_sem); } enum umount_tree_flags { UMOUNT_SYNC = 1, UMOUNT_PROPAGATE = 2, UMOUNT_CONNECTED = 4, }; static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how) { /* Leaving mounts connected is only valid for lazy umounts */ if (how & UMOUNT_SYNC) return true; /* A mount without a parent has nothing to be connected to */ if (!mnt_has_parent(mnt)) return true; /* Because the reference counting rules change when mounts are * unmounted and connected, umounted mounts may not be * connected to mounted mounts. */ if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) return true; /* Has it been requested that the mount remain connected? */ if (how & UMOUNT_CONNECTED) return false; /* Is the mount locked such that it needs to remain connected? */ if (IS_MNT_LOCKED(mnt)) return false; /* By default disconnect the mount */ return true; } /* * mount_lock must be held * namespace_sem must be held for write */ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) { LIST_HEAD(tmp_list); struct mount *p; if (how & UMOUNT_PROPAGATE) propagate_mount_unlock(mnt); /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; list_move(&p->mnt_list, &tmp_list); } /* Hide the mounts from mnt_mounts */ list_for_each_entry(p, &tmp_list, mnt_list) { list_del_init(&p->mnt_child); } /* Add propogated mounts to the tmp_list */ if (how & UMOUNT_PROPAGATE) propagate_umount(&tmp_list); while (!list_empty(&tmp_list)) { struct mnt_namespace *ns; bool disconnect; p = list_first_entry(&tmp_list, struct mount, mnt_list); list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); ns = p->mnt_ns; if (ns) { ns->mounts--; __touch_mnt_namespace(ns); } p->mnt_ns = NULL; if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { /* Don't forget about p */ list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts); } else { umount_mnt(p); } } change_mnt_propagation(p, MS_PRIVATE); if (disconnect) hlist_add_head(&p->mnt_umount, &unmounted); } } static void shrink_submounts(struct mount *mnt); static int do_umount_root(struct super_block *sb) { int ret = 0; down_write(&sb->s_umount); if (!sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY, SB_RDONLY); if (IS_ERR(fc)) { ret = PTR_ERR(fc); } else { ret = parse_monolithic_mount_data(fc, NULL); if (!ret) ret = reconfigure_super(fc); put_fs_context(fc); } } up_write(&sb->s_umount); return ret; } static int do_umount(struct mount *mnt, int flags) { struct super_block *sb = mnt->mnt.mnt_sb; int retval; retval = security_sb_umount(&mnt->mnt, flags); if (retval) return retval; /* * Allow userspace to request a mountpoint be expired rather than * unmounting unconditionally. Unmount only happens if: * (1) the mark is already set (the mark is cleared by mntput()) * (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount] */ if (flags & MNT_EXPIRE) { if (&mnt->mnt == current->fs->root.mnt || flags & (MNT_FORCE | MNT_DETACH)) return -EINVAL; /* * probably don't strictly need the lock here if we examined * all race cases, but it's a slowpath. */ lock_mount_hash(); if (mnt_get_count(mnt) != 2) { unlock_mount_hash(); return -EBUSY; } unlock_mount_hash(); if (!xchg(&mnt->mnt_expiry_mark, 1)) return -EAGAIN; } /* * If we may have to abort operations to get out of this * mount, and they will themselves hold resources we must * allow the fs to do things. In the Unix tradition of * 'Gee thats tricky lets do it in userspace' the umount_begin * might fail to complete on the first run through as other tasks * must return, and the like. Thats for the mount program to worry * about for the moment. */ if (flags & MNT_FORCE && sb->s_op->umount_begin) { sb->s_op->umount_begin(sb); } /* * No sense to grab the lock for this test, but test itself looks * somewhat bogus. Suggestions for better replacement? * Ho-hum... In principle, we might treat that as umount + switch * to rootfs. GC would eventually take care of the old vfsmount. * Actually it makes sense, especially if rootfs would contain a * /reboot - static binary that would close all descriptors and * call reboot(9). Then init(8) could umount root and exec /reboot. */ if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) { /* * Special case for "unmounting" root ... * we just try to remount it readonly. */ if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return do_umount_root(sb); } namespace_lock(); lock_mount_hash(); /* Recheck MNT_LOCKED with the locks held */ retval = -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) goto out; event++; if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { smp_mb(); // paired with __legitimize_mnt() shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } } out: unlock_mount_hash(); namespace_unlock(); return retval; } /* * __detach_mounts - lazily unmount all mounts on the specified dentry * * During unlink, rmdir, and d_drop it is possible to loose the path * to an existing mountpoint, and wind up leaking the mount. * detach_mounts allows lazily unmounting those mounts instead of * leaking them. * * The caller may hold dentry->d_inode->i_mutex. */ void __detach_mounts(struct dentry *dentry) { struct mountpoint *mp; struct mount *mnt; namespace_lock(); lock_mount_hash(); mp = lookup_mountpoint(dentry); if (!mp) goto out_unlock; event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { umount_mnt(mnt); hlist_add_head(&mnt->mnt_umount, &unmounted); } else umount_tree(mnt, UMOUNT_CONNECTED); } put_mountpoint(mp); out_unlock: unlock_mount_hash(); namespace_unlock(); } /* * Is the caller allowed to modify his namespace? */ static inline bool may_mount(void) { return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN); } #ifdef CONFIG_MANDATORY_FILE_LOCKING static bool may_mandlock(void) { pr_warn_once("======================================================\n" "WARNING: the mand mount option is being deprecated and\n" " will be removed in v5.15!\n" "======================================================\n"); return capable(CAP_SYS_ADMIN); } #else static inline bool may_mandlock(void) { pr_warn("VFS: \"mand\" mount option not supported"); return false; } #endif static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); struct super_block *sb = path->dentry->d_sb; if (!may_mount()) return -EPERM; if (path->dentry != path->mnt->mnt_root) return -EINVAL; if (!check_mnt(mnt)) return -EINVAL; if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ return -EINVAL; if (flags & MNT_FORCE && !ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } // caller is responsible for flags being sane int path_umount(struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); int ret; ret = can_umount(path, flags); if (!ret) ret = do_umount(mnt, flags); /* we mustn't call path_put() as that would clear mnt_expiry_mark */ dput(path->dentry); mntput_no_expire(mnt); return ret; } static int ksys_umount(char __user *name, int flags) { int lookup_flags = LOOKUP_MOUNTPOINT; struct path path; int ret; // basic validity checks done first if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) return -EINVAL; if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; ret = user_path_at(AT_FDCWD, name, lookup_flags, &path); if (ret) return ret; return path_umount(&path, flags); } SYSCALL_DEFINE2(umount, char __user *, name, int, flags) { return ksys_umount(name, flags); } #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* * The 2.0 compatible umount. No flags. */ SYSCALL_DEFINE1(oldumount, char __user *, name) { return ksys_umount(name, 0); } #endif static bool is_mnt_ns_file(struct dentry *dentry) { /* Is this a proxy for a mount namespace? */ return dentry->d_op == &ns_dentry_operations && dentry->d_fsdata == &mntns_operations; } static struct mnt_namespace *to_mnt_ns(struct ns_common *ns) { return container_of(ns, struct mnt_namespace, ns); } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) { return &mnt->ns; } static bool mnt_ns_loop(struct dentry *dentry) { /* Could bind mounting the mount namespace inode cause a * mount namespace loop? */ struct mnt_namespace *mnt_ns; if (!is_mnt_ns_file(dentry)) return false; mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode)); return current->nsproxy->mnt_ns->seq >= mnt_ns->seq; } struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, int flag) { struct mount *res, *p, *q, *r, *parent; if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(mnt)) return ERR_PTR(-EINVAL); if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry)) return ERR_PTR(-EINVAL); res = q = clone_mnt(mnt, dentry, flag); if (IS_ERR(q)) return q; q->mnt_mountpoint = mnt->mnt_mountpoint; p = mnt; list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) { struct mount *s; if (!is_subdir(r->mnt_mountpoint, dentry)) continue; for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { if (s->mnt.mnt_flags & MNT_LOCKED) { /* Both unbindable and locked. */ q = ERR_PTR(-EPERM); goto out; } else { s = skip_mnt_tree(s); continue; } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { s = skip_mnt_tree(s); continue; } while (p != s->mnt_parent) { p = p->mnt_parent; q = q->mnt_parent; } p = s; parent = q; q = clone_mnt(p, p->mnt.mnt_root, flag); if (IS_ERR(q)) goto out; lock_mount_hash(); list_add_tail(&q->mnt_list, &res->mnt_list); attach_mnt(q, parent, p->mnt_mp); unlock_mount_hash(); } } return res; out: if (res) { lock_mount_hash(); umount_tree(res, UMOUNT_SYNC); unlock_mount_hash(); } return q; } /* Caller should check returned pointer for errors */ struct vfsmount *collect_mounts(const struct path *path) { struct mount *tree; namespace_lock(); if (!check_mnt(real_mount(path->mnt))) tree = ERR_PTR(-EINVAL); else tree = copy_tree(real_mount(path->mnt), path->dentry, CL_COPY_ALL | CL_PRIVATE); namespace_unlock(); if (IS_ERR(tree)) return ERR_CAST(tree); return &tree->mnt; } static void free_mnt_ns(struct mnt_namespace *); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool); void dissolve_on_fput(struct vfsmount *mnt) { struct mnt_namespace *ns; namespace_lock(); lock_mount_hash(); ns = real_mount(mnt)->mnt_ns; if (ns) { if (is_anon_ns(ns)) umount_tree(real_mount(mnt), UMOUNT_CONNECTED); else ns = NULL; } unlock_mount_hash(); namespace_unlock(); if (ns) free_mnt_ns(ns); } void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } static bool has_locked_children(struct mount *mnt, struct dentry *dentry) { struct mount *child; list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { if (!is_subdir(child->mnt_mountpoint, dentry)) continue; if (child->mnt.mnt_flags & MNT_LOCKED) return true; } return false; } /** * clone_private_mount - create a private clone of a path * * This creates a new vfsmount, which will be the clone of @path. The new will * not be attached anywhere in the namespace and will be private (i.e. changes * to the originating mount won't be propagated into this). * * Release with mntput(). */ struct vfsmount *clone_private_mount(const struct path *path) { struct mount *old_mnt = real_mount(path->mnt); struct mount *new_mnt; down_read(&namespace_sem); if (IS_MNT_UNBINDABLE(old_mnt)) goto invalid; if (!check_mnt(old_mnt)) goto invalid; if (has_locked_children(old_mnt, path->dentry)) goto invalid; new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); up_read(&namespace_sem); if (IS_ERR(new_mnt)) return ERR_CAST(new_mnt); /* Longterm mount to be removed by kern_unmount*() */ new_mnt->mnt_ns = MNT_NS_INTERNAL; return &new_mnt->mnt; invalid: up_read(&namespace_sem); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(clone_private_mount); int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { struct mount *mnt; int res = f(root, arg); if (res) return res; list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) { res = f(&mnt->mnt, arg); if (res) return res; } return 0; } static void lock_mnt_tree(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { int flags = p->mnt.mnt_flags; /* Don't allow unprivileged users to change mount flags */ flags |= MNT_LOCK_ATIME; if (flags & MNT_READONLY) flags |= MNT_LOCK_READONLY; if (flags & MNT_NODEV) flags |= MNT_LOCK_NODEV; if (flags & MNT_NOSUID) flags |= MNT_LOCK_NOSUID; if (flags & MNT_NOEXEC) flags |= MNT_LOCK_NOEXEC; /* Don't allow unprivileged users to reveal what is under a mount */ if (list_empty(&p->mnt_expire)) flags |= MNT_LOCKED; p->mnt.mnt_flags = flags; } } static void cleanup_group_ids(struct mount *mnt, struct mount *end) { struct mount *p; for (p = mnt; p != end; p = next_mnt(p, mnt)) { if (p->mnt_group_id && !IS_MNT_SHARED(p)) mnt_release_group_id(p); } } static int invent_group_ids(struct mount *mnt, bool recurse) { struct mount *p; for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) { if (!p->mnt_group_id && !IS_MNT_SHARED(p)) { int err = mnt_alloc_group_id(p); if (err) { cleanup_group_ids(mnt, p); return err; } } } return 0; } int count_mounts(struct mnt_namespace *ns, struct mount *mnt) { unsigned int max = READ_ONCE(sysctl_mount_max); unsigned int mounts = 0, old, pending, sum; struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) mounts++; old = ns->mounts; pending = ns->pending_mounts; sum = old + pending; if ((old > sum) || (pending > sum) || (max < sum) || (mounts > (max - sum))) return -ENOSPC; ns->pending_mounts = pending + mounts; return 0; } /* * @source_mnt : mount tree to be attached * @nd : place the mount tree @source_mnt is attached * @parent_nd : if non-null, detach the source_mnt from its parent and * store the parent mount and mountpoint dentry. * (done when source_mnt is moved) * * NOTE: in the table below explains the semantics when a source mount * of a given type is attached to a destination mount of a given type. * --------------------------------------------------------------------------- * | BIND MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (++) | shared (+) | shared(+++)| invalid | * | | | | | | * |non-shared| shared (+) | private | slave (*) | invalid | * *************************************************************************** * A bind operation clones the source mount and mounts the clone on the * destination mount. * * (++) the cloned mount is propagated to all the mounts in the propagation * tree of the destination mount and the cloned mount is added to * the peer group of the source mount. * (+) the cloned mount is created under the destination mount and is marked * as shared. The cloned mount is added to the peer group of the source * mount. * (+++) the mount is propagated to all the mounts in the propagation tree * of the destination mount and the cloned mount is made slave * of the same master as that of the source mount. The cloned mount * is marked as 'shared and slave'. * (*) the cloned mount is made a slave of the same master as that of the * source mount. * * --------------------------------------------------------------------------- * | MOVE MOUNT OPERATION | * |************************************************************************** * | source-->| shared | private | slave | unbindable | * | dest | | | | | * | | | | | | | * | v | | | | | * |************************************************************************** * | shared | shared (+) | shared (+) | shared(+++) | invalid | * | | | | | | * |non-shared| shared (+*) | private | slave (*) | unbindable | * *************************************************************************** * * (+) the mount is moved to the destination. And is then propagated to * all the mounts in the propagation tree of the destination mount. * (+*) the mount is moved to the destination. * (+++) the mount is moved to the destination and is then propagated to * all the mounts belonging to the destination mount's propagation tree. * the mount is marked as 'shared and slave'. * (*) the mount continues to be a slave at the new location. * * if the source mount is a tree, the operations explained above is * applied to each mount in the tree. * Must be called without spinlocks held, since this function can sleep * in allocations. */ static int attach_recursive_mnt(struct mount *source_mnt, struct mount *dest_mnt, struct mountpoint *dest_mp, bool moving) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; HLIST_HEAD(tree_list); struct mnt_namespace *ns = dest_mnt->mnt_ns; struct mountpoint *smp; struct mount *child, *p; struct hlist_node *n; int err; /* Preallocate a mountpoint in case the new mounts need * to be tucked under other mounts. */ smp = get_mountpoint(source_mnt->mnt.mnt_root); if (IS_ERR(smp)) return PTR_ERR(smp); /* Is there space to add these mounts to the mount namespace? */ if (!moving) { err = count_mounts(ns, source_mnt); if (err) goto out; } if (IS_MNT_SHARED(dest_mnt)) { err = invent_group_ids(source_mnt, true); if (err) goto out; err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list); lock_mount_hash(); if (err) goto out_cleanup_ids; for (p = source_mnt; p; p = next_mnt(p, source_mnt)) set_mnt_shared(p); } else { lock_mount_hash(); } if (moving) { unhash_mnt(source_mnt); attach_mnt(source_mnt, dest_mnt, dest_mp); touch_mnt_namespace(source_mnt->mnt_ns); } else { if (source_mnt->mnt_ns) { /* move from anon - the caller will destroy */ list_del_init(&source_mnt->mnt_ns->list); } mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt); commit_tree(source_mnt); } hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) { struct mount *q; hlist_del_init(&child->mnt_hash); /* Notice when we are propagating across user namespaces */ if (child->mnt_parent->mnt_ns->user_ns != user_ns) lock_mnt_tree(child); child->mnt.mnt_flags &= ~MNT_LOCKED; q = __lookup_mnt(&child->mnt_parent->mnt, child->mnt_mountpoint); if (q) mnt_change_mountpoint(child, smp, q); commit_tree(child); } put_mountpoint(smp); unlock_mount_hash(); return 0; out_cleanup_ids: while (!hlist_empty(&tree_list)) { child = hlist_entry(tree_list.first, struct mount, mnt_hash); child->mnt_parent->mnt_ns->pending_mounts = 0; umount_tree(child, UMOUNT_SYNC); } unlock_mount_hash(); cleanup_group_ids(source_mnt, NULL); out: ns->pending_mounts = 0; read_seqlock_excl(&mount_lock); put_mountpoint(smp); read_sequnlock_excl(&mount_lock); return err; } static struct mountpoint *lock_mount(struct path *path) { struct vfsmount *mnt; struct dentry *dentry = path->dentry; retry: inode_lock(dentry->d_inode); if (unlikely(cant_mount(dentry))) { inode_unlock(dentry->d_inode); return ERR_PTR(-ENOENT); } namespace_lock(); mnt = lookup_mnt(path); if (likely(!mnt)) { struct mountpoint *mp = get_mountpoint(dentry); if (IS_ERR(mp)) { namespace_unlock(); inode_unlock(dentry->d_inode); return mp; } return mp; } namespace_unlock(); inode_unlock(path->dentry->d_inode); path_put(path); path->mnt = mnt; dentry = path->dentry = dget(mnt->mnt_root); goto retry; } static void unlock_mount(struct mountpoint *where) { struct dentry *dentry = where->m_dentry; read_seqlock_excl(&mount_lock); put_mountpoint(where); read_sequnlock_excl(&mount_lock); namespace_unlock(); inode_unlock(dentry->d_inode); } static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) { if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER) return -EINVAL; if (d_is_dir(mp->m_dentry) != d_is_dir(mnt->mnt.mnt_root)) return -ENOTDIR; return attach_recursive_mnt(mnt, p, mp, false); } static int may_change_propagation(const struct mount *m) { struct mnt_namespace *ns = m->mnt_ns; // it must be mounted in some namespace if (IS_ERR_OR_NULL(ns)) // is_mounted() return -EINVAL; // and the caller must be admin in userns of that namespace if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * Sanity check the flags to change_mnt_propagation. */ static int flags_to_propagation_type(int ms_flags) { int type = ms_flags & ~(MS_REC | MS_SILENT); /* Fail if any non-propagation flags are set */ if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return 0; /* Only one propagation flag should be set */ if (!is_power_of_2(type)) return 0; return type; } /* * recursively change the type of the mountpoint. */ static int do_change_type(struct path *path, int ms_flags) { struct mount *m; struct mount *mnt = real_mount(path->mnt); int recurse = ms_flags & MS_REC; int type; int err = 0; if (path->dentry != path->mnt->mnt_root) return -EINVAL; type = flags_to_propagation_type(ms_flags); if (!type) return -EINVAL; namespace_lock(); err = may_change_propagation(mnt); if (err) goto out_unlock; if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) goto out_unlock; } lock_mount_hash(); for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL)) change_mnt_propagation(m, type); unlock_mount_hash(); out_unlock: namespace_unlock(); return err; } static struct mount *__do_loopback(struct path *old_path, int recurse) { struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt); if (IS_MNT_UNBINDABLE(old)) return mnt; if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations) return mnt; if (!recurse && has_locked_children(old, old_path->dentry)) return mnt; if (recurse) mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE); else mnt = clone_mnt(old, old_path->dentry, 0); if (!IS_ERR(mnt)) mnt->mnt.mnt_flags &= ~MNT_LOCKED; return mnt; } /* * do loopback mount. */ static int do_loopback(struct path *path, const char *old_name, int recurse) { struct path old_path; struct mount *mnt = NULL, *parent; struct mountpoint *mp; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path); if (err) return err; err = -EINVAL; if (mnt_ns_loop(old_path.dentry)) goto out; mp = lock_mount(path); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto out; } parent = real_mount(path->mnt); if (!check_mnt(parent)) goto out2; mnt = __do_loopback(&old_path, recurse); if (IS_ERR(mnt)) { err = PTR_ERR(mnt); goto out2; } err = graft_tree(mnt, parent, mp); if (err) { lock_mount_hash(); umount_tree(mnt, UMOUNT_SYNC); unlock_mount_hash(); } out2: unlock_mount(mp); out: path_put(&old_path); return err; } static struct file *open_detached_copy(struct path *path, bool recursive) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; struct mnt_namespace *ns = alloc_mnt_ns(user_ns, true); struct mount *mnt, *p; struct file *file; if (IS_ERR(ns)) return ERR_CAST(ns); namespace_lock(); mnt = __do_loopback(path, recursive); if (IS_ERR(mnt)) { namespace_unlock(); free_mnt_ns(ns); return ERR_CAST(mnt); } lock_mount_hash(); for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt_ns = ns; ns->mounts++; } ns->root = mnt; list_add_tail(&ns->list, &mnt->mnt_list); mntget(&mnt->mnt); unlock_mount_hash(); namespace_unlock(); mntput(path->mnt); path->mnt = &mnt->mnt; file = dentry_open(path, O_PATH, current_cred()); if (IS_ERR(file)) dissolve_on_fput(path->mnt); else file->f_mode |= FMODE_NEED_UNMOUNT; return file; } SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags) { struct file *file; struct path path; int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW; bool detached = flags & OPEN_TREE_CLONE; int error; int fd; BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC); if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE | AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC)) return -EINVAL; if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE) return -EINVAL; if (flags & AT_NO_AUTOMOUNT) lookup_flags &= ~LOOKUP_AUTOMOUNT; if (flags & AT_SYMLINK_NOFOLLOW) lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; if (detached && !may_mount()) return -EPERM; fd = get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) return fd; error = user_path_at(dfd, filename, lookup_flags, &path); if (unlikely(error)) { file = ERR_PTR(error); } else { if (detached) file = open_detached_copy(&path, flags & AT_RECURSIVE); else file = dentry_open(&path, O_PATH, current_cred()); path_put(&path); } if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } fd_install(fd, file); return fd; } /* * Don't allow locked mount flags to be cleared. * * No locks need to be held here while testing the various MNT_LOCK * flags because those flags can never be cleared once they are set. */ static bool can_change_locked_flags(struct mount *mnt, unsigned int mnt_flags) { unsigned int fl = mnt->mnt.mnt_flags; if ((fl & MNT_LOCK_READONLY) && !(mnt_flags & MNT_READONLY)) return false; if ((fl & MNT_LOCK_NODEV) && !(mnt_flags & MNT_NODEV)) return false; if ((fl & MNT_LOCK_NOSUID) && !(mnt_flags & MNT_NOSUID)) return false; if ((fl & MNT_LOCK_NOEXEC) && !(mnt_flags & MNT_NOEXEC)) return false; if ((fl & MNT_LOCK_ATIME) && ((fl & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) return false; return true; } static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags) { bool readonly_request = (mnt_flags & MNT_READONLY); if (readonly_request == __mnt_is_readonly(&mnt->mnt)) return 0; if (readonly_request) return mnt_make_readonly(mnt); return __mnt_unmake_readonly(mnt); } /* * Update the user-settable attributes on a mount. The caller must hold * sb->s_umount for writing. */ static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags) { lock_mount_hash(); mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; mnt->mnt.mnt_flags = mnt_flags; touch_mnt_namespace(mnt->mnt_ns); unlock_mount_hash(); } static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt) { struct super_block *sb = mnt->mnt_sb; if (!__mnt_is_readonly(mnt) && (!(sb->s_iflags & SB_I_TS_EXPIRY_WARNED)) && (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) { char *buf, *mntpath; buf = (char *)__get_free_page(GFP_KERNEL); if (buf) mntpath = d_path(mountpoint, buf, PAGE_SIZE); else mntpath = ERR_PTR(-ENOMEM); if (IS_ERR(mntpath)) mntpath = "(unknown)"; pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n", sb->s_type->name, is_mounted(mnt) ? "remounted" : "mounted", mntpath, &sb->s_time_max, (unsigned long long)sb->s_time_max); sb->s_iflags |= SB_I_TS_EXPIRY_WARNED; if (buf) free_page((unsigned long)buf); } } /* * Handle reconfiguration of the mountpoint only without alteration of the * superblock it refers to. This is triggered by specifying MS_REMOUNT|MS_BIND * to mount(2). */ static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags) { struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); int ret; if (!check_mnt(mnt)) return -EINVAL; if (path->dentry != mnt->mnt.mnt_root) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; down_write(&sb->s_umount); ret = change_mount_ro_state(mnt, mnt_flags); if (ret == 0) set_mount_attributes(mnt, mnt_flags); up_write(&sb->s_umount); mnt_warn_timestamp_expiry(path, &mnt->mnt); return ret; } /* * change filesystem flags. dir should be a physical root of filesystem. * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. */ static int do_remount(struct path *path, int ms_flags, int sb_flags, int mnt_flags, void *data) { int err; struct super_block *sb = path->mnt->mnt_sb; struct mount *mnt = real_mount(path->mnt); struct fs_context *fc; if (!check_mnt(mnt)) return -EINVAL; if (path->dentry != path->mnt->mnt_root) return -EINVAL; if (!can_change_locked_flags(mnt, mnt_flags)) return -EPERM; fc = fs_context_for_reconfigure(path->dentry, sb_flags, MS_RMT_MASK); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the remount request is coming * from the legacy mount system call. */ fc->oldapi = true; err = parse_monolithic_mount_data(fc, data); if (!err) { down_write(&sb->s_umount); err = -EPERM; if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) { err = reconfigure_super(fc); if (!err) set_mount_attributes(mnt, mnt_flags); } up_write(&sb->s_umount); } mnt_warn_timestamp_expiry(path, &mnt->mnt); put_fs_context(fc); return err; } static inline int tree_contains_unbindable(struct mount *mnt) { struct mount *p; for (p = mnt; p; p = next_mnt(p, mnt)) { if (IS_MNT_UNBINDABLE(p)) return 1; } return 0; } /* * Check that there aren't references to earlier/same mount namespaces in the * specified subtree. Such references can act as pins for mount namespaces * that aren't checked by the mount-cycle checking code, thereby allowing * cycles to be made. */ static bool check_for_nsfs_mounts(struct mount *subtree) { struct mount *p; bool ret = false; lock_mount_hash(); for (p = subtree; p; p = next_mnt(p, subtree)) if (mnt_ns_loop(p->mnt.mnt_root)) goto out; ret = true; out: unlock_mount_hash(); return ret; } static int do_set_group(struct path *from_path, struct path *to_path) { struct mount *from, *to; int err; from = real_mount(from_path->mnt); to = real_mount(to_path->mnt); namespace_lock(); err = may_change_propagation(from); if (err) goto out; err = may_change_propagation(to); if (err) goto out; err = -EINVAL; /* To and From paths should be mount roots */ if (from_path->dentry != from_path->mnt->mnt_root) goto out; if (to_path->dentry != to_path->mnt->mnt_root) goto out; /* Setting sharing groups is only allowed across same superblock */ if (from->mnt.mnt_sb != to->mnt.mnt_sb) goto out; /* From mount root should be wider than To mount root */ if (!is_subdir(to->mnt.mnt_root, from->mnt.mnt_root)) goto out; /* From mount should not have locked children in place of To's root */ if (has_locked_children(from, to->mnt.mnt_root)) goto out; /* Setting sharing groups is only allowed on private mounts */ if (IS_MNT_SHARED(to) || IS_MNT_SLAVE(to)) goto out; /* From should not be private */ if (!IS_MNT_SHARED(from) && !IS_MNT_SLAVE(from)) goto out; if (IS_MNT_SLAVE(from)) { struct mount *m = from->mnt_master; list_add(&to->mnt_slave, &m->mnt_slave_list); to->mnt_master = m; } if (IS_MNT_SHARED(from)) { to->mnt_group_id = from->mnt_group_id; list_add(&to->mnt_share, &from->mnt_share); lock_mount_hash(); set_mnt_shared(to); unlock_mount_hash(); } err = 0; out: namespace_unlock(); return err; } static int do_move_mount(struct path *old_path, struct path *new_path) { struct mnt_namespace *ns; struct mount *p; struct mount *old; struct mount *parent; struct mountpoint *mp, *old_mp; int err; bool attached; mp = lock_mount(new_path); if (IS_ERR(mp)) return PTR_ERR(mp); old = real_mount(old_path->mnt); p = real_mount(new_path->mnt); parent = old->mnt_parent; attached = mnt_has_parent(old); old_mp = old->mnt_mp; ns = old->mnt_ns; err = -EINVAL; /* The mountpoint must be in our namespace. */ if (!check_mnt(p)) goto out; /* The thing moved must be mounted... */ if (!is_mounted(&old->mnt)) goto out; /* ... and either ours or the root of anon namespace */ if (!(attached ? check_mnt(old) : is_anon_ns(ns))) goto out; if (old->mnt.mnt_flags & MNT_LOCKED) goto out; if (old_path->dentry != old_path->mnt->mnt_root) goto out; if (d_is_dir(new_path->dentry) != d_is_dir(old_path->dentry)) goto out; /* * Don't move a mount residing in a shared parent. */ if (attached && IS_MNT_SHARED(parent)) goto out; /* * Don't move a mount tree containing unbindable mounts to a destination * mount which is shared. */ if (IS_MNT_SHARED(p) && tree_contains_unbindable(old)) goto out; err = -ELOOP; if (!check_for_nsfs_mounts(old)) goto out; for (; mnt_has_parent(p); p = p->mnt_parent) if (p == old) goto out; err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, attached); if (err) goto out; /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old->mnt_expire); if (attached) put_mountpoint(old_mp); out: unlock_mount(mp); if (!err) { if (attached) mntput_no_expire(parent); else free_mnt_ns(ns); } return err; } static int do_move_mount_old(struct path *path, const char *old_name) { struct path old_path; int err; if (!old_name || !*old_name) return -EINVAL; err = kern_path(old_name, LOOKUP_FOLLOW, &old_path); if (err) return err; err = do_move_mount(&old_path, path); path_put(&old_path); return err; } /* * add a mount into a namespace's mount tree */ static int do_add_mount(struct mount *newmnt, struct mountpoint *mp, struct path *path, int mnt_flags) { struct mount *parent = real_mount(path->mnt); mnt_flags &= ~MNT_INTERNAL_FLAGS; if (unlikely(!check_mnt(parent))) { /* that's acceptable only for automounts done in private ns */ if (!(mnt_flags & MNT_SHRINKABLE)) return -EINVAL; /* ... and for those we'd better have mountpoint still alive */ if (!parent->mnt_ns) return -EINVAL; } /* Refuse the same filesystem on the same mount point */ if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb && path->mnt->mnt_root == path->dentry) return -EBUSY; if (d_is_symlink(newmnt->mnt.mnt_root)) return -EINVAL; newmnt->mnt.mnt_flags = mnt_flags; return graft_tree(newmnt, parent, mp); } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags); /* * Create a new mount using a superblock configuration and request it * be added to the namespace tree. */ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint, unsigned int mnt_flags) { struct vfsmount *mnt; struct mountpoint *mp; struct super_block *sb = fc->root->d_sb; int error; error = security_sb_kern_mount(sb); if (!error && mount_too_revealing(sb, &mnt_flags)) error = -EPERM; if (unlikely(error)) { fc_drop_locked(fc); return error; } up_write(&sb->s_umount); mnt = vfs_create_mount(fc); if (IS_ERR(mnt)) return PTR_ERR(mnt); mnt_warn_timestamp_expiry(mountpoint, mnt); mp = lock_mount(mountpoint); if (IS_ERR(mp)) { mntput(mnt); return PTR_ERR(mp); } error = do_add_mount(real_mount(mnt), mp, mountpoint, mnt_flags); unlock_mount(mp); if (error < 0) mntput(mnt); return error; } /* * create a new mount for userspace and request it to be added into the * namespace's tree */ static int do_new_mount(struct path *path, const char *fstype, int sb_flags, int mnt_flags, const char *name, void *data) { struct file_system_type *type; struct fs_context *fc; const char *subtype = NULL; int err = 0; if (!fstype) return -EINVAL; type = get_fs_type(fstype); if (!type) return -ENODEV; if (type->fs_flags & FS_HAS_SUBTYPE) { subtype = strchr(fstype, '.'); if (subtype) { subtype++; if (!*subtype) { put_filesystem(type); return -EINVAL; } } } fc = fs_context_for_mount(type, sb_flags); put_filesystem(type); if (IS_ERR(fc)) return PTR_ERR(fc); /* * Indicate to the filesystem that the mount request is coming * from the legacy mount system call. */ fc->oldapi = true; if (subtype) err = vfs_parse_fs_string(fc, "subtype", subtype, strlen(subtype)); if (!err && name) err = vfs_parse_fs_string(fc, "source", name, strlen(name)); if (!err) err = parse_monolithic_mount_data(fc, data); if (!err && !mount_capable(fc)) err = -EPERM; if (!err) err = vfs_get_tree(fc); if (!err) err = do_new_mount_fc(fc, path, mnt_flags); put_fs_context(fc); return err; } int finish_automount(struct vfsmount *m, struct path *path) { struct dentry *dentry = path->dentry; struct mountpoint *mp; struct mount *mnt; int err; if (!m) return 0; if (IS_ERR(m)) return PTR_ERR(m); mnt = real_mount(m); /* The new mount record should have at least 2 refs to prevent it being * expired before we get a chance to add it */ BUG_ON(mnt_get_count(mnt) < 2); if (m->mnt_sb == path->mnt->mnt_sb && m->mnt_root == dentry) { err = -ELOOP; goto discard; } /* * we don't want to use lock_mount() - in this case finding something * that overmounts our mountpoint to be means "quitely drop what we've * got", not "try to mount it on top". */ inode_lock(dentry->d_inode); namespace_lock(); if (unlikely(cant_mount(dentry))) { err = -ENOENT; goto discard_locked; } rcu_read_lock(); if (unlikely(__lookup_mnt(path->mnt, dentry))) { rcu_read_unlock(); err = 0; goto discard_locked; } rcu_read_unlock(); mp = get_mountpoint(dentry); if (IS_ERR(mp)) { err = PTR_ERR(mp); goto discard_locked; } err = do_add_mount(mnt, mp, path, path->mnt->mnt_flags | MNT_SHRINKABLE); unlock_mount(mp); if (unlikely(err)) goto discard; mntput(m); return 0; discard_locked: namespace_unlock(); inode_unlock(dentry->d_inode); discard: /* remove m from any expiration list it may be on */ if (!list_empty(&mnt->mnt_expire)) { namespace_lock(); list_del_init(&mnt->mnt_expire); namespace_unlock(); } mntput(m); mntput(m); return err; } /** * mnt_set_expiry - Put a mount on an expiration list * @mnt: The mount to list. * @expiry_list: The list to add the mount to. */ void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list) { namespace_lock(); list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list); namespace_unlock(); } EXPORT_SYMBOL(mnt_set_expiry); /* * process a list of expirable mountpoints with the intent of discarding any * mountpoints that aren't in use and haven't been touched since last we came * here */ void mark_mounts_for_expiry(struct list_head *mounts) { struct mount *mnt, *next; LIST_HEAD(graveyard); if (list_empty(mounts)) return; namespace_lock(); lock_mount_hash(); /* extract from the expiration list every vfsmount that matches the * following criteria: * - only referenced by its parent vfsmount * - still marked for expiry (marked on the last call here; marks are * cleared by mntput()) */ list_for_each_entry_safe(mnt, next, mounts, mnt_expire) { if (!xchg(&mnt->mnt_expiry_mark, 1) || propagate_mount_busy(mnt, 1)) continue; list_move(&mnt->mnt_expire, &graveyard); } while (!list_empty(&graveyard)) { mnt = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(mnt->mnt_ns); umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); } unlock_mount_hash(); namespace_unlock(); } EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); /* * Ripoff of 'select_parent()' * * search the list of submounts for a given mountpoint, and move any * shrinkable submounts to the 'graveyard' list. */ static int select_submounts(struct mount *parent, struct list_head *graveyard) { struct mount *this_parent = parent; struct list_head *next; int found = 0; repeat: next = this_parent->mnt_mounts.next; resume: while (next != &this_parent->mnt_mounts) { struct list_head *tmp = next; struct mount *mnt = list_entry(tmp, struct mount, mnt_child); next = tmp->next; if (!(mnt->mnt.mnt_flags & MNT_SHRINKABLE)) continue; /* * Descend a level if the d_mounts list is non-empty. */ if (!list_empty(&mnt->mnt_mounts)) { this_parent = mnt; goto repeat; } if (!propagate_mount_busy(mnt, 1)) { list_move_tail(&mnt->mnt_expire, graveyard); found++; } } /* * All done at this level ... ascend and resume the search */ if (this_parent != parent) { next = this_parent->mnt_child.next; this_parent = this_parent->mnt_parent; goto resume; } return found; } /* * process a list of expirable mountpoints with the intent of discarding any * submounts of a specific parent mountpoint * * mount_lock must be held for write */ static void shrink_submounts(struct mount *mnt) { LIST_HEAD(graveyard); struct mount *m; /* extract submounts of 'mountpoint' from the expiration list */ while (select_submounts(mnt, &graveyard)) { while (!list_empty(&graveyard)) { m = list_first_entry(&graveyard, struct mount, mnt_expire); touch_mnt_namespace(m->mnt_ns); umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC); } } } static void *copy_mount_options(const void __user * data) { char *copy; unsigned left, offset; if (!data) return NULL; copy = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!copy) return ERR_PTR(-ENOMEM); left = copy_from_user(copy, data, PAGE_SIZE); /* * Not all architectures have an exact copy_from_user(). Resort to * byte at a time. */ offset = PAGE_SIZE - left; while (left) { char c; if (get_user(c, (const char __user *)data + offset)) break; copy[offset] = c; left--; offset++; } if (left == PAGE_SIZE) { kfree(copy); return ERR_PTR(-EFAULT); } return copy; } static char *copy_mount_string(const void __user *data) { return data ? strndup_user(data, PATH_MAX) : NULL; } /* * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to * be given to the mount() call (ie: read-only, no-dev, no-suid etc). * * data is a (void *) that can point to any structure up to * PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent * information (or be NULL). * * Pre-0.97 versions of mount() didn't have a flags word. * When the flags word was introduced its top half was required * to have the magic value 0xC0ED, and this remained so until 2.4.0-test9. * Therefore, if this magic number is present, it carries no information * and must be discarded. */ int path_mount(const char *dev_name, struct path *path, const char *type_page, unsigned long flags, void *data_page) { unsigned int mnt_flags = 0, sb_flags; int ret; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; /* Basic sanity checks */ if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; if (flags & MS_NOUSER) return -EINVAL; ret = security_sb_mount(dev_name, path, type_page, flags, data_page); if (ret) return ret; if (!may_mount()) return -EPERM; if ((flags & SB_MANDLOCK) && !may_mandlock()) return -EPERM; /* Default to relatime unless overriden */ if (!(flags & MS_NOATIME)) mnt_flags |= MNT_RELATIME; /* Separate the per-mountpoint flags */ if (flags & MS_NOSUID) mnt_flags |= MNT_NOSUID; if (flags & MS_NODEV) mnt_flags |= MNT_NODEV; if (flags & MS_NOEXEC) mnt_flags |= MNT_NOEXEC; if (flags & MS_NOATIME) mnt_flags |= MNT_NOATIME; if (flags & MS_NODIRATIME) mnt_flags |= MNT_NODIRATIME; if (flags & MS_STRICTATIME) mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; if (flags & MS_NOSYMFOLLOW) mnt_flags |= MNT_NOSYMFOLLOW; /* The default atime for remount is preservation */ if ((flags & MS_REMOUNT) && ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME | MS_STRICTATIME)) == 0)) { mnt_flags &= ~MNT_ATIME_MASK; mnt_flags |= path->mnt->mnt_flags & MNT_ATIME_MASK; } sb_flags = flags & (SB_RDONLY | SB_SYNCHRONOUS | SB_MANDLOCK | SB_DIRSYNC | SB_SILENT | SB_POSIXACL | SB_LAZYTIME | SB_I_VERSION); if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND)) return do_reconfigure_mnt(path, mnt_flags); if (flags & MS_REMOUNT) return do_remount(path, flags, sb_flags, mnt_flags, data_page); if (flags & MS_BIND) return do_loopback(path, dev_name, flags & MS_REC); if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return do_change_type(path, flags); if (flags & MS_MOVE) return do_move_mount_old(path, dev_name); return do_new_mount(path, type_page, sb_flags, mnt_flags, dev_name, data_page); } long do_mount(const char *dev_name, const char __user *dir_name, const char *type_page, unsigned long flags, void *data_page) { struct path path; int ret; ret = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path); if (ret) return ret; ret = path_mount(dev_name, &path, type_page, flags, data_page); path_put(&path); return ret; } static struct ucounts *inc_mnt_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_MNT_NAMESPACES); } static void dec_mnt_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_MNT_NAMESPACES); } static void free_mnt_ns(struct mnt_namespace *ns) { if (!is_anon_ns(ns)) ns_free_inum(&ns->ns); dec_mnt_namespaces(ns->ucounts); put_user_ns(ns->user_ns); kfree(ns); } /* * Assign a sequence number so we can detect when we attempt to bind * mount a reference to an older mount namespace into the current * mount namespace, preventing reference counting loops. A 64bit * number incrementing at 10Ghz will take 12,427 years to wrap which * is effectively never, so we can ignore the possibility. */ static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1); static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool anon) { struct mnt_namespace *new_ns; struct ucounts *ucounts; int ret; ucounts = inc_mnt_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL); if (!new_ns) { dec_mnt_namespaces(ucounts); return ERR_PTR(-ENOMEM); } if (!anon) { ret = ns_alloc_inum(&new_ns->ns); if (ret) { kfree(new_ns); dec_mnt_namespaces(ucounts); return ERR_PTR(ret); } } new_ns->ns.ops = &mntns_operations; if (!anon) new_ns->seq = atomic64_add_return(1, &mnt_ns_seq); atomic_set(&new_ns->count, 1); INIT_LIST_HEAD(&new_ns->list); init_waitqueue_head(&new_ns->poll); spin_lock_init(&new_ns->ns_lock); new_ns->user_ns = get_user_ns(user_ns); new_ns->ucounts = ucounts; return new_ns; } __latent_entropy struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns, struct user_namespace *user_ns, struct fs_struct *new_fs) { struct mnt_namespace *new_ns; struct vfsmount *rootmnt = NULL, *pwdmnt = NULL; struct mount *p, *q; struct mount *old; struct mount *new; int copy_flags; BUG_ON(!ns); if (likely(!(flags & CLONE_NEWNS))) { get_mnt_ns(ns); return ns; } old = ns->root; new_ns = alloc_mnt_ns(user_ns, false); if (IS_ERR(new_ns)) return new_ns; namespace_lock(); /* First pass: copy the tree topology */ copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE; if (user_ns != ns->user_ns) copy_flags |= CL_SHARED_TO_SLAVE; new = copy_tree(old, old->mnt.mnt_root, copy_flags); if (IS_ERR(new)) { namespace_unlock(); free_mnt_ns(new_ns); return ERR_CAST(new); } if (user_ns != ns->user_ns) { lock_mount_hash(); lock_mnt_tree(new); unlock_mount_hash(); } new_ns->root = new; list_add_tail(&new_ns->list, &new->mnt_list); /* * Second pass: switch the tsk->fs->* elements and mark new vfsmounts * as belonging to new namespace. We have already acquired a private * fs_struct, so tsk->fs->lock is not needed. */ p = old; q = new; while (p) { q->mnt_ns = new_ns; new_ns->mounts++; if (new_fs) { if (&p->mnt == new_fs->root.mnt) { new_fs->root.mnt = mntget(&q->mnt); rootmnt = &p->mnt; } if (&p->mnt == new_fs->pwd.mnt) { new_fs->pwd.mnt = mntget(&q->mnt); pwdmnt = &p->mnt; } } p = next_mnt(p, old); q = next_mnt(q, new); if (!q) break; while (p->mnt.mnt_root != q->mnt.mnt_root) p = next_mnt(p, old); } namespace_unlock(); if (rootmnt) mntput(rootmnt); if (pwdmnt) mntput(pwdmnt); return new_ns; } struct dentry *mount_subtree(struct vfsmount *m, const char *name) { struct mount *mnt = real_mount(m); struct mnt_namespace *ns; struct super_block *s; struct path path; int err; ns = alloc_mnt_ns(&init_user_ns, true); if (IS_ERR(ns)) { mntput(m); return ERR_CAST(ns); } mnt->mnt_ns = ns; ns->root = mnt; ns->mounts++; list_add(&mnt->mnt_list, &ns->list); err = vfs_path_lookup(m->mnt_root, m, name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path); put_mnt_ns(ns); if (err) return ERR_PTR(err); /* trade a vfsmount reference for active sb one */ s = path.mnt->mnt_sb; atomic_inc(&s->s_active); mntput(path.mnt); /* lock the sucker */ down_write(&s->s_umount); /* ... and return the root of (sub)tree on it */ return path.dentry; } EXPORT_SYMBOL(mount_subtree); SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, char __user *, type, unsigned long, flags, void __user *, data) { int ret; char *kernel_type; char *kernel_dev; void *options; kernel_type = copy_mount_string(type); ret = PTR_ERR(kernel_type); if (IS_ERR(kernel_type)) goto out_type; kernel_dev = copy_mount_string(dev_name); ret = PTR_ERR(kernel_dev); if (IS_ERR(kernel_dev)) goto out_dev; options = copy_mount_options(data); ret = PTR_ERR(options); if (IS_ERR(options)) goto out_data; ret = do_mount(kernel_dev, dir_name, kernel_type, flags, options); kfree(options); out_data: kfree(kernel_dev); out_dev: kfree(kernel_type); out_type: return ret; } /* * Create a kernel mount representation for a new, prepared superblock * (specified by fs_fd) and attach to an open_tree-like file descriptor. */ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, unsigned int, attr_flags) { struct mnt_namespace *ns; struct fs_context *fc; struct file *file; struct path newmount; struct mount *mnt; struct fd f; unsigned int mnt_flags = 0; long ret; if (!may_mount()) return -EPERM; if ((flags & ~(FSMOUNT_CLOEXEC)) != 0) return -EINVAL; if (attr_flags & ~(MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME)) return -EINVAL; if (attr_flags & MOUNT_ATTR_RDONLY) mnt_flags |= MNT_READONLY; if (attr_flags & MOUNT_ATTR_NOSUID) mnt_flags |= MNT_NOSUID; if (attr_flags & MOUNT_ATTR_NODEV) mnt_flags |= MNT_NODEV; if (attr_flags & MOUNT_ATTR_NOEXEC) mnt_flags |= MNT_NOEXEC; if (attr_flags & MOUNT_ATTR_NODIRATIME) mnt_flags |= MNT_NODIRATIME; switch (attr_flags & MOUNT_ATTR__ATIME) { case MOUNT_ATTR_STRICTATIME: break; case MOUNT_ATTR_NOATIME: mnt_flags |= MNT_NOATIME; break; case MOUNT_ATTR_RELATIME: mnt_flags |= MNT_RELATIME; break; default: return -EINVAL; } f = fdget(fs_fd); if (!f.file) return -EBADF; ret = -EINVAL; if (f.file->f_op != &fscontext_fops) goto err_fsfd; fc = f.file->private_data; ret = mutex_lock_interruptible(&fc->uapi_mutex); if (ret < 0) goto err_fsfd; /* There must be a valid superblock or we can't mount it */ ret = -EINVAL; if (!fc->root) goto err_unlock; ret = -EPERM; if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) { pr_warn("VFS: Mount too revealing\n"); goto err_unlock; } ret = -EBUSY; if (fc->phase != FS_CONTEXT_AWAITING_MOUNT) goto err_unlock; ret = -EPERM; if ((fc->sb_flags & SB_MANDLOCK) && !may_mandlock()) goto err_unlock; newmount.mnt = vfs_create_mount(fc); if (IS_ERR(newmount.mnt)) { ret = PTR_ERR(newmount.mnt); goto err_unlock; } newmount.dentry = dget(fc->root); newmount.mnt->mnt_flags = mnt_flags; /* We've done the mount bit - now move the file context into more or * less the same state as if we'd done an fspick(). We don't want to * do any memory allocation or anything like that at this point as we * don't want to have to handle any errors incurred. */ vfs_clean_context(fc); ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true); if (IS_ERR(ns)) { ret = PTR_ERR(ns); goto err_path; } mnt = real_mount(newmount.mnt); mnt->mnt_ns = ns; ns->root = mnt; ns->mounts = 1; list_add(&mnt->mnt_list, &ns->list); mntget(newmount.mnt); /* Attach to an apparent O_PATH fd with a note that we need to unmount * it, not just simply put it. */ file = dentry_open(&newmount, O_PATH, fc->cred); if (IS_ERR(file)) { dissolve_on_fput(newmount.mnt); ret = PTR_ERR(file); goto err_path; } file->f_mode |= FMODE_NEED_UNMOUNT; ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0); if (ret >= 0) fd_install(ret, file); else fput(file); err_path: path_put(&newmount); err_unlock: mutex_unlock(&fc->uapi_mutex); err_fsfd: fdput(f); return ret; } /* * Move a mount from one place to another. In combination with * fsopen()/fsmount() this is used to install a new mount and in combination * with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy * a mount subtree. * * Note the flags value is a combination of MOVE_MOUNT_* flags. */ SYSCALL_DEFINE5(move_mount, int, from_dfd, const char __user *, from_pathname, int, to_dfd, const char __user *, to_pathname, unsigned int, flags) { struct path from_path, to_path; unsigned int lflags; int ret = 0; if (!may_mount()) return -EPERM; if (flags & ~MOVE_MOUNT__MASK) return -EINVAL; /* If someone gives a pathname, they aren't permitted to move * from an fd that requires unmount as we can't get at the flag * to clear it afterwards. */ lflags = 0; if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_F_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(from_dfd, from_pathname, lflags, &from_path); if (ret < 0) return ret; lflags = 0; if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW; if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; if (flags & MOVE_MOUNT_T_EMPTY_PATH) lflags |= LOOKUP_EMPTY; ret = user_path_at(to_dfd, to_pathname, lflags, &to_path); if (ret < 0) goto out_from; ret = security_move_mount(&from_path, &to_path); if (ret < 0) goto out_to; if (flags & MOVE_MOUNT_SET_GROUP) ret = do_set_group(&from_path, &to_path); else ret = do_move_mount(&from_path, &to_path); out_to: path_put(&to_path); out_from: path_put(&from_path); return ret; } /* * Return true if path is reachable from root * * namespace_sem or mount_lock is held */ bool is_path_reachable(struct mount *mnt, struct dentry *dentry, const struct path *root) { while (&mnt->mnt != root->mnt && mnt_has_parent(mnt)) { dentry = mnt->mnt_mountpoint; mnt = mnt->mnt_parent; } return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry); } bool path_is_under(const struct path *path1, const struct path *path2) { bool res; read_seqlock_excl(&mount_lock); res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2); read_sequnlock_excl(&mount_lock); return res; } EXPORT_SYMBOL(path_is_under); /* * pivot_root Semantics: * Moves the root file system of the current process to the directory put_old, * makes new_root as the new root file system of the current process, and sets * root/cwd of all processes which had them on the current root to new_root. * * Restrictions: * The new_root and put_old must be directories, and must not be on the * same file system as the current process root. The put_old must be * underneath new_root, i.e. adding a non-zero number of /.. to the string * pointed to by put_old must yield the same directory as new_root. No other * file system may be mounted on put_old. After all, new_root is a mountpoint. * * Also, the current root cannot be on the 'rootfs' (initial ramfs) filesystem. * See Documentation/filesystems/ramfs-rootfs-initramfs.rst for alternatives * in this situation. * * Notes: * - we don't move root/cwd if they are not at the root (reason: if something * cared enough to change them, it's probably wrong to force them elsewhere) * - it's okay to pick a root that isn't the root of a file system, e.g. * /nfs/my_root where /nfs is the mount point. It must be a mountpoint, * though, so you may need to say mount --bind /nfs/my_root /nfs/my_root * first. */ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, const char __user *, put_old) { struct path new, old, root; struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent; struct mountpoint *old_mp, *root_mp; int error; if (!may_mount()) return -EPERM; error = user_path_at(AT_FDCWD, new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &new); if (error) goto out0; error = user_path_at(AT_FDCWD, put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old); if (error) goto out1; error = security_sb_pivotroot(&old, &new); if (error) goto out2; get_fs_root(current->fs, &root); old_mp = lock_mount(&old); error = PTR_ERR(old_mp); if (IS_ERR(old_mp)) goto out3; error = -EINVAL; new_mnt = real_mount(new.mnt); root_mnt = real_mount(root.mnt); old_mnt = real_mount(old.mnt); ex_parent = new_mnt->mnt_parent; root_parent = root_mnt->mnt_parent; if (IS_MNT_SHARED(old_mnt) || IS_MNT_SHARED(ex_parent) || IS_MNT_SHARED(root_parent)) goto out4; if (!check_mnt(root_mnt) || !check_mnt(new_mnt)) goto out4; if (new_mnt->mnt.mnt_flags & MNT_LOCKED) goto out4; error = -ENOENT; if (d_unlinked(new.dentry)) goto out4; error = -EBUSY; if (new_mnt == root_mnt || old_mnt == root_mnt) goto out4; /* loop, on the same file system */ error = -EINVAL; if (root.mnt->mnt_root != root.dentry) goto out4; /* not a mountpoint */ if (!mnt_has_parent(root_mnt)) goto out4; /* not attached */ if (new.mnt->mnt_root != new.dentry) goto out4; /* not a mountpoint */ if (!mnt_has_parent(new_mnt)) goto out4; /* not attached */ /* make sure we can reach put_old from new_root */ if (!is_path_reachable(old_mnt, old.dentry, &new)) goto out4; /* make certain new is below the root */ if (!is_path_reachable(new_mnt, new.dentry, &root)) goto out4; lock_mount_hash(); umount_mnt(new_mnt); root_mp = unhash_mnt(root_mnt); /* we'll need its mountpoint */ if (root_mnt->mnt.mnt_flags & MNT_LOCKED) { new_mnt->mnt.mnt_flags |= MNT_LOCKED; root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; } /* mount old root on put_old */ attach_mnt(root_mnt, old_mnt, old_mp); /* mount new_root on / */ attach_mnt(new_mnt, root_parent, root_mp); mnt_add_count(root_parent, -1); touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ list_del_init(&new_mnt->mnt_expire); put_mountpoint(root_mp); unlock_mount_hash(); chroot_fs_refs(&root, &new); error = 0; out4: unlock_mount(old_mp); if (!error) mntput_no_expire(ex_parent); out3: path_put(&root); out2: path_put(&old); out1: path_put(&new); out0: return error; } static void __init init_mount_tree(void) { struct vfsmount *mnt; struct mount *m; struct mnt_namespace *ns; struct path root; mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", NULL); if (IS_ERR(mnt)) panic("Can't create rootfs"); ns = alloc_mnt_ns(&init_user_ns, false); if (IS_ERR(ns)) panic("Can't allocate initial namespace"); m = real_mount(mnt); m->mnt_ns = ns; ns->root = m; ns->mounts = 1; list_add(&m->mnt_list, &ns->list); init_task.nsproxy->mnt_ns = ns; get_mnt_ns(ns); root.mnt = mnt; root.dentry = mnt->mnt_root; mnt->mnt_flags |= MNT_LOCKED; set_fs_pwd(current->fs, &root); set_fs_root(current->fs, &root); } void __init mnt_init(void) { int err; mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); mount_hashtable = alloc_large_system_hash("Mount-cache", sizeof(struct hlist_head), mhash_entries, 19, HASH_ZERO, &m_hash_shift, &m_hash_mask, 0, 0); mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", sizeof(struct hlist_head), mphash_entries, 19, HASH_ZERO, &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); kernfs_init(); err = sysfs_init(); if (err) printk(KERN_WARNING "%s: sysfs_init error: %d\n", __func__, err); fs_kobj = kobject_create_and_add("fs", NULL); if (!fs_kobj) printk(KERN_WARNING "%s: kobj create error\n", __func__); shmem_init(); init_rootfs(); init_mount_tree(); } void put_mnt_ns(struct mnt_namespace *ns) { if (!atomic_dec_and_test(&ns->count)) return; drop_collected_mounts(&ns->root->mnt); free_mnt_ns(ns); } struct vfsmount *kern_mount(struct file_system_type *type) { struct vfsmount *mnt; mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (!IS_ERR(mnt)) { /* * it is a longterm mount, don't release mnt until * we unmount before file sys is unregistered */ real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL; } return mnt; } EXPORT_SYMBOL_GPL(kern_mount); void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ if (!IS_ERR_OR_NULL(mnt)) { real_mount(mnt)->mnt_ns = NULL; synchronize_rcu(); /* yecchhh... */ mntput(mnt); } } EXPORT_SYMBOL(kern_unmount); void kern_unmount_array(struct vfsmount *mnt[], unsigned int num) { unsigned int i; for (i = 0; i < num; i++) if (mnt[i]) real_mount(mnt[i])->mnt_ns = NULL; synchronize_rcu_expedited(); for (i = 0; i < num; i++) mntput(mnt[i]); } EXPORT_SYMBOL(kern_unmount_array); bool our_mnt(struct vfsmount *mnt) { return check_mnt(real_mount(mnt)); } bool current_chrooted(void) { /* Does the current process have a non-standard root */ struct path ns_root; struct path fs_root; bool chrooted; /* Find the namespace root */ ns_root.mnt = ¤t->nsproxy->mnt_ns->root->mnt; ns_root.dentry = ns_root.mnt->mnt_root; path_get(&ns_root); while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root)) ; get_fs_root(current->fs, &fs_root); chrooted = !path_equal(&fs_root, &ns_root); path_put(&fs_root); path_put(&ns_root); return chrooted; } static bool mnt_already_visible(struct mnt_namespace *ns, const struct super_block *sb, int *new_mnt_flags) { int new_flags = *new_mnt_flags; struct mount *mnt; bool visible = false; down_read(&namespace_sem); lock_ns_list(ns); list_for_each_entry(mnt, &ns->list, mnt_list) { struct mount *child; int mnt_flags; if (mnt_is_cursor(mnt)) continue; if (mnt->mnt.mnt_sb->s_type != sb->s_type) continue; /* This mount is not fully visible if it's root directory * is not the root directory of the filesystem. */ if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; /* A local view of the mount flags */ mnt_flags = mnt->mnt.mnt_flags; /* Don't miss readonly hidden in the superblock flags */ if (sb_rdonly(mnt->mnt.mnt_sb)) mnt_flags |= MNT_LOCK_READONLY; /* Verify the mount flags are equal to or more permissive * than the proposed new mount. */ if ((mnt_flags & MNT_LOCK_READONLY) && !(new_flags & MNT_READONLY)) continue; if ((mnt_flags & MNT_LOCK_ATIME) && ((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) continue; /* This mount is not fully visible if there are any * locked child mounts that cover anything except for * empty directories. */ list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; /* Only worry about locked mounts */ if (!(child->mnt.mnt_flags & MNT_LOCKED)) continue; /* Is the directory permanetly empty? */ if (!is_empty_dir_inode(inode)) goto next; } /* Preserve the locked attributes */ *new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \ MNT_LOCK_ATIME); visible = true; goto found; next: ; } found: unlock_ns_list(ns); up_read(&namespace_sem); return visible; } static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags) { const unsigned long required_iflags = SB_I_NOEXEC | SB_I_NODEV; struct mnt_namespace *ns = current->nsproxy->mnt_ns; unsigned long s_iflags; if (ns->user_ns == &init_user_ns) return false; /* Can this filesystem be too revealing? */ s_iflags = sb->s_iflags; if (!(s_iflags & SB_I_USERNS_VISIBLE)) return false; if ((s_iflags & required_iflags) != required_iflags) { WARN_ONCE(1, "Expected s_iflags to contain 0x%lx\n", required_iflags); return true; } return !mnt_already_visible(ns, sb, new_mnt_flags); } bool mnt_may_suid(struct vfsmount *mnt) { /* * Foreign mounts (accessed via fchdir or through /proc * symlinks) are always treated as if they are nosuid. This * prevents namespaces from trusting potentially unsafe * suid/sgid bits, file caps, or security labels that originate * in other namespaces. */ return !(mnt->mnt_flags & MNT_NOSUID) && check_mnt(real_mount(mnt)) && current_in_userns(mnt->mnt_sb->s_user_ns); } static struct ns_common *mntns_get(struct task_struct *task) { struct ns_common *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = &nsproxy->mnt_ns->ns; get_mnt_ns(to_mnt_ns(ns)); } task_unlock(task); return ns; } static void mntns_put(struct ns_common *ns) { put_mnt_ns(to_mnt_ns(ns)); } static int mntns_install(struct nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct fs_struct *fs = nsset->fs; struct mnt_namespace *mnt_ns = to_mnt_ns(ns), *old_mnt_ns; struct user_namespace *user_ns = nsset->cred->user_ns; struct path root; int err; if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(user_ns, CAP_SYS_CHROOT) || !ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; if (is_anon_ns(mnt_ns)) return -EINVAL; if (fs->users != 1) return -EINVAL; get_mnt_ns(mnt_ns); old_mnt_ns = nsproxy->mnt_ns; nsproxy->mnt_ns = mnt_ns; /* Find the root */ err = vfs_path_lookup(mnt_ns->root->mnt.mnt_root, &mnt_ns->root->mnt, "/", LOOKUP_DOWN, &root); if (err) { /* revert to old namespace */ nsproxy->mnt_ns = old_mnt_ns; put_mnt_ns(mnt_ns); return err; } put_mnt_ns(old_mnt_ns); /* Update the pwd and root */ set_fs_pwd(fs, &root); set_fs_root(fs, &root); path_put(&root); return 0; } static struct user_namespace *mntns_owner(struct ns_common *ns) { return to_mnt_ns(ns)->user_ns; } const struct proc_ns_operations mntns_operations = { .name = "mnt", .type = CLONE_NEWNS, .get = mntns_get, .put = mntns_put, .install = mntns_install, .owner = mntns_owner, }; |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/highuid.h> #include <linux/cred.h> #include <linux/securebits.h> #include <linux/keyctl.h> #include <linux/key-type.h> #include <keys/user-type.h> #include <linux/seq_file.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/projid.h> #include <linux/fs_struct.h> #include <linux/bsearch.h> #include <linux/sort.h> static struct kmem_cache *user_ns_cachep __read_mostly; static DEFINE_MUTEX(userns_state_mutex); static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *map); static void free_user_ns(struct work_struct *work); static struct ucounts *inc_user_namespaces(struct user_namespace *ns, kuid_t uid) { return inc_ucount(ns, uid, UCOUNT_USER_NAMESPACES); } static void dec_user_namespaces(struct ucounts *ucounts) { return dec_ucount(ucounts, UCOUNT_USER_NAMESPACES); } static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) { /* Start with the same capabilities as init but useless for doing * anything as the capabilities are bound to the new user namespace. */ cred->securebits = SECUREBITS_DEFAULT; cred->cap_inheritable = CAP_EMPTY_SET; cred->cap_permitted = CAP_FULL_SET; cred->cap_effective = CAP_FULL_SET; cred->cap_ambient = CAP_EMPTY_SET; cred->cap_bset = CAP_FULL_SET; #ifdef CONFIG_KEYS key_put(cred->request_key_auth); cred->request_key_auth = NULL; #endif /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ cred->user_ns = user_ns; } /* * Create a new user namespace, deriving the creator from the user in the * passed credentials, and replacing that user with the new root user for the * new namespace. * * This is called by copy_creds(), which will finish setting the target task's * credentials. */ int create_user_ns(struct cred *new) { struct user_namespace *ns, *parent_ns = new->user_ns; kuid_t owner = new->euid; kgid_t group = new->egid; struct ucounts *ucounts; int ret, i; ret = -ENOSPC; if (parent_ns->level > 32) goto fail; ucounts = inc_user_namespaces(parent_ns, owner); if (!ucounts) goto fail; /* * Verify that we can not violate the policy of which files * may be accessed that is specified by the root directory, * by verifing that the root directory is at the root of the * mount namespace which allows all files to be accessed. */ ret = -EPERM; if (current_chrooted()) goto fail_dec; /* The creator needs a mapping in the parent user namespace * or else we won't be able to reasonably tell userspace who * created a user_namespace. */ ret = -EPERM; if (!kuid_has_mapping(parent_ns, owner) || !kgid_has_mapping(parent_ns, group)) goto fail_dec; ret = -ENOMEM; ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL); if (!ns) goto fail_dec; ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP); ret = ns_alloc_inum(&ns->ns); if (ret) goto fail_free; ns->ns.ops = &userns_operations; atomic_set(&ns->count, 1); /* Leave the new->user_ns reference with the new user namespace. */ ns->parent = parent_ns; ns->level = parent_ns->level + 1; ns->owner = owner; ns->group = group; INIT_WORK(&ns->work, free_user_ns); for (i = 0; i < UCOUNT_COUNTS; i++) { ns->ucount_max[i] = INT_MAX; } ns->ucounts = ucounts; /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ mutex_lock(&userns_state_mutex); ns->flags = parent_ns->flags; mutex_unlock(&userns_state_mutex); #ifdef CONFIG_KEYS INIT_LIST_HEAD(&ns->keyring_name_list); init_rwsem(&ns->keyring_sem); #endif ret = -ENOMEM; if (!setup_userns_sysctls(ns)) goto fail_keyring; set_cred_user_ns(new, ns); return 0; fail_keyring: #ifdef CONFIG_PERSISTENT_KEYRINGS key_put(ns->persistent_keyring_register); #endif ns_free_inum(&ns->ns); fail_free: kmem_cache_free(user_ns_cachep, ns); fail_dec: dec_user_namespaces(ucounts); fail: return ret; } int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { struct cred *cred; int err = -ENOMEM; if (!(unshare_flags & CLONE_NEWUSER)) return 0; cred = prepare_creds(); if (cred) { err = create_user_ns(cred); if (err) put_cred(cred); else *new_cred = cred; } return err; } static void free_user_ns(struct work_struct *work) { struct user_namespace *parent, *ns = container_of(work, struct user_namespace, work); do { struct ucounts *ucounts = ns->ucounts; parent = ns->parent; if (ns->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->gid_map.forward); kfree(ns->gid_map.reverse); } if (ns->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->uid_map.forward); kfree(ns->uid_map.reverse); } if (ns->projid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->projid_map.forward); kfree(ns->projid_map.reverse); } retire_userns_sysctls(ns); key_free_user_ns(ns); ns_free_inum(&ns->ns); kmem_cache_free(user_ns_cachep, ns); dec_user_namespaces(ucounts); ns = parent; } while (atomic_dec_and_test(&parent->count)); } void __put_user_ns(struct user_namespace *ns) { schedule_work(&ns->work); } EXPORT_SYMBOL(__put_user_ns); /** * idmap_key struct holds the information necessary to find an idmapping in a * sorted idmap array. It is passed to cmp_map_id() as first argument. */ struct idmap_key { bool map_up; /* true -> id from kid; false -> kid from id */ u32 id; /* id to find */ u32 count; /* == 0 unless used with map_id_range_down() */ }; /** * cmp_map_id - Function to be passed to bsearch() to find the requested * idmapping. Expects struct idmap_key to be passed via @k. */ static int cmp_map_id(const void *k, const void *e) { u32 first, last, id2; const struct idmap_key *key = k; const struct uid_gid_extent *el = e; id2 = key->id + key->count - 1; /* handle map_id_{down,up}() */ if (key->map_up) first = el->lower_first; else first = el->first; last = first + el->count - 1; if (key->id >= first && key->id <= last && (id2 >= first && id2 <= last)) return 0; if (key->id < first || id2 < first) return -1; return 1; } /** * map_id_range_down_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { struct idmap_key key; key.map_up = false; key.count = count; key.id = id; return bsearch(&key, map->forward, extents, sizeof(struct uid_gid_extent), cmp_map_id); } /** * map_id_range_down_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_base(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { unsigned idx; u32 first, last, id2; id2 = id + count - 1; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last && (id2 >= first && id2 <= last)) return &map->extent[idx]; } return NULL; } static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_range_down_base(extents, map, id, count); else extent = map_id_range_down_max(extents, map, id, count); /* Map the id or note failure */ if (extent) id = (id - extent->first) + extent->lower_first; else id = (u32) -1; return id; } static u32 map_id_down(struct uid_gid_map *map, u32 id) { return map_id_range_down(map, id, 1); } /** * map_id_up_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_up_base(unsigned extents, struct uid_gid_map *map, u32 id) { unsigned idx; u32 first, last; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].lower_first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last) return &map->extent[idx]; } return NULL; } /** * map_id_up_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_up_max(unsigned extents, struct uid_gid_map *map, u32 id) { struct idmap_key key; key.map_up = true; key.count = 1; key.id = id; return bsearch(&key, map->reverse, extents, sizeof(struct uid_gid_extent), cmp_map_id); } static u32 map_id_up(struct uid_gid_map *map, u32 id) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_up_base(extents, map, id); else extent = map_id_up_max(extents, map, id); /* Map the id or note failure */ if (extent) id = (id - extent->lower_first) + extent->first; else id = (u32) -1; return id; } /** * make_kuid - Map a user-namespace uid pair into a kuid. * @ns: User namespace that the uid is in * @uid: User identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace uid * pair INVALID_UID is returned. Callers are expected to test * for and handle INVALID_UID being returned. INVALID_UID * may be tested for using uid_valid(). */ kuid_t make_kuid(struct user_namespace *ns, uid_t uid) { /* Map the uid to a global kernel uid */ return KUIDT_INIT(map_id_down(&ns->uid_map, uid)); } EXPORT_SYMBOL(make_kuid); /** * from_kuid - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * If @kuid has no mapping in @targ (uid_t)-1 is returned. */ uid_t from_kuid(struct user_namespace *targ, kuid_t kuid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->uid_map, __kuid_val(kuid)); } EXPORT_SYMBOL(from_kuid); /** * from_kuid_munged - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kuid from_kuid_munged never fails and always * returns a valid uid. This makes from_kuid_munged appropriate * for use in syscalls like stat and getuid where failing the * system call and failing to provide a valid uid are not an * options. * * If @kuid has no mapping in @targ overflowuid is returned. */ uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid) { uid_t uid; uid = from_kuid(targ, kuid); if (uid == (uid_t) -1) uid = overflowuid; return uid; } EXPORT_SYMBOL(from_kuid_munged); /** * make_kgid - Map a user-namespace gid pair into a kgid. * @ns: User namespace that the gid is in * @gid: group identifier * * Maps a user-namespace gid pair into a kernel internal kgid, * and returns that kgid. * * When there is no mapping defined for the user-namespace gid * pair INVALID_GID is returned. Callers are expected to test * for and handle INVALID_GID being returned. INVALID_GID may be * tested for using gid_valid(). */ kgid_t make_kgid(struct user_namespace *ns, gid_t gid) { /* Map the gid to a global kernel gid */ return KGIDT_INIT(map_id_down(&ns->gid_map, gid)); } EXPORT_SYMBOL(make_kgid); /** * from_kgid - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * If @kgid has no mapping in @targ (gid_t)-1 is returned. */ gid_t from_kgid(struct user_namespace *targ, kgid_t kgid) { /* Map the gid from a global kernel gid */ return map_id_up(&targ->gid_map, __kgid_val(kgid)); } EXPORT_SYMBOL(from_kgid); /** * from_kgid_munged - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kgid from_kgid_munged never fails and always * returns a valid gid. This makes from_kgid_munged appropriate * for use in syscalls like stat and getgid where failing the * system call and failing to provide a valid gid are not options. * * If @kgid has no mapping in @targ overflowgid is returned. */ gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid) { gid_t gid; gid = from_kgid(targ, kgid); if (gid == (gid_t) -1) gid = overflowgid; return gid; } EXPORT_SYMBOL(from_kgid_munged); /** * make_kprojid - Map a user-namespace projid pair into a kprojid. * @ns: User namespace that the projid is in * @projid: Project identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace projid * pair INVALID_PROJID is returned. Callers are expected to test * for and handle INVALID_PROJID being returned. INVALID_PROJID * may be tested for using projid_valid(). */ kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid) { /* Map the uid to a global kernel uid */ return KPROJIDT_INIT(map_id_down(&ns->projid_map, projid)); } EXPORT_SYMBOL(make_kprojid); /** * from_kprojid - Create a projid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal project identifier to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * If @kprojid has no mapping in @targ (projid_t)-1 is returned. */ projid_t from_kprojid(struct user_namespace *targ, kprojid_t kprojid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->projid_map, __kprojid_val(kprojid)); } EXPORT_SYMBOL(from_kprojid); /** * from_kprojid_munged - Create a projiid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal projid to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kprojid from_kprojid_munged never fails and always * returns a valid projid. This makes from_kprojid_munged * appropriate for use in syscalls like stat and where * failing the system call and failing to provide a valid projid are * not an options. * * If @kprojid has no mapping in @targ OVERFLOW_PROJID is returned. */ projid_t from_kprojid_munged(struct user_namespace *targ, kprojid_t kprojid) { projid_t projid; projid = from_kprojid(targ, kprojid); if (projid == (projid_t) -1) projid = OVERFLOW_PROJID; return projid; } EXPORT_SYMBOL(from_kprojid_munged); static int uid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; uid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int gid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; gid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int projid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; projid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kprojid(lower_ns, KPROJIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map) { loff_t pos = *ppos; unsigned extents = map->nr_extents; smp_rmb(); if (pos >= extents) return NULL; if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return &map->extent[pos]; return &map->forward[pos]; } static void *uid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->uid_map); } static void *gid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->gid_map); } static void *projid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->projid_map); } static void *m_next(struct seq_file *seq, void *v, loff_t *pos) { (*pos)++; return seq->op->start(seq, pos); } static void m_stop(struct seq_file *seq, void *v) { return; } const struct seq_operations proc_uid_seq_operations = { .start = uid_m_start, .stop = m_stop, .next = m_next, .show = uid_m_show, }; const struct seq_operations proc_gid_seq_operations = { .start = gid_m_start, .stop = m_stop, .next = m_next, .show = gid_m_show, }; const struct seq_operations proc_projid_seq_operations = { .start = projid_m_start, .stop = m_stop, .next = m_next, .show = projid_m_show, }; static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent *extent) { u32 upper_first, lower_first, upper_last, lower_last; unsigned idx; upper_first = extent->first; lower_first = extent->lower_first; upper_last = upper_first + extent->count - 1; lower_last = lower_first + extent->count - 1; for (idx = 0; idx < new_map->nr_extents; idx++) { u32 prev_upper_first, prev_lower_first; u32 prev_upper_last, prev_lower_last; struct uid_gid_extent *prev; if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) prev = &new_map->extent[idx]; else prev = &new_map->forward[idx]; prev_upper_first = prev->first; prev_lower_first = prev->lower_first; prev_upper_last = prev_upper_first + prev->count - 1; prev_lower_last = prev_lower_first + prev->count - 1; /* Does the upper range intersect a previous extent? */ if ((prev_upper_first <= upper_last) && (prev_upper_last >= upper_first)) return true; /* Does the lower range intersect a previous extent? */ if ((prev_lower_first <= lower_last) && (prev_lower_last >= lower_first)) return true; } return false; } /** * insert_extent - Safely insert a new idmap extent into struct uid_gid_map. * Takes care to allocate a 4K block of memory if the number of mappings exceeds * UID_GID_MAP_MAX_BASE_EXTENTS. */ static int insert_extent(struct uid_gid_map *map, struct uid_gid_extent *extent) { struct uid_gid_extent *dest; if (map->nr_extents == UID_GID_MAP_MAX_BASE_EXTENTS) { struct uid_gid_extent *forward; /* Allocate memory for 340 mappings. */ forward = kmalloc_array(UID_GID_MAP_MAX_EXTENTS, sizeof(struct uid_gid_extent), GFP_KERNEL); if (!forward) return -ENOMEM; /* Copy over memory. Only set up memory for the forward pointer. * Defer the memory setup for the reverse pointer. */ memcpy(forward, map->extent, map->nr_extents * sizeof(map->extent[0])); map->forward = forward; map->reverse = NULL; } if (map->nr_extents < UID_GID_MAP_MAX_BASE_EXTENTS) dest = &map->extent[map->nr_extents]; else dest = &map->forward[map->nr_extents]; *dest = *extent; map->nr_extents++; return 0; } /* cmp function to sort() forward mappings */ static int cmp_extents_forward(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->first < e2->first) return -1; if (e1->first > e2->first) return 1; return 0; } /* cmp function to sort() reverse mappings */ static int cmp_extents_reverse(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->lower_first < e2->lower_first) return -1; if (e1->lower_first > e2->lower_first) return 1; return 0; } /** * sort_idmaps - Sorts an array of idmap entries. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static int sort_idmaps(struct uid_gid_map *map) { if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return 0; /* Sort forward array. */ sort(map->forward, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_forward, NULL); /* Only copy the memory from forward we actually need. */ map->reverse = kmemdup(map->forward, map->nr_extents * sizeof(struct uid_gid_extent), GFP_KERNEL); if (!map->reverse) return -ENOMEM; /* Sort reverse array. */ sort(map->reverse, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_reverse, NULL); return 0; } /** * verify_root_map() - check the uid 0 mapping * @file: idmapping file * @map_ns: user namespace of the target process * @new_map: requested idmap * * If a process requests mapping parent uid 0 into the new ns, verify that the * process writing the map had the CAP_SETFCAP capability as the target process * will be able to write fscaps that are valid in ancestor user namespaces. * * Return: true if the mapping is allowed, false if not. */ static bool verify_root_map(const struct file *file, struct user_namespace *map_ns, struct uid_gid_map *new_map) { int idx; const struct user_namespace *file_ns = file->f_cred->user_ns; struct uid_gid_extent *extent0 = NULL; for (idx = 0; idx < new_map->nr_extents; idx++) { if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent0 = &new_map->extent[idx]; else extent0 = &new_map->forward[idx]; if (extent0->lower_first == 0) break; extent0 = NULL; } if (!extent0) return true; if (map_ns == file_ns) { /* The process unshared its ns and is writing to its own * /proc/self/uid_map. User already has full capabilites in * the new namespace. Verify that the parent had CAP_SETFCAP * when it unshared. * */ if (!file_ns->parent_could_setfcap) return false; } else { /* Process p1 is writing to uid_map of p2, who is in a child * user namespace to p1's. Verify that the opener of the map * file has CAP_SETFCAP against the parent of the new map * namespace */ if (!file_ns_capable(file, map_ns->parent, CAP_SETFCAP)) return false; } return true; } static ssize_t map_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos, int cap_setid, struct uid_gid_map *map, struct uid_gid_map *parent_map) { struct seq_file *seq = file->private_data; struct user_namespace *map_ns = seq->private; struct uid_gid_map new_map; unsigned idx; struct uid_gid_extent extent; char *kbuf = NULL, *pos, *next_line; ssize_t ret; /* Only allow < page size writes at the beginning of the file */ if ((*ppos != 0) || (count >= PAGE_SIZE)) return -EINVAL; /* Slurp in the user data */ kbuf = memdup_user_nul(buf, count); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); /* * The userns_state_mutex serializes all writes to any given map. * * Any map is only ever written once. * * An id map fits within 1 cache line on most architectures. * * On read nothing needs to be done unless you are on an * architecture with a crazy cache coherency model like alpha. * * There is a one time data dependency between reading the * count of the extents and the values of the extents. The * desired behavior is to see the values of the extents that * were written before the count of the extents. * * To achieve this smp_wmb() is used on guarantee the write * order and smp_rmb() is guaranteed that we don't have crazy * architectures returning stale data. */ mutex_lock(&userns_state_mutex); memset(&new_map, 0, sizeof(struct uid_gid_map)); ret = -EPERM; /* Only allow one successful write to the map */ if (map->nr_extents != 0) goto out; /* * Adjusting namespace settings requires capabilities on the target. */ if (cap_valid(cap_setid) && !file_ns_capable(file, map_ns, CAP_SYS_ADMIN)) goto out; /* Parse the user data */ ret = -EINVAL; pos = kbuf; for (; pos; pos = next_line) { /* Find the end of line and ensure I don't look past it */ next_line = strchr(pos, '\n'); if (next_line) { *next_line = '\0'; next_line++; if (*next_line == '\0') next_line = NULL; } pos = skip_spaces(pos); extent.first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.lower_first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.count = simple_strtoul(pos, &pos, 10); if (*pos && !isspace(*pos)) goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; /* Verify we have been given valid starting values */ if ((extent.first == (u32) -1) || (extent.lower_first == (u32) -1)) goto out; /* Verify count is not zero and does not cause the * extent to wrap */ if ((extent.first + extent.count) <= extent.first) goto out; if ((extent.lower_first + extent.count) <= extent.lower_first) goto out; /* Do the ranges in extent overlap any previous extents? */ if (mappings_overlap(&new_map, &extent)) goto out; if ((new_map.nr_extents + 1) == UID_GID_MAP_MAX_EXTENTS && (next_line != NULL)) goto out; ret = insert_extent(&new_map, &extent); if (ret < 0) goto out; ret = -EINVAL; } /* Be very certaint the new map actually exists */ if (new_map.nr_extents == 0) goto out; ret = -EPERM; /* Validate the user is allowed to use user id's mapped to. */ if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map)) goto out; ret = -EPERM; /* Map the lower ids from the parent user namespace to the * kernel global id space. */ for (idx = 0; idx < new_map.nr_extents; idx++) { struct uid_gid_extent *e; u32 lower_first; if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) e = &new_map.extent[idx]; else e = &new_map.forward[idx]; lower_first = map_id_range_down(parent_map, e->lower_first, e->count); /* Fail if we can not map the specified extent to * the kernel global id space. */ if (lower_first == (u32) -1) goto out; e->lower_first = lower_first; } /* * If we want to use binary search for lookup, this clones the extent * array and sorts both copies. */ ret = sort_idmaps(&new_map); if (ret < 0) goto out; /* Install the map */ if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { memcpy(map->extent, new_map.extent, new_map.nr_extents * sizeof(new_map.extent[0])); } else { map->forward = new_map.forward; map->reverse = new_map.reverse; } smp_wmb(); map->nr_extents = new_map.nr_extents; *ppos = count; ret = count; out: if (ret < 0 && new_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(new_map.forward); kfree(new_map.reverse); map->forward = NULL; map->reverse = NULL; map->nr_extents = 0; } mutex_unlock(&userns_state_mutex); kfree(kbuf); return ret; } ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETUID, &ns->uid_map, &ns->parent->uid_map); } ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETGID, &ns->gid_map, &ns->parent->gid_map); } ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; /* Anyone can set any valid project id no capability needed */ return map_write(file, buf, size, ppos, -1, &ns->projid_map, &ns->parent->projid_map); } static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { const struct cred *cred = file->f_cred; if (cap_setid == CAP_SETUID && !verify_root_map(file, ns, new_map)) return false; /* Don't allow mappings that would allow anything that wouldn't * be allowed without the establishment of unprivileged mappings. */ if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && uid_eq(ns->owner, cred->euid)) { u32 id = new_map->extent[0].lower_first; if (cap_setid == CAP_SETUID) { kuid_t uid = make_kuid(ns->parent, id); if (uid_eq(uid, cred->euid)) return true; } else if (cap_setid == CAP_SETGID) { kgid_t gid = make_kgid(ns->parent, id); if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) && gid_eq(gid, cred->egid)) return true; } } /* Allow anyone to set a mapping that doesn't require privilege */ if (!cap_valid(cap_setid)) return true; /* Allow the specified ids if we have the appropriate capability * (CAP_SETUID or CAP_SETGID) over the parent user namespace. * And the opener of the id file also had the approprpiate capability. */ if (ns_capable(ns->parent, cap_setid) && file_ns_capable(file, ns->parent, cap_setid)) return true; return false; } int proc_setgroups_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; unsigned long userns_flags = READ_ONCE(ns->flags); seq_printf(seq, "%s\n", (userns_flags & USERNS_SETGROUPS_ALLOWED) ? "allow" : "deny"); return 0; } ssize_t proc_setgroups_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; char kbuf[8], *pos; bool setgroups_allowed; ssize_t ret; /* Only allow a very narrow range of strings to be written */ ret = -EINVAL; if ((*ppos != 0) || (count >= sizeof(kbuf))) goto out; /* What was written? */ ret = -EFAULT; if (copy_from_user(kbuf, buf, count)) goto out; kbuf[count] = '\0'; pos = kbuf; /* What is being requested? */ ret = -EINVAL; if (strncmp(pos, "allow", 5) == 0) { pos += 5; setgroups_allowed = true; } else if (strncmp(pos, "deny", 4) == 0) { pos += 4; setgroups_allowed = false; } else goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; ret = -EPERM; mutex_lock(&userns_state_mutex); if (setgroups_allowed) { /* Enabling setgroups after setgroups has been disabled * is not allowed. */ if (!(ns->flags & USERNS_SETGROUPS_ALLOWED)) goto out_unlock; } else { /* Permanently disabling setgroups after setgroups has * been enabled by writing the gid_map is not allowed. */ if (ns->gid_map.nr_extents != 0) goto out_unlock; ns->flags &= ~USERNS_SETGROUPS_ALLOWED; } mutex_unlock(&userns_state_mutex); /* Report a successful write */ *ppos = count; ret = count; out: return ret; out_unlock: mutex_unlock(&userns_state_mutex); goto out; } bool userns_may_setgroups(const struct user_namespace *ns) { bool allowed; mutex_lock(&userns_state_mutex); /* It is not safe to use setgroups until a gid mapping in * the user namespace has been established. */ allowed = ns->gid_map.nr_extents != 0; /* Is setgroups allowed? */ allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED); mutex_unlock(&userns_state_mutex); return allowed; } /* * Returns true if @child is the same namespace or a descendant of * @ancestor. */ bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { const struct user_namespace *ns; for (ns = child; ns->level > ancestor->level; ns = ns->parent) ; return (ns == ancestor); } bool current_in_userns(const struct user_namespace *target_ns) { return in_userns(target_ns, current_user_ns()); } EXPORT_SYMBOL(current_in_userns); static inline struct user_namespace *to_user_ns(struct ns_common *ns) { return container_of(ns, struct user_namespace, ns); } static struct ns_common *userns_get(struct task_struct *task) { struct user_namespace *user_ns; rcu_read_lock(); user_ns = get_user_ns(__task_cred(task)->user_ns); rcu_read_unlock(); return user_ns ? &user_ns->ns : NULL; } static void userns_put(struct ns_common *ns) { put_user_ns(to_user_ns(ns)); } static int userns_install(struct nsset *nsset, struct ns_common *ns) { struct user_namespace *user_ns = to_user_ns(ns); struct cred *cred; /* Don't allow gaining capabilities by reentering * the same user namespace. */ if (user_ns == current_user_ns()) return -EINVAL; /* Tasks that share a thread group must share a user namespace */ if (!thread_group_empty(current)) return -EINVAL; if (current->fs->users != 1) return -EINVAL; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; cred = nsset_cred(nsset); if (!cred) return -EINVAL; put_user_ns(cred->user_ns); set_cred_user_ns(cred, get_user_ns(user_ns)); return 0; } struct ns_common *ns_get_owner(struct ns_common *ns) { struct user_namespace *my_user_ns = current_user_ns(); struct user_namespace *owner, *p; /* See if the owner is in the current user namespace */ owner = p = ns->ops->owner(ns); for (;;) { if (!p) return ERR_PTR(-EPERM); if (p == my_user_ns) break; p = p->parent; } return &get_user_ns(owner)->ns; } static struct user_namespace *userns_owner(struct ns_common *ns) { return to_user_ns(ns)->parent; } const struct proc_ns_operations userns_operations = { .name = "user", .type = CLONE_NEWUSER, .get = userns_get, .put = userns_put, .install = userns_install, .owner = userns_owner, .get_parent = ns_get_owner, }; static __init int user_namespaces_init(void) { user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC); return 0; } subsys_initcall(user_namespaces_init); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CURRENT_H #define _ASM_X86_CURRENT_H #include <linux/compiler.h> #include <asm/percpu.h> #ifndef __ASSEMBLY__ struct task_struct; DECLARE_PER_CPU(struct task_struct *, current_task); static __always_inline struct task_struct *get_current(void) { return this_cpu_read_stable(current_task); } #define current get_current() #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_CURRENT_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: mm/ internal definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/tracepoint-defs.h> /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_ATOMIC) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation cpuset and node placement constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) void page_writeback_init(void); /* * This is a file-backed mapping, and is about to be memory mapped - invoke its * mmap hook and safely handle error conditions. On error, VMA hooks will be * mutated. * * @file: File which backs the mapping. * @vma: VMA which we are mapping. * * Returns: 0 if success, error otherwise. */ int mmap_file(struct file *file, struct vm_area_struct *vma); /* * If the VMA has a close hook then close it, and since closing it might leave * it in an inconsistent state which makes the use of any hooks suspect, clear * them down by installing dummy empty hooks. */ void vma_close(struct vm_area_struct *vma); vm_fault_t do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)); } void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); void do_page_cache_ra(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_size); void force_page_cache_ra(struct readahead_control *, struct file_ra_state *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) { DEFINE_READAHEAD(ractl, file, mapping, index); force_page_cache_ra(&ractl, &file->f_ra, nr_to_read); } struct page *find_get_entry(struct address_space *mapping, pgoff_t index); struct page *find_lock_entry(struct address_space *mapping, pgoff_t index); /** * page_evictable - test whether a page is evictable * @page: the page to test * * Test whether page is evictable--i.e., should be placed on active/inactive * lists vs unevictable list. * * Reasons page might not be evictable: * (1) page's mapping marked unevictable * (2) page is part of an mlocked VMA * */ static inline bool page_evictable(struct page *page) { bool ret; /* Prevent address_space of inode and swap cache from being freed */ rcu_read_lock(); ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page); rcu_read_unlock(); return ret; } /* * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1); } extern unsigned long highest_memmap_pfn; /* * Maximum number of reclaim retries without progress before the OOM * killer is consider the only way forward. */ #define MAX_RECLAIM_RETRIES 16 /* * in mm/vmscan.c: */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); /* * in mm/rmap.c: */ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/page_alloc.c */ /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* * family of functions. * * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages_nodemask() and then never change. * * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages_nodemask() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole structure * by a const pointer. */ struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; /* * highest_zoneidx represents highest usable zone index of * the allocation request. Due to the nature of the zone, * memory on lower zone than the highest_zoneidx will be * protected by lowmem_reserve[highest_zoneidx]. * * highest_zoneidx is also used by reclaim/compaction to limit * the target zone since higher zone than this index cannot be * usable for this allocation request. */ enum zone_type highest_zoneidx; bool spread_dirty_pages; }; /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * * 1) Any buddy B1 will have an order O twin B2 which satisfies * the following equation: * B2 = B1 ^ (1 << O) * For example, if the starting buddy (buddy2) is #8 its order * 1 buddy is #10: * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 * * 2) Any buddy B will have an order O+1 parent P which * satisfies the following equation: * P = B & ~(1 << O) * * Assumption: *_mem_map is contiguous at least up to MAX_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) { return page_pfn ^ (1 << order); } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) { if (zone->contiguous) return pfn_to_page(start_pfn); return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } extern int __isolate_free_page(struct page *page, unsigned int order); extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order); extern void prep_compound_page(struct page *page, unsigned int order); extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern int user_min_free_kbytes; extern void zone_pcp_update(struct zone *zone); extern void zone_pcp_reset(struct zone *zone); #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* * in mm/compaction.c */ /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts * at the end of a zone and migrate_pfn begins at the start. Movable pages * are moved to the end of a zone during a compaction run and the run * completes when free_pfn <= migrate_pfn */ struct compact_control { struct list_head freepages; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; unsigned short fast_search_fail;/* failures to use free list searches */ short search_order; /* order to start a fast search at */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock or sched contention */ bool rescan; /* Rescanning the same pageblock */ bool alloc_contig; /* alloc_contig_range allocation */ }; /* * Used in direct compaction when a page should be taken from the freelists * immediately when one is created during the free path. */ struct capture_control { struct compact_control *cc; struct page *page; }; unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); unsigned long isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); #endif /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the * page from being allocated in parallel and returning garbage as the order. * If a caller does not hold page_zone(page)->lock, it must guarantee that the * page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use buddy_order_unsafe() below. */ static inline unsigned int buddy_order(struct page *page) { /* PageBuddy() must be checked by the caller */ return page_private(page); } /* * Like buddy_order(), but for callers who cannot afford to hold the zone lock. * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) static inline bool is_cow_mapping(vm_flags_t flags) { return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } /* * These three helpers classifies VMAs for virtual memory accounting. */ /* * Executable code area - executable, not writable, not stack */ static inline bool is_exec_mapping(vm_flags_t flags) { return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; } /* * Stack area - atomatically grows in one direction * * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: * do_mmap() forbids all other combinations. */ static inline bool is_stack_mapping(vm_flags_t flags) { return (flags & VM_STACK) == VM_STACK; } /* * Data area - private, writable, not stack */ static inline bool is_data_mapping(vm_flags_t flags) { return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; } /* mm/util.c */ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev); void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma); #ifdef CONFIG_MMU extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *nonblocking); extern void munlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); static inline void munlock_vma_pages_all(struct vm_area_struct *vma) { munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end); } /* * must be called with vma's mmap_lock held for read or write, and page locked. */ extern void mlock_vma_page(struct page *page); extern unsigned int munlock_vma_page(struct page *page); /* * Clear the page's PageMlocked(). This can be useful in a situation where * we want to unconditionally remove a page from the pagecache -- e.g., * on truncation or freeing. * * It is legal to call this function for any page, mlocked or not. * If called for a page that is still mapped by mlocked vmas, all we do * is revert to lazy LRU behaviour -- semantics are not broken. */ extern void clear_page_mlock(struct page *page); /* * mlock_migrate_page - called only from migrate_misplaced_transhuge_page() * (because that does not go through the full procedure of migration ptes): * to migrate the Mlocked page flag; update statistics. */ static inline void mlock_migrate_page(struct page *newpage, struct page *page) { if (TestClearPageMlocked(page)) { int nr_pages = thp_nr_pages(page); /* Holding pmd lock, no change in irq context: __mod is safe */ __mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); SetPageMlocked(newpage); __mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages); } } extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /* * At what user virtual address is page expected in vma? * Returns -EFAULT if all of the page is outside the range of vma. * If page is a compound head, the entire compound page is considered. */ static inline unsigned long vma_address(struct page *page, struct vm_area_struct *vma) { pgoff_t pgoff; unsigned long address; VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ pgoff = page_to_pgoff(page); if (pgoff >= vma->vm_pgoff) { address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address >= vma->vm_end) address = -EFAULT; } else if (PageHead(page) && pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) { /* Test above avoids possibility of wrap to 0 on 32-bit */ address = vma->vm_start; } else { address = -EFAULT; } return address; } /* * Then at what user virtual address will none of the page be found in vma? * Assumes that vma_address() already returned a good starting address. * If page is a compound head, the entire compound page is considered. */ static inline unsigned long vma_address_end(struct page *page, struct vm_area_struct *vma) { pgoff_t pgoff; unsigned long address; VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ pgoff = page_to_pgoff(page) + compound_nr(page); address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address > vma->vm_end) address = vma->vm_end; return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, struct file *fpin) { int flags = vmf->flags; if (fpin) return fpin; /* * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or * anything, so we only pin the file and drop the mmap_lock if only * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt. */ if (fault_flag_allow_retry_first(flags) && !(flags & FAULT_FLAG_RETRY_NOWAIT)) { fpin = get_file(vmf->vma->vm_file); mmap_read_unlock(vmf->vma->vm_mm); } return fpin; } #else /* !CONFIG_MMU */ static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } static inline void mlock_migrate_page(struct page *new, struct page *old) { } #endif /* !CONFIG_MMU */ /* * Return the mem_map entry representing the 'offset' subpage within * the maximally aligned gigantic page 'base'. Handle any discontiguity * in the mem_map at MAX_ORDER_NR_PAGES boundaries. */ static inline struct page *mem_map_offset(struct page *base, int offset) { if (unlikely(offset >= MAX_ORDER_NR_PAGES)) return nth_page(base, offset); return base + offset; } /* * Iterator over all subpages within the maximally aligned gigantic * page 'base'. Handle any discontiguity in the mem_map. */ static inline struct page *mem_map_next(struct page *iter, struct page *base, int offset) { if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) { unsigned long pfn = page_to_pfn(base) + offset; if (!pfn_valid(pfn)) return NULL; return pfn_to_page(pfn); } return iter + 1; } /* Memory initialisation debug and verification */ enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, MMINIT_TRACE }; #ifdef CONFIG_DEBUG_MEMORY_INIT extern int mminit_loglevel; #define mminit_dprintk(level, prefix, fmt, arg...) \ do { \ if (level < mminit_loglevel) { \ if (level <= MMINIT_WARNING) \ pr_warn("mminit::" prefix " " fmt, ##arg); \ else \ printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ } \ } while (0) extern void mminit_verify_pageflags_layout(void); extern void mminit_verify_zonelist(void); #else static inline void mminit_dprintk(enum mminit_level level, const char *prefix, const char *fmt, ...) { } static inline void mminit_verify_pageflags_layout(void) { } static inline void mminit_verify_zonelist(void) { } #endif /* CONFIG_DEBUG_MEMORY_INIT */ /* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */ #if defined(CONFIG_SPARSEMEM) extern void mminit_validate_memmodel_limits(unsigned long *start_pfn, unsigned long *end_pfn); #else static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn, unsigned long *end_pfn) { } #endif /* CONFIG_SPARSEMEM */ #define NODE_RECLAIM_NOSCAN -2 #define NODE_RECLAIM_FULL -1 #define NODE_RECLAIM_SOME 0 #define NODE_RECLAIM_SUCCESS 1 #ifdef CONFIG_NUMA extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); #else static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, unsigned int order) { return NODE_RECLAIM_NOSCAN; } #endif extern int hwpoison_filter(struct page *p); extern u32 hwpoison_filter_dev_major; extern u32 hwpoison_filter_dev_minor; extern u64 hwpoison_filter_flags_mask; extern u64 hwpoison_filter_flags_value; extern u64 hwpoison_filter_memcg; extern u32 hwpoison_filter_enable; extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern void set_pageblock_order(void); unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *page_list); /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW #define ALLOC_WMARK_HIGH WMARK_HIGH #define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ /* Mask to get the watermark bits */ #define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) /* * Only MMU archs have async oom victim reclaim - aka oom_reaper so we * cannot assume a reduced access to memory reserves is sufficient for * !MMU */ #ifdef CONFIG_MMU #define ALLOC_OOM 0x08 #else #define ALLOC_OOM ALLOC_NO_WATERMARKS #endif #define ALLOC_HARDER 0x10 /* try to alloc harder */ #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ #ifdef CONFIG_ZONE_DMA32 #define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */ #else #define ALLOC_NOFRAGMENT 0x0 #endif #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ enum ttu_flags; struct tlbflush_unmap_batch; /* * only for MM internal work items which do not depend on * any allocations or locks which might depend on allocations */ extern struct workqueue_struct *mm_percpu_wq; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { } static inline void try_to_unmap_flush_dirty(void) { } static inline void flush_tlb_batched_pending(struct mm_struct *mm) { } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; static inline bool is_migrate_highatomic(enum migratetype migratetype) { return migratetype == MIGRATE_HIGHATOMIC; } static inline bool is_migrate_highatomic_page(struct page *page) { return get_pageblock_migratetype(page) == MIGRATE_HIGHATOMIC; } void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; }; #endif /* __MM_INTERNAL_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X86_IRQFLAGS_H_ #define _X86_IRQFLAGS_H_ #include <asm/processor-flags.h> #ifndef __ASSEMBLY__ #include <asm/nospec-branch.h> /* Provide __cpuidle; we can't safely include <linux/cpu.h> */ #define __cpuidle __section(".cpuidle.text") /* * Interrupt control: */ /* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */ extern inline unsigned long native_save_fl(void); extern __always_inline unsigned long native_save_fl(void) { unsigned long flags; /* * "=rm" is safe here, because "pop" adjusts the stack before * it evaluates its effective address -- this is part of the * documented behavior of the "pop" instruction. */ asm volatile("# __raw_save_flags\n\t" "pushf ; pop %0" : "=rm" (flags) : /* no input */ : "memory"); return flags; } extern inline void native_restore_fl(unsigned long flags); extern inline void native_restore_fl(unsigned long flags) { asm volatile("push %0 ; popf" : /* no output */ :"g" (flags) :"memory", "cc"); } static __always_inline void native_irq_disable(void) { asm volatile("cli": : :"memory"); } static __always_inline void native_irq_enable(void) { asm volatile("sti": : :"memory"); } static inline __cpuidle void native_safe_halt(void) { x86_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } static inline __cpuidle void native_halt(void) { x86_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); } #endif #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #ifndef __ASSEMBLY__ #include <linux/types.h> static __always_inline unsigned long arch_local_save_flags(void) { return native_save_fl(); } static __always_inline void arch_local_irq_restore(unsigned long flags) { native_restore_fl(flags); } static __always_inline void arch_local_irq_disable(void) { native_irq_disable(); } static __always_inline void arch_local_irq_enable(void) { native_irq_enable(); } /* * Used in the idle loop; sti takes one instruction cycle * to complete: */ static inline __cpuidle void arch_safe_halt(void) { native_safe_halt(); } /* * Used when interrupts are already enabled or to * shutdown the processor: */ static inline __cpuidle void halt(void) { native_halt(); } /* * For spinlocks, etc: */ static __always_inline unsigned long arch_local_irq_save(void) { unsigned long flags = arch_local_save_flags(); arch_local_irq_disable(); return flags; } #else #define ENABLE_INTERRUPTS(x) sti #define DISABLE_INTERRUPTS(x) cli #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(x) pushfq; popq %rax #endif #define INTERRUPT_RETURN jmp native_iret #else #define INTERRUPT_RETURN iret #endif #endif /* __ASSEMBLY__ */ #endif /* CONFIG_PARAVIRT_XXL */ #ifndef __ASSEMBLY__ static __always_inline int arch_irqs_disabled_flags(unsigned long flags) { return !(flags & X86_EFLAGS_IF); } static __always_inline int arch_irqs_disabled(void) { unsigned long flags = arch_local_save_flags(); return arch_irqs_disabled_flags(flags); } #else #ifdef CONFIG_X86_64 #ifdef CONFIG_XEN_PV #define SWAPGS ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV #else #define SWAPGS swapgs #endif #endif #endif /* !__ASSEMBLY__ */ #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PTRACE_H #define _ASM_X86_PTRACE_H #include <asm/segment.h> #include <asm/page_types.h> #include <uapi/asm/ptrace.h> #ifndef __ASSEMBLY__ #ifdef __i386__ struct pt_regs { /* * NB: 32-bit x86 CPUs are inconsistent as what happens in the * following cases (where %seg represents a segment register): * * - pushl %seg: some do a 16-bit write and leave the high * bits alone * - movl %seg, [mem]: some do a 16-bit write despite the movl * - IDT entry: some (e.g. 486) will leave the high bits of CS * and (if applicable) SS undefined. * * Fortunately, x86-32 doesn't read the high bits on POP or IRET, * so we can just treat all of the segment registers as 16-bit * values. */ unsigned long bx; unsigned long cx; unsigned long dx; unsigned long si; unsigned long di; unsigned long bp; unsigned long ax; unsigned short ds; unsigned short __dsh; unsigned short es; unsigned short __esh; unsigned short fs; unsigned short __fsh; /* * On interrupt, gs and __gsh store the vector number. They never * store gs any more. */ unsigned short gs; unsigned short __gsh; /* On interrupt, this is the error code. */ unsigned long orig_ax; unsigned long ip; unsigned short cs; unsigned short __csh; unsigned long flags; unsigned long sp; unsigned short ss; unsigned short __ssh; }; #else /* __i386__ */ struct pt_regs { /* * C ABI says these regs are callee-preserved. They aren't saved on kernel entry * unless syscall needs a complete, fully filled "struct pt_regs". */ unsigned long r15; unsigned long r14; unsigned long r13; unsigned long r12; unsigned long bp; unsigned long bx; /* These regs are callee-clobbered. Always saved on kernel entry. */ unsigned long r11; unsigned long r10; unsigned long r9; unsigned long r8; unsigned long ax; unsigned long cx; unsigned long dx; unsigned long si; unsigned long di; /* * On syscall entry, this is syscall#. On CPU exception, this is error code. * On hw interrupt, it's IRQ number: */ unsigned long orig_ax; /* Return frame for iretq */ unsigned long ip; unsigned long cs; unsigned long flags; unsigned long sp; unsigned long ss; /* top of stack page */ }; #endif /* !__i386__ */ #ifdef CONFIG_PARAVIRT #include <asm/paravirt_types.h> #endif #include <asm/proto.h> struct cpuinfo_x86; struct task_struct; extern unsigned long profile_pc(struct pt_regs *regs); extern unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); extern void send_sigtrap(struct pt_regs *regs, int error_code, int si_code); static inline unsigned long regs_return_value(struct pt_regs *regs) { return regs->ax; } static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) { regs->ax = rc; } /* * user_mode(regs) determines whether a register set came from user * mode. On x86_32, this is true if V8086 mode was enabled OR if the * register set was from protected mode with RPL-3 CS value. This * tricky test checks that with one comparison. * * On x86_64, vm86 mode is mercifully nonexistent, and we don't need * the extra check. */ static __always_inline int user_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL; #else return !!(regs->cs & 3); #endif } static inline int v8086_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 return (regs->flags & X86_VM_MASK); #else return 0; /* No V86 mode support in long mode */ #endif } static inline bool user_64bit_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_64 #ifndef CONFIG_PARAVIRT_XXL /* * On non-paravirt systems, this is the only long mode CPL 3 * selector. We do not allow long mode selectors in the LDT. */ return regs->cs == __USER_CS; #else /* Headers are too twisted for this to go in paravirt.h. */ return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs; #endif #else /* !CONFIG_X86_64 */ return false; #endif } /* * Determine whether the register set came from any context that is running in * 64-bit mode. */ static inline bool any_64bit_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_64 return !user_mode(regs) || user_64bit_mode(regs); #else return false; #endif } #ifdef CONFIG_X86_64 #define current_user_stack_pointer() current_pt_regs()->sp #define compat_user_stack_pointer() current_pt_regs()->sp static inline bool ip_within_syscall_gap(struct pt_regs *regs) { bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 && regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack); #ifdef CONFIG_IA32_EMULATION ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat && regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack); #endif return ret; } #endif static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { return regs->sp; } static inline unsigned long instruction_pointer(struct pt_regs *regs) { return regs->ip; } static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->ip = val; } static inline unsigned long frame_pointer(struct pt_regs *regs) { return regs->bp; } static inline unsigned long user_stack_pointer(struct pt_regs *regs) { return regs->sp; } static inline void user_stack_pointer_set(struct pt_regs *regs, unsigned long val) { regs->sp = val; } static __always_inline bool regs_irqs_disabled(struct pt_regs *regs) { return !(regs->flags & X86_EFLAGS_IF); } /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); extern const char *regs_query_register_name(unsigned int offset); #define MAX_REG_OFFSET (offsetof(struct pt_regs, ss)) /** * regs_get_register() - get register value from its offset * @regs: pt_regs from which register value is gotten. * @offset: offset number of the register. * * regs_get_register returns the value of a register. The @offset is the * offset of the register in struct pt_regs address which specified by @regs. * If @offset is bigger than MAX_REG_OFFSET, this returns 0. */ static inline unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset) { if (unlikely(offset > MAX_REG_OFFSET)) return 0; #ifdef CONFIG_X86_32 /* The selector fields are 16-bit. */ if (offset == offsetof(struct pt_regs, cs) || offset == offsetof(struct pt_regs, ss) || offset == offsetof(struct pt_regs, ds) || offset == offsetof(struct pt_regs, es) || offset == offsetof(struct pt_regs, fs) || offset == offsetof(struct pt_regs, gs)) { return *(u16 *)((unsigned long)regs + offset); } #endif return *(unsigned long *)((unsigned long)regs + offset); } /** * regs_within_kernel_stack() - check the address in the stack * @regs: pt_regs which contains kernel stack pointer. * @addr: address which is checked. * * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). * If @addr is within the kernel stack, it returns true. If not, returns false. */ static inline int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { return ((addr & ~(THREAD_SIZE - 1)) == (regs->sp & ~(THREAD_SIZE - 1))); } /** * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns the address of the @n th entry of the * kernel stack which is specified by @regs. If the @n th entry is NOT in * the kernel stack, this returns NULL. */ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n) { unsigned long *addr = (unsigned long *)regs->sp; addr += n; if (regs_within_kernel_stack(regs, (unsigned long)addr)) return addr; else return NULL; } /* To avoid include hell, we can't include uaccess.h */ extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size); /** * regs_get_kernel_stack_nth() - get Nth entry of the stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which * is specified by @regs. If the @n th entry is NOT in the kernel stack * this returns 0. */ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long *addr; unsigned long val; long ret; addr = regs_get_kernel_stack_nth_addr(regs, n); if (addr) { ret = copy_from_kernel_nofault(&val, addr, sizeof(val)); if (!ret) return val; } return 0; } /** * regs_get_kernel_argument() - get Nth function argument in kernel * @regs: pt_regs of that context * @n: function argument number (start from 0) * * regs_get_argument() returns @n th argument of the function call. * Note that this chooses most probably assignment, in some case * it can be incorrect. * This is expected to be called from kprobes or ftrace with regs * where the top of stack is the return address. */ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, unsigned int n) { static const unsigned int argument_offs[] = { #ifdef __i386__ offsetof(struct pt_regs, ax), offsetof(struct pt_regs, dx), offsetof(struct pt_regs, cx), #define NR_REG_ARGUMENTS 3 #else offsetof(struct pt_regs, di), offsetof(struct pt_regs, si), offsetof(struct pt_regs, dx), offsetof(struct pt_regs, cx), offsetof(struct pt_regs, r8), offsetof(struct pt_regs, r9), #define NR_REG_ARGUMENTS 6 #endif }; if (n >= NR_REG_ARGUMENTS) { n -= NR_REG_ARGUMENTS - 1; return regs_get_kernel_stack_nth(regs, n); } else return regs_get_register(regs, argument_offs[n]); } #define arch_has_single_step() (1) #ifdef CONFIG_X86_DEBUGCTLMSR #define arch_has_block_step() (1) #else #define arch_has_block_step() (boot_cpu_data.x86 >= 6) #endif #define ARCH_HAS_USER_SINGLE_STEP_REPORT struct user_desc; extern int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *info); extern int do_set_thread_area(struct task_struct *p, int idx, struct user_desc __user *info, int can_allocate); #ifdef CONFIG_X86_64 # define do_set_thread_area_64(p, s, t) do_arch_prctl_64(p, s, t) #else # define do_set_thread_area_64(p, s, t) (0) #endif #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PTRACE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 | /* * kernel/cpuset.c * * Processor and Memory placement constraints for sets of tasks. * * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2007 Silicon Graphics, Inc. * Copyright (C) 2006 Google, Inc * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * 2006 Rework by Paul Menage to use generic cgroups * 2008 Rework of the scheduler domains and CPU hotplug handling * by Max Krasnyansky * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ #include "cgroup-internal.h" #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/cpuset.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/kthread.h> #include <linux/list.h> #include <linux/mempolicy.h> #include <linux/mm.h> #include <linux/memory.h> #include <linux/export.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/deadline.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/seq_file.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/time.h> #include <linux/time64.h> #include <linux/backing-dev.h> #include <linux/sort.h> #include <linux/oom.h> #include <linux/sched/isolation.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <linux/mutex.h> #include <linux/cgroup.h> #include <linux/wait.h> DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); /* * There could be abnormal cpuset configurations for cpu or memory * node binding, add this key to provide a quick low-cost judgement * of the situation. */ DEFINE_STATIC_KEY_FALSE(cpusets_insane_config_key); /* See "Frequency meter" comments, below. */ struct fmeter { int cnt; /* unprocessed events count */ int val; /* most recent output value */ time64_t time; /* clock (secs) when val computed */ spinlock_t lock; /* guards read or write of above */ }; struct cpuset { struct cgroup_subsys_state css; unsigned long flags; /* "unsigned long" so bitops work */ /* * On default hierarchy: * * The user-configured masks can only be changed by writing to * cpuset.cpus and cpuset.mems, and won't be limited by the * parent masks. * * The effective masks is the real masks that apply to the tasks * in the cpuset. They may be changed if the configured masks are * changed or hotplug happens. * * effective_mask == configured_mask & parent's effective_mask, * and if it ends up empty, it will inherit the parent's mask. * * * On legacy hierachy: * * The user-configured masks are always the same with effective masks. */ /* user-configured CPUs and Memory Nodes allow to tasks */ cpumask_var_t cpus_allowed; nodemask_t mems_allowed; /* effective CPUs and Memory Nodes allow to tasks */ cpumask_var_t effective_cpus; nodemask_t effective_mems; /* * CPUs allocated to child sub-partitions (default hierarchy only) * - CPUs granted by the parent = effective_cpus U subparts_cpus * - effective_cpus and subparts_cpus are mutually exclusive. * * effective_cpus contains only onlined CPUs, but subparts_cpus * may have offlined ones. */ cpumask_var_t subparts_cpus; /* * This is old Memory Nodes tasks took on. * * - top_cpuset.old_mems_allowed is initialized to mems_allowed. * - A new cpuset's old_mems_allowed is initialized when some * task is moved into it. * - old_mems_allowed is used in cpuset_migrate_mm() when we change * cpuset.mems_allowed and have tasks' nodemask updated, and * then old_mems_allowed is updated to mems_allowed. */ nodemask_t old_mems_allowed; struct fmeter fmeter; /* memory_pressure filter */ /* * Tasks are being attached to this cpuset. Used to prevent * zeroing cpus/mems_allowed between ->can_attach() and ->attach(). */ int attach_in_progress; /* partition number for rebuild_sched_domains() */ int pn; /* for custom sched domain */ int relax_domain_level; /* number of CPUs in subparts_cpus */ int nr_subparts_cpus; /* partition root state */ int partition_root_state; /* * Default hierarchy only: * use_parent_ecpus - set if using parent's effective_cpus * child_ecpus_count - # of children with use_parent_ecpus set */ int use_parent_ecpus; int child_ecpus_count; /* * number of SCHED_DEADLINE tasks attached to this cpuset, so that we * know when to rebuild associated root domain bandwidth information. */ int nr_deadline_tasks; int nr_migrate_dl_tasks; u64 sum_migrate_dl_bw; }; /* * Partition root states: * * 0 - not a partition root * * 1 - partition root * * -1 - invalid partition root * None of the cpus in cpus_allowed can be put into the parent's * subparts_cpus. In this case, the cpuset is not a real partition * root anymore. However, the CPU_EXCLUSIVE bit will still be set * and the cpuset can be restored back to a partition root if the * parent cpuset can give more CPUs back to this child cpuset. */ #define PRS_DISABLED 0 #define PRS_ENABLED 1 #define PRS_ERROR -1 /* * Temporary cpumasks for working with partitions that are passed among * functions to avoid memory allocation in inner functions. */ struct tmpmasks { cpumask_var_t addmask, delmask; /* For partition root */ cpumask_var_t new_cpus; /* For update_cpumasks_hier() */ }; static inline struct cpuset *css_cs(struct cgroup_subsys_state *css) { return css ? container_of(css, struct cpuset, css) : NULL; } /* Retrieve the cpuset for a task */ static inline struct cpuset *task_cs(struct task_struct *task) { return css_cs(task_css(task, cpuset_cgrp_id)); } static inline struct cpuset *parent_cs(struct cpuset *cs) { return css_cs(cs->css.parent); } void inc_dl_tasks_cs(struct task_struct *p) { struct cpuset *cs = task_cs(p); cs->nr_deadline_tasks++; } void dec_dl_tasks_cs(struct task_struct *p) { struct cpuset *cs = task_cs(p); cs->nr_deadline_tasks--; } /* bits in struct cpuset flags field */ typedef enum { CS_ONLINE, CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE, CS_MEM_HARDWALL, CS_MEMORY_MIGRATE, CS_SCHED_LOAD_BALANCE, CS_SPREAD_PAGE, CS_SPREAD_SLAB, } cpuset_flagbits_t; /* convenient tests for these bits */ static inline bool is_cpuset_online(struct cpuset *cs) { return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css); } static inline int is_cpu_exclusive(const struct cpuset *cs) { return test_bit(CS_CPU_EXCLUSIVE, &cs->flags); } static inline int is_mem_exclusive(const struct cpuset *cs) { return test_bit(CS_MEM_EXCLUSIVE, &cs->flags); } static inline int is_mem_hardwall(const struct cpuset *cs) { return test_bit(CS_MEM_HARDWALL, &cs->flags); } static inline int is_sched_load_balance(const struct cpuset *cs) { return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); } static inline int is_memory_migrate(const struct cpuset *cs) { return test_bit(CS_MEMORY_MIGRATE, &cs->flags); } static inline int is_spread_page(const struct cpuset *cs) { return test_bit(CS_SPREAD_PAGE, &cs->flags); } static inline int is_spread_slab(const struct cpuset *cs) { return test_bit(CS_SPREAD_SLAB, &cs->flags); } static inline int is_partition_root(const struct cpuset *cs) { return cs->partition_root_state > 0; } static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), .partition_root_state = PRS_ENABLED, }; /** * cpuset_for_each_child - traverse online children of a cpuset * @child_cs: loop cursor pointing to the current child * @pos_css: used for iteration * @parent_cs: target cpuset to walk children of * * Walk @child_cs through the online children of @parent_cs. Must be used * with RCU read locked. */ #define cpuset_for_each_child(child_cs, pos_css, parent_cs) \ css_for_each_child((pos_css), &(parent_cs)->css) \ if (is_cpuset_online(((child_cs) = css_cs((pos_css))))) /** * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants * @des_cs: loop cursor pointing to the current descendant * @pos_css: used for iteration * @root_cs: target cpuset to walk ancestor of * * Walk @des_cs through the online descendants of @root_cs. Must be used * with RCU read locked. The caller may modify @pos_css by calling * css_rightmost_descendant() to skip subtree. @root_cs is included in the * iteration and the first node to be visited. */ #define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs) \ css_for_each_descendant_pre((pos_css), &(root_cs)->css) \ if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* * There are two global locks guarding cpuset structures - cpuset_mutex and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this * comment. * * A task must hold both locks to modify cpusets. If a task holds * cpuset_mutex, then it blocks others wanting that mutex, ensuring that it * is the only task able to also acquire callback_lock and be able to * modify cpusets. It can perform various checks on the cpuset structure * first, knowing nothing will change. It can also allocate memory while * just holding cpuset_mutex. While it is performing these checks, various * callback routines can briefly acquire callback_lock to query cpusets. * Once it is ready to make the changes, it takes callback_lock, blocking * everyone else. * * Calls to the kernel memory allocator can not be made while holding * callback_lock, as that would risk double tripping on callback_lock * from one of the callbacks into the cpuset code from within * __alloc_pages(). * * If a task is only holding callback_lock, then it has read-only * access to cpusets. * * Now, the task_struct fields mems_allowed and mempolicy may be changed * by other task, we use alloc_lock in the task_struct fields to protect * them. * * The cpuset_common_file_read() handlers only hold callback_lock across * small pieces of code, such as when reading out possibly multi-word * cpumasks and nodemasks. * * Accessing a task's cpuset should be done in accordance with the * guidelines for accessing subsystem state in kernel/cgroup.c */ static DEFINE_MUTEX(cpuset_mutex); void cpuset_lock(void) { mutex_lock(&cpuset_mutex); } void cpuset_unlock(void) { mutex_unlock(&cpuset_mutex); } static DEFINE_SPINLOCK(callback_lock); static struct workqueue_struct *cpuset_migrate_mm_wq; /* * CPU / memory hotplug is handled asynchronously. */ static void cpuset_hotplug_workfn(struct work_struct *work); static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); static inline void check_insane_mems_config(nodemask_t *nodes) { if (!cpusets_insane_config() && movable_only_nodes(nodes)) { static_branch_enable_cpuslocked(&cpusets_insane_config_key); pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n" "Cpuset allocations might fail even with a lot of memory available.\n", nodemask_pr_args(nodes)); } } /* * Cgroup v2 behavior is used on the "cpus" and "mems" control files when * on default hierarchy or when the cpuset_v2_mode flag is set by mounting * the v1 cpuset cgroup filesystem with the "cpuset_v2_mode" mount option. * With v2 behavior, "cpus" and "mems" are always what the users have * requested and won't be changed by hotplug events. Only the effective * cpus or mems will be affected. */ static inline bool is_in_v2_mode(void) { return cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); } /* * Return in pmask the portion of a cpusets's cpus_allowed that * are online. If none are online, walk up the cpuset hierarchy * until we find one that does have some online cpus. * * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask) { while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) { cs = parent_cs(cs); if (unlikely(!cs)) { /* * The top cpuset doesn't have any online cpu as a * consequence of a race between cpuset_hotplug_work * and cpu hotplug notifier. But we know the top * cpuset's effective_cpus is on its way to be * identical to cpu_online_mask. */ cpumask_copy(pmask, cpu_online_mask); return; } } cpumask_and(pmask, cs->effective_cpus, cpu_online_mask); } /* * Return in *pmask the portion of a cpusets's mems_allowed that * are online, with memory. If none are online with memory, walk * up the cpuset hierarchy until we find one that does have some * online mems. The top cpuset always has some mems online. * * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { while (!nodes_intersects(cs->effective_mems, node_states[N_MEMORY])) cs = parent_cs(cs); nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY]); } /* * update task's spread flag if cpuset's page/slab spread flag is set * * Call with callback_lock or cpuset_mutex held. */ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) { if (is_spread_page(cs)) task_set_spread_page(tsk); else task_clear_spread_page(tsk); if (is_spread_slab(cs)) task_set_spread_slab(tsk); else task_clear_spread_slab(tsk); } /* * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q? * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags * are only set if the other's are set. Call holding cpuset_mutex. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) { return cpumask_subset(p->cpus_allowed, q->cpus_allowed) && nodes_subset(p->mems_allowed, q->mems_allowed) && is_cpu_exclusive(p) <= is_cpu_exclusive(q) && is_mem_exclusive(p) <= is_mem_exclusive(q); } /** * alloc_cpumasks - allocate three cpumasks for cpuset * @cs: the cpuset that have cpumasks to be allocated. * @tmp: the tmpmasks structure pointer * Return: 0 if successful, -ENOMEM otherwise. * * Only one of the two input arguments should be non-NULL. */ static inline int alloc_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) { cpumask_var_t *pmask1, *pmask2, *pmask3; if (cs) { pmask1 = &cs->cpus_allowed; pmask2 = &cs->effective_cpus; pmask3 = &cs->subparts_cpus; } else { pmask1 = &tmp->new_cpus; pmask2 = &tmp->addmask; pmask3 = &tmp->delmask; } if (!zalloc_cpumask_var(pmask1, GFP_KERNEL)) return -ENOMEM; if (!zalloc_cpumask_var(pmask2, GFP_KERNEL)) goto free_one; if (!zalloc_cpumask_var(pmask3, GFP_KERNEL)) goto free_two; return 0; free_two: free_cpumask_var(*pmask2); free_one: free_cpumask_var(*pmask1); return -ENOMEM; } /** * free_cpumasks - free cpumasks in a tmpmasks structure * @cs: the cpuset that have cpumasks to be free. * @tmp: the tmpmasks structure pointer */ static inline void free_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) { if (cs) { free_cpumask_var(cs->cpus_allowed); free_cpumask_var(cs->effective_cpus); free_cpumask_var(cs->subparts_cpus); } if (tmp) { free_cpumask_var(tmp->new_cpus); free_cpumask_var(tmp->addmask); free_cpumask_var(tmp->delmask); } } /** * alloc_trial_cpuset - allocate a trial cpuset * @cs: the cpuset that the trial cpuset duplicates */ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs) { struct cpuset *trial; trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL); if (!trial) return NULL; if (alloc_cpumasks(trial, NULL)) { kfree(trial); return NULL; } cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); cpumask_copy(trial->effective_cpus, cs->effective_cpus); return trial; } /** * free_cpuset - free the cpuset * @cs: the cpuset to be freed */ static inline void free_cpuset(struct cpuset *cs) { free_cpumasks(cs, NULL); kfree(cs); } /* * validate_change() - Used to validate that any proposed cpuset change * follows the structural rules for cpusets. * * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes * cpuset_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the * cpuset in the list must use cur below, not trial. * * 'trial' is the address of bulk structure copy of cur, with * perhaps one or more of the fields cpus_allowed, mems_allowed, * or flags changed to new, trial values. * * Return 0 if valid, -errno if not. */ static int validate_change(struct cpuset *cur, struct cpuset *trial) { struct cgroup_subsys_state *css; struct cpuset *c, *par; int ret; rcu_read_lock(); /* Each of our child cpusets must be a subset of us */ ret = -EBUSY; cpuset_for_each_child(c, css, cur) if (!is_cpuset_subset(c, trial)) goto out; /* Remaining checks don't apply to root cpuset */ ret = 0; if (cur == &top_cpuset) goto out; par = parent_cs(cur); /* On legacy hiearchy, we must be a subset of our parent cpuset. */ ret = -EACCES; if (!is_in_v2_mode() && !is_cpuset_subset(trial, par)) goto out; /* * If either I or some sibling (!= me) is exclusive, we can't * overlap */ ret = -EINVAL; cpuset_for_each_child(c, css, par) { if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && c != cur && cpumask_intersects(trial->cpus_allowed, c->cpus_allowed)) goto out; if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && c != cur && nodes_intersects(trial->mems_allowed, c->mems_allowed)) goto out; } /* * Cpusets with tasks - existing or newly being attached - can't * be changed to have empty cpus_allowed or mems_allowed. */ ret = -ENOSPC; if ((cgroup_is_populated(cur->css.cgroup) || cur->attach_in_progress)) { if (!cpumask_empty(cur->cpus_allowed) && cpumask_empty(trial->cpus_allowed)) goto out; if (!nodes_empty(cur->mems_allowed) && nodes_empty(trial->mems_allowed)) goto out; } /* * We can't shrink if we won't have enough room for SCHED_DEADLINE * tasks. */ ret = -EBUSY; if (is_cpu_exclusive(cur) && !cpuset_cpumask_can_shrink(cur->cpus_allowed, trial->cpus_allowed)) goto out; ret = 0; out: rcu_read_unlock(); return ret; } #ifdef CONFIG_SMP /* * Helper routine for generate_sched_domains(). * Do cpusets a, b have overlapping effective cpus_allowed masks? */ static int cpusets_overlap(struct cpuset *a, struct cpuset *b) { return cpumask_intersects(a->effective_cpus, b->effective_cpus); } static void update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c) { if (dattr->relax_domain_level < c->relax_domain_level) dattr->relax_domain_level = c->relax_domain_level; return; } static void update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *root_cs) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { /* skip the whole subtree if @cp doesn't have any CPU */ if (cpumask_empty(cp->cpus_allowed)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (is_sched_load_balance(cp)) update_domain_attr(dattr, cp); } rcu_read_unlock(); } /* Must be called with cpuset_mutex held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ return static_key_count(&cpusets_enabled_key.key) + 1; } /* * generate_sched_domains() * * This function builds a partial partition of the systems CPUs * A 'partial partition' is a set of non-overlapping subsets whose * union is a subset of that set. * The output of this function needs to be passed to kernel/sched/core.c * partition_sched_domains() routine, which will rebuild the scheduler's * load balancing domains (sched domains) as specified by that partial * partition. * * See "What is sched_load_balance" in Documentation/admin-guide/cgroup-v1/cpusets.rst * for a background explanation of this. * * Does not return errors, on the theory that the callers of this * routine would rather not worry about failures to rebuild sched * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * * Must be called with cpuset_mutex held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a * top-down scan of all cpusets. For our purposes, rebuilding * the schedulers sched domains, we can ignore !is_sched_load_ * balance cpusets. * csa - (for CpuSet Array) Array of pointers to all the cpusets * that need to be load balanced, for convenient iterative * access by the subsequent code that finds the best partition, * i.e the set of domains (subsets) of CPUs such that the * cpus_allowed of every cpuset marked is_sched_load_balance * is a subset of one of these domains, while there are as * many such domains as possible, each as small as possible. * doms - Conversion of 'csa' to an array of cpumasks, for passing to * the kernel/sched/core.c routine partition_sched_domains() in a * convenient format, that can be easily compared to the prior * value to determine what partition elements (sched domains) * were changed (added or removed.) * * Finding the best partition (set of domains): * The triple nested loops below over i, j, k scan over the * load balanced cpusets (using the array of cpuset pointers in * csa[]) looking for pairs of cpusets that have overlapping * cpus_allowed, but which don't have the same 'pn' partition * number and gives them in the same partition number. It keeps * looping on the 'restart' label until it can no longer find * any such pairs. * * The union of the cpus_allowed masks from the set of * all cpusets having the same 'pn' value then form the one * element of the partition (one sched domain) to be passed to * partition_sched_domains(). */ static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr **attributes) { struct cpuset *cp; /* top-down scan of cpusets */ struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ struct cgroup_subsys_state *pos_css; bool root_load_balance = is_sched_load_balance(&top_cpuset); doms = NULL; dattr = NULL; csa = NULL; /* Special case for the 99% of systems with one, full, sched domain */ if (root_load_balance && !top_cpuset.nr_subparts_cpus) { ndoms = 1; doms = alloc_sched_domains(ndoms); if (!doms) goto done; dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL); if (dattr) { *dattr = SD_ATTR_INIT; update_domain_attr_tree(dattr, &top_cpuset); } cpumask_and(doms[0], top_cpuset.effective_cpus, housekeeping_cpumask(HK_FLAG_DOMAIN)); goto done; } csa = kmalloc_array(nr_cpusets(), sizeof(cp), GFP_KERNEL); if (!csa) goto done; csn = 0; rcu_read_lock(); if (root_load_balance) csa[csn++] = &top_cpuset; cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) { if (cp == &top_cpuset) continue; /* * Continue traversing beyond @cp iff @cp has some CPUs and * isn't load balancing. The former is obvious. The * latter: All child cpusets contain a subset of the * parent's cpus, so just skip them, and then we call * update_domain_attr_tree() to calc relax_domain_level of * the corresponding sched domain. * * If root is load-balancing, we can skip @cp if it * is a subset of the root's effective_cpus. */ if (!cpumask_empty(cp->cpus_allowed) && !(is_sched_load_balance(cp) && cpumask_intersects(cp->cpus_allowed, housekeeping_cpumask(HK_FLAG_DOMAIN)))) continue; if (root_load_balance && cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus)) continue; if (is_sched_load_balance(cp) && !cpumask_empty(cp->effective_cpus)) csa[csn++] = cp; /* skip @cp's subtree if not a partition root */ if (!is_partition_root(cp)) pos_css = css_rightmost_descendant(pos_css); } rcu_read_unlock(); for (i = 0; i < csn; i++) csa[i]->pn = i; ndoms = csn; restart: /* Find the best partition (set of sched domains) */ for (i = 0; i < csn; i++) { struct cpuset *a = csa[i]; int apn = a->pn; for (j = 0; j < csn; j++) { struct cpuset *b = csa[j]; int bpn = b->pn; if (apn != bpn && cpusets_overlap(a, b)) { for (k = 0; k < csn; k++) { struct cpuset *c = csa[k]; if (c->pn == bpn) c->pn = apn; } ndoms--; /* one less element */ goto restart; } } } /* * Now we know how many domains to create. * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. */ doms = alloc_sched_domains(ndoms); if (!doms) goto done; /* * The rest of the code, including the scheduler, can deal with * dattr==NULL case. No need to abort if alloc fails. */ dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr), GFP_KERNEL); for (nslot = 0, i = 0; i < csn; i++) { struct cpuset *a = csa[i]; struct cpumask *dp; int apn = a->pn; if (apn < 0) { /* Skip completed partitions */ continue; } dp = doms[nslot]; if (nslot == ndoms) { static int warnings = 10; if (warnings) { pr_warn("rebuild_sched_domains confused: nslot %d, ndoms %d, csn %d, i %d, apn %d\n", nslot, ndoms, csn, i, apn); warnings--; } continue; } cpumask_clear(dp); if (dattr) *(dattr + nslot) = SD_ATTR_INIT; for (j = i; j < csn; j++) { struct cpuset *b = csa[j]; if (apn == b->pn) { cpumask_or(dp, dp, b->effective_cpus); cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN)); if (dattr) update_domain_attr_tree(dattr + nslot, b); /* Done with this partition */ b->pn = -1; } } nslot++; } BUG_ON(nslot != ndoms); done: kfree(csa); /* * Fallback to the default domain if kmalloc() failed. * See comments in partition_sched_domains(). */ if (doms == NULL) ndoms = 1; *domains = doms; *attributes = dattr; return ndoms; } static void dl_update_tasks_root_domain(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; if (cs->nr_deadline_tasks == 0) return; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) dl_add_task_root_domain(task); css_task_iter_end(&it); } static void dl_rebuild_rd_accounting(void) { struct cpuset *cs = NULL; struct cgroup_subsys_state *pos_css; lockdep_assert_held(&cpuset_mutex); lockdep_assert_cpus_held(); lockdep_assert_held(&sched_domains_mutex); rcu_read_lock(); /* * Clear default root domain DL accounting, it will be computed again * if a task belongs to it. */ dl_clear_root_domain(&def_root_domain); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cpumask_empty(cs->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } css_get(&cs->css); rcu_read_unlock(); dl_update_tasks_root_domain(cs); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } static void partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { mutex_lock(&sched_domains_mutex); partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); dl_rebuild_rd_accounting(); mutex_unlock(&sched_domains_mutex); } /* * Rebuild scheduler domains. * * If the flag 'sched_load_balance' of any cpuset with non-empty * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset * which has that flag enabled, or if any cpuset with a non-empty * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * * Call with cpuset_mutex held. Takes get_online_cpus(). */ static void rebuild_sched_domains_locked(void) { struct cgroup_subsys_state *pos_css; struct sched_domain_attr *attr; cpumask_var_t *doms; struct cpuset *cs; int ndoms; lockdep_assert_cpus_held(); lockdep_assert_held(&cpuset_mutex); /* * If we have raced with CPU hotplug, return early to avoid * passing doms with offlined cpu to partition_sched_domains(). * Anyways, cpuset_hotplug_workfn() will rebuild sched domains. * * With no CPUs in any subpartitions, top_cpuset's effective CPUs * should be the same as the active CPUs, so checking only top_cpuset * is enough to detect racing CPU offlines. */ if (!top_cpuset.nr_subparts_cpus && !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) return; /* * With subpartition CPUs, however, the effective CPUs of a partition * root should be only a subset of the active CPUs. Since a CPU in any * partition root could be offlined, all must be checked. */ if (top_cpuset.nr_subparts_cpus) { rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (!is_partition_root(cs)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!cpumask_subset(cs->effective_cpus, cpu_active_mask)) { rcu_read_unlock(); return; } } rcu_read_unlock(); } /* Generate domain masks and attrs */ ndoms = generate_sched_domains(&doms, &attr); /* Have scheduler rebuild the domains */ partition_and_rebuild_sched_domains(ndoms, doms, attr); } #else /* !CONFIG_SMP */ static void rebuild_sched_domains_locked(void) { } #endif /* CONFIG_SMP */ void rebuild_sched_domains(void) { get_online_cpus(); mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); mutex_unlock(&cpuset_mutex); put_online_cpus(); } /** * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed * * Iterate through each task of @cs updating its cpus_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_cpumask(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; bool top_cs = cs == &top_cpuset; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { /* * Percpu kthreads in top_cpuset are ignored */ if (top_cs && (task->flags & PF_KTHREAD) && kthread_is_per_cpu(task)) continue; set_cpus_allowed_ptr(task, cs->effective_cpus); } css_task_iter_end(&it); } /** * compute_effective_cpumask - Compute the effective cpumask of the cpuset * @new_cpus: the temp variable for the new effective_cpus mask * @cs: the cpuset the need to recompute the new effective_cpus mask * @parent: the parent cpuset * * If the parent has subpartition CPUs, include them in the list of * allowable CPUs in computing the new effective_cpus mask. Since offlined * CPUs are not removed from subparts_cpus, we have to use cpu_active_mask * to mask those out. */ static void compute_effective_cpumask(struct cpumask *new_cpus, struct cpuset *cs, struct cpuset *parent) { if (parent->nr_subparts_cpus) { cpumask_or(new_cpus, parent->effective_cpus, parent->subparts_cpus); cpumask_and(new_cpus, new_cpus, cs->cpus_allowed); cpumask_and(new_cpus, new_cpus, cpu_active_mask); } else { cpumask_and(new_cpus, cs->cpus_allowed, parent->effective_cpus); } } /* * Commands for update_parent_subparts_cpumask */ enum subparts_cmd { partcmd_enable, /* Enable partition root */ partcmd_disable, /* Disable partition root */ partcmd_update, /* Update parent's subparts_cpus */ }; /** * update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset * @cpuset: The cpuset that requests change in partition root state * @cmd: Partition root state change command * @newmask: Optional new cpumask for partcmd_update * @tmp: Temporary addmask and delmask * Return: 0, 1 or an error code * * For partcmd_enable, the cpuset is being transformed from a non-partition * root to a partition root. The cpus_allowed mask of the given cpuset will * be put into parent's subparts_cpus and taken away from parent's * effective_cpus. The function will return 0 if all the CPUs listed in * cpus_allowed can be granted or an error code will be returned. * * For partcmd_disable, the cpuset is being transofrmed from a partition * root back to a non-partition root. Any CPUs in cpus_allowed that are in * parent's subparts_cpus will be taken away from that cpumask and put back * into parent's effective_cpus. 0 should always be returned. * * For partcmd_update, if the optional newmask is specified, the cpu * list is to be changed from cpus_allowed to newmask. Otherwise, * cpus_allowed is assumed to remain the same. The cpuset should either * be a partition root or an invalid partition root. The partition root * state may change if newmask is NULL and none of the requested CPUs can * be granted by the parent. The function will return 1 if changes to * parent's subparts_cpus and effective_cpus happen or 0 otherwise. * Error code should only be returned when newmask is non-NULL. * * The partcmd_enable and partcmd_disable commands are used by * update_prstate(). The partcmd_update command is used by * update_cpumasks_hier() with newmask NULL and update_cpumask() with * newmask set. * * The checking is more strict when enabling partition root than the * other two commands. * * Because of the implicit cpu exclusive nature of a partition root, * cpumask changes that violates the cpu exclusivity rule will not be * permitted when checked by validate_change(). The validate_change() * function will also prevent any changes to the cpu list if it is not * a superset of children's cpu lists. */ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, struct cpumask *newmask, struct tmpmasks *tmp) { struct cpuset *parent = parent_cs(cpuset); int adding; /* Moving cpus from effective_cpus to subparts_cpus */ int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ int new_prs; bool part_error = false; /* Partition error? */ lockdep_assert_held(&cpuset_mutex); /* * The parent must be a partition root. * The new cpumask, if present, or the current cpus_allowed must * not be empty. */ if (!is_partition_root(parent) || (newmask && cpumask_empty(newmask)) || (!newmask && cpumask_empty(cpuset->cpus_allowed))) return -EINVAL; /* * Enabling/disabling partition root is not allowed if there are * online children. */ if ((cmd != partcmd_update) && css_has_online_children(&cpuset->css)) return -EBUSY; /* * Enabling partition root is not allowed if not all the CPUs * can be granted from parent's effective_cpus or at least one * CPU will be left after that. */ if ((cmd == partcmd_enable) && (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus))) return -EINVAL; /* * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; new_prs = cpuset->partition_root_state; if (cmd == partcmd_enable) { cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; } else if (cmd == partcmd_disable) { deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed, parent->subparts_cpus); } else if (newmask) { /* * partcmd_update with newmask: * * delmask = cpus_allowed & ~newmask & parent->subparts_cpus * addmask = newmask & parent->effective_cpus * & ~parent->subparts_cpus */ cpumask_andnot(tmp->delmask, cpuset->cpus_allowed, newmask); deleting = cpumask_and(tmp->delmask, tmp->delmask, parent->subparts_cpus); cpumask_and(tmp->addmask, newmask, parent->effective_cpus); adding = cpumask_andnot(tmp->addmask, tmp->addmask, parent->subparts_cpus); /* * Return error if the new effective_cpus could become empty. */ if (adding && cpumask_equal(parent->effective_cpus, tmp->addmask)) { if (!deleting) return -EINVAL; /* * As some of the CPUs in subparts_cpus might have * been offlined, we need to compute the real delmask * to confirm that. */ if (!cpumask_and(tmp->addmask, tmp->delmask, cpu_active_mask)) return -EINVAL; cpumask_copy(tmp->addmask, parent->effective_cpus); } } else { /* * partcmd_update w/o newmask: * * addmask = cpus_allowed & parent->effective_cpus * * Note that parent's subparts_cpus may have been * pre-shrunk in case there is a change in the cpu list. * So no deletion is needed. */ adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed, parent->effective_cpus); part_error = cpumask_equal(tmp->addmask, parent->effective_cpus); } if (cmd == partcmd_update) { int prev_prs = cpuset->partition_root_state; /* * Check for possible transition between PRS_ENABLED * and PRS_ERROR. */ switch (cpuset->partition_root_state) { case PRS_ENABLED: if (part_error) new_prs = PRS_ERROR; break; case PRS_ERROR: if (!part_error) new_prs = PRS_ENABLED; break; } /* * Set part_error if previously in invalid state. */ part_error = (prev_prs == PRS_ERROR); } if (!part_error && (new_prs == PRS_ERROR)) return 0; /* Nothing need to be done */ if (new_prs == PRS_ERROR) { /* * Remove all its cpus from parent's subparts_cpus. */ adding = false; deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed, parent->subparts_cpus); } if (!adding && !deleting && (new_prs == cpuset->partition_root_state)) return 0; /* * Change the parent's subparts_cpus. * Newly added CPUs will be removed from effective_cpus and * newly deleted ones will be added back to effective_cpus. */ spin_lock_irq(&callback_lock); if (adding) { cpumask_or(parent->subparts_cpus, parent->subparts_cpus, tmp->addmask); cpumask_andnot(parent->effective_cpus, parent->effective_cpus, tmp->addmask); } if (deleting) { cpumask_andnot(parent->subparts_cpus, parent->subparts_cpus, tmp->delmask); /* * Some of the CPUs in subparts_cpus might have been offlined. */ cpumask_and(tmp->delmask, tmp->delmask, cpu_active_mask); cpumask_or(parent->effective_cpus, parent->effective_cpus, tmp->delmask); } parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus); if (cpuset->partition_root_state != new_prs) cpuset->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); return cmd == partcmd_update; } /* * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree * @cs: the cpuset to consider * @tmp: temp variables for calculating effective_cpus & partition setup * * When congifured cpumask is changed, the effective cpumasks of this cpuset * and all its descendants need to be updated. * * On legacy hierachy, effective_cpus will be the same with cpu_allowed. * * Called with cpuset_mutex held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; bool need_rebuild_sched_domains = false; int new_prs; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); compute_effective_cpumask(tmp->new_cpus, cp, parent); /* * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some CPUs. */ if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) { cpumask_copy(tmp->new_cpus, parent->effective_cpus); if (!cp->use_parent_ecpus) { cp->use_parent_ecpus = true; parent->child_ecpus_count++; } } else if (cp->use_parent_ecpus) { cp->use_parent_ecpus = false; WARN_ON_ONCE(!parent->child_ecpus_count); parent->child_ecpus_count--; } /* * Skip the whole subtree if the cpumask remains the same * and has no partition root state. */ if (!cp->partition_root_state && cpumask_equal(tmp->new_cpus, cp->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } /* * update_parent_subparts_cpumask() should have been called * for cs already in update_cpumask(). We should also call * update_tasks_cpumask() again for tasks in the parent * cpuset if the parent's subparts_cpus changes. */ new_prs = cp->partition_root_state; if ((cp != cs) && new_prs) { switch (parent->partition_root_state) { case PRS_DISABLED: /* * If parent is not a partition root or an * invalid partition root, clear its state * and its CS_CPU_EXCLUSIVE flag. */ WARN_ON_ONCE(cp->partition_root_state != PRS_ERROR); new_prs = PRS_DISABLED; /* * clear_bit() is an atomic operation and * readers aren't interested in the state * of CS_CPU_EXCLUSIVE anyway. So we can * just update the flag without holding * the callback_lock. */ clear_bit(CS_CPU_EXCLUSIVE, &cp->flags); break; case PRS_ENABLED: if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp)) update_tasks_cpumask(parent); break; case PRS_ERROR: /* * When parent is invalid, it has to be too. */ new_prs = PRS_ERROR; break; } } if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); spin_lock_irq(&callback_lock); cpumask_copy(cp->effective_cpus, tmp->new_cpus); if (cp->nr_subparts_cpus && (new_prs != PRS_ENABLED)) { cp->nr_subparts_cpus = 0; cpumask_clear(cp->subparts_cpus); } else if (cp->nr_subparts_cpus) { /* * Make sure that effective_cpus & subparts_cpus * are mutually exclusive. * * In the unlikely event that effective_cpus * becomes empty. we clear cp->nr_subparts_cpus and * let its child partition roots to compete for * CPUs again. */ cpumask_andnot(cp->effective_cpus, cp->effective_cpus, cp->subparts_cpus); if (cpumask_empty(cp->effective_cpus)) { cpumask_copy(cp->effective_cpus, tmp->new_cpus); cpumask_clear(cp->subparts_cpus); cp->nr_subparts_cpus = 0; } else if (!cpumask_subset(cp->subparts_cpus, tmp->new_cpus)) { cpumask_andnot(cp->subparts_cpus, cp->subparts_cpus, tmp->new_cpus); cp->nr_subparts_cpus = cpumask_weight(cp->subparts_cpus); } } if (new_prs != cp->partition_root_state) cp->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); update_tasks_cpumask(cp); /* * On legacy hierarchy, if the effective cpumask of any non- * empty cpuset is changed, we need to rebuild sched domains. * On default hierarchy, the cpuset needs to be a partition * root as well. */ if (!cpumask_empty(cp->cpus_allowed) && is_sched_load_balance(cp) && (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || is_partition_root(cp))) need_rebuild_sched_domains = true; rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); if (need_rebuild_sched_domains) rebuild_sched_domains_locked(); } /** * update_sibling_cpumasks - Update siblings cpumasks * @parent: Parent cpuset * @cs: Current cpuset * @tmp: Temp variables */ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *sibling; struct cgroup_subsys_state *pos_css; lockdep_assert_held(&cpuset_mutex); /* * Check all its siblings and call update_cpumasks_hier() * if their use_parent_ecpus flag is set in order for them * to use the right effective_cpus value. * * The update_cpumasks_hier() function may sleep. So we have to * release the RCU read lock before calling it. */ rcu_read_lock(); cpuset_for_each_child(sibling, pos_css, parent) { if (sibling == cs) continue; if (!sibling->use_parent_ecpus) continue; if (!css_tryget_online(&sibling->css)) continue; rcu_read_unlock(); update_cpumasks_hier(sibling, tmp); rcu_read_lock(); css_put(&sibling->css); } rcu_read_unlock(); } /** * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it * @cs: the cpuset to consider * @trialcs: trial cpuset * @buf: buffer of cpu numbers written to this cpuset */ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; struct tmpmasks tmp; /* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */ if (cs == &top_cpuset) return -EACCES; /* * An empty cpus_allowed is ok only if the cpuset has no tasks. * Since cpulist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have cpus. */ if (!*buf) { cpumask_clear(trialcs->cpus_allowed); } else { retval = cpulist_parse(buf, trialcs->cpus_allowed); if (retval < 0) return retval; if (!cpumask_subset(trialcs->cpus_allowed, top_cpuset.cpus_allowed)) return -EINVAL; } /* Nothing to do if the cpus didn't change */ if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed)) return 0; retval = validate_change(cs, trialcs); if (retval < 0) return retval; #ifdef CONFIG_CPUMASK_OFFSTACK /* * Use the cpumasks in trialcs for tmpmasks when they are pointers * to allocated cpumasks. */ tmp.addmask = trialcs->subparts_cpus; tmp.delmask = trialcs->effective_cpus; tmp.new_cpus = trialcs->cpus_allowed; #endif if (cs->partition_root_state) { /* Cpumask of a partition root cannot be empty */ if (cpumask_empty(trialcs->cpus_allowed)) return -EINVAL; if (update_parent_subparts_cpumask(cs, partcmd_update, trialcs->cpus_allowed, &tmp) < 0) return -EINVAL; } spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); /* * Make sure that subparts_cpus is a subset of cpus_allowed. */ if (cs->nr_subparts_cpus) { cpumask_and(cs->subparts_cpus, cs->subparts_cpus, cs->cpus_allowed); cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus); } spin_unlock_irq(&callback_lock); update_cpumasks_hier(cs, &tmp); if (cs->partition_root_state) { struct cpuset *parent = parent_cs(cs); /* * For partition root, update the cpumasks of sibling * cpusets if they use parent's effective_cpus. */ if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmp); } return 0; } /* * Migrate memory region from one set of nodes to another. This is * performed asynchronously as it can be called from process migration path * holding locks involved in process management. All mm migrations are * performed in the queued order and can be waited for by flushing * cpuset_migrate_mm_wq. */ struct cpuset_migrate_mm_work { struct work_struct work; struct mm_struct *mm; nodemask_t from; nodemask_t to; }; static void cpuset_migrate_mm_workfn(struct work_struct *work) { struct cpuset_migrate_mm_work *mwork = container_of(work, struct cpuset_migrate_mm_work, work); /* on a wq worker, no need to worry about %current's mems_allowed */ do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL); mmput(mwork->mm); kfree(mwork); } static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to) { struct cpuset_migrate_mm_work *mwork; mwork = kzalloc(sizeof(*mwork), GFP_KERNEL); if (mwork) { mwork->mm = mm; mwork->from = *from; mwork->to = *to; INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn); queue_work(cpuset_migrate_mm_wq, &mwork->work); } else { mmput(mm); } } static void cpuset_post_attach(void) { flush_workqueue(cpuset_migrate_mm_wq); } /* * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy * @tsk: the task to change * @newmems: new nodes that the task will be set * * We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed * and rebind an eventual tasks' mempolicy. If the task is allocating in * parallel, it might temporarily see an empty intersection, which results in * a seqlock check and retry before OOM or allocation failure. */ static void cpuset_change_task_nodemask(struct task_struct *tsk, nodemask_t *newmems) { task_lock(tsk); local_irq_disable(); write_seqcount_begin(&tsk->mems_allowed_seq); nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); mpol_rebind_task(tsk, newmems); tsk->mems_allowed = *newmems; write_seqcount_end(&tsk->mems_allowed_seq); local_irq_enable(); task_unlock(tsk); } static void *cpuset_being_rebound; /** * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { static nodemask_t newmems; /* protected by cpuset_mutex */ struct css_task_iter it; struct task_struct *task; cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ guarantee_online_mems(cs, &newmems); /* * The mpol_rebind_mm() call takes mmap_lock, which we couldn't * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold * the global cpuset_mutex, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. */ css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { struct mm_struct *mm; bool migrate; cpuset_change_task_nodemask(task, &newmems); mm = get_task_mm(task); if (!mm) continue; migrate = is_memory_migrate(cs); mpol_rebind_mm(mm, &cs->mems_allowed); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); else mmput(mm); } css_task_iter_end(&it); /* * All the tasks' nodemasks have been updated, update * cs->old_mems_allowed. */ cs->old_mems_allowed = newmems; /* We're done rebinding vmas to this cpuset's new mems_allowed. */ cpuset_being_rebound = NULL; } /* * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree * @cs: the cpuset to consider * @new_mems: a temp variable for calculating new effective_mems * * When configured nodemask is changed, the effective nodemasks of this cpuset * and all its descendants need to be updated. * * On legacy hiearchy, effective_mems will be the same with mems_allowed. * * Called with cpuset_mutex held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems); /* * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some MEMs. */ if (is_in_v2_mode() && nodes_empty(*new_mems)) *new_mems = parent->effective_mems; /* Skip the whole subtree if the nodemask remains the same. */ if (nodes_equal(*new_mems, cp->effective_mems)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); spin_lock_irq(&callback_lock); cp->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !nodes_equal(cp->mems_allowed, cp->effective_mems)); update_tasks_nodemask(cp); rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); } /* * Handle user request to change the 'mems' memory placement * of a cpuset. Needs to validate the request, update the * cpusets mems_allowed, and for each task in the cpuset, * update mems_allowed and rebind task's mempolicy and any vma * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * * Call with cpuset_mutex held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_lock, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. */ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; /* * top_cpuset.mems_allowed tracks node_stats[N_MEMORY]; * it's read-only */ if (cs == &top_cpuset) { retval = -EACCES; goto done; } /* * An empty mems_allowed is ok iff there are no tasks in the cpuset. * Since nodelist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have memory. */ if (!*buf) { nodes_clear(trialcs->mems_allowed); } else { retval = nodelist_parse(buf, trialcs->mems_allowed); if (retval < 0) goto done; if (!nodes_subset(trialcs->mems_allowed, top_cpuset.mems_allowed)) { retval = -EINVAL; goto done; } } if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) { retval = 0; /* Too easy - nothing to do */ goto done; } retval = validate_change(cs, trialcs); if (retval < 0) goto done; check_insane_mems_config(&trialcs->mems_allowed); spin_lock_irq(&callback_lock); cs->mems_allowed = trialcs->mems_allowed; spin_unlock_irq(&callback_lock); /* use trialcs->mems_allowed as a temp variable */ update_nodemasks_hier(cs, &trialcs->mems_allowed); done: return retval; } bool current_cpuset_is_being_rebound(void) { bool ret; rcu_read_lock(); ret = task_cs(current) == cpuset_being_rebound; rcu_read_unlock(); return ret; } static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP if (val < -1 || val > sched_domain_level_max + 1) return -EINVAL; #endif if (val != cs->relax_domain_level) { cs->relax_domain_level = val; if (!cpumask_empty(cs->cpus_allowed) && is_sched_load_balance(cs)) rebuild_sched_domains_locked(); } return 0; } /** * update_tasks_flags - update the spread flags of tasks in the cpuset. * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this * function is called with cpuset_mutex held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) cpuset_update_task_spread_flag(cs, task); css_task_iter_end(&it); } /* * update_flag - read a 0 or a 1 in a file and update associated flag * bit: the bit to update (see cpuset_flagbits_t) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * * Call with cpuset_mutex held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on) { struct cpuset *trialcs; int balance_flag_changed; int spread_flag_changed; int err; trialcs = alloc_trial_cpuset(cs); if (!trialcs) return -ENOMEM; if (turning_on) set_bit(bit, &trialcs->flags); else clear_bit(bit, &trialcs->flags); err = validate_change(cs, trialcs); if (err < 0) goto out; balance_flag_changed = (is_sched_load_balance(cs) != is_sched_load_balance(trialcs)); spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) || (is_spread_page(cs) != is_spread_page(trialcs))); spin_lock_irq(&callback_lock); cs->flags = trialcs->flags; spin_unlock_irq(&callback_lock); if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) rebuild_sched_domains_locked(); if (spread_flag_changed) update_tasks_flags(cs); out: free_cpuset(trialcs); return err; } /* * update_prstate - update partititon_root_state * cs: the cpuset to update * new_prs: new partition root state * * Call with cpuset_mutex held. */ static int update_prstate(struct cpuset *cs, int new_prs) { int err, old_prs = cs->partition_root_state; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmpmask; if (old_prs == new_prs) return 0; /* * Cannot force a partial or invalid partition root to a full * partition root. */ if (new_prs && (old_prs == PRS_ERROR)) return -EINVAL; if (alloc_cpumasks(NULL, &tmpmask)) return -ENOMEM; err = -EINVAL; if (!old_prs) { /* * Turning on partition root requires setting the * CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed * cannot be NULL. */ if (cpumask_empty(cs->cpus_allowed)) goto out; err = update_flag(CS_CPU_EXCLUSIVE, cs, 1); if (err) goto out; err = update_parent_subparts_cpumask(cs, partcmd_enable, NULL, &tmpmask); if (err) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); goto out; } } else { /* * Turning off partition root will clear the * CS_CPU_EXCLUSIVE bit. */ if (old_prs == PRS_ERROR) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); err = 0; goto out; } err = update_parent_subparts_cpumask(cs, partcmd_disable, NULL, &tmpmask); if (err) goto out; /* Turning off CS_CPU_EXCLUSIVE will not return error */ update_flag(CS_CPU_EXCLUSIVE, cs, 0); } update_tasks_cpumask(parent); if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmpmask); rebuild_sched_domains_locked(); out: if (!err) { spin_lock_irq(&callback_lock); cs->partition_root_state = new_prs; spin_unlock_irq(&callback_lock); } free_cpumasks(NULL, &tmpmask); return err; } /* * Frequency meter - How fast is some event occurring? * * These routines manage a digitally filtered, constant time based, * event frequency meter. There are four routines: * fmeter_init() - initialize a frequency meter. * fmeter_markevent() - called each time the event happens. * fmeter_getrate() - returns the recent rate of such events. * fmeter_update() - internal routine used to update fmeter. * * A common data structure is passed to each of these routines, * which is used to keep track of the state required to manage the * frequency meter and its digital filter. * * The filter works on the number of events marked per unit time. * The filter is single-pole low-pass recursive (IIR). The time unit * is 1 second. Arithmetic is done using 32-bit integers scaled to * simulate 3 decimal digits of precision (multiplied by 1000). * * With an FM_COEF of 933, and a time base of 1 second, the filter * has a half-life of 10 seconds, meaning that if the events quit * happening, then the rate returned from the fmeter_getrate() * will be cut in half each 10 seconds, until it converges to zero. * * It is not worth doing a real infinitely recursive filter. If more * than FM_MAXTICKS ticks have elapsed since the last filter event, * just compute FM_MAXTICKS ticks worth, by which point the level * will be stable. * * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid * arithmetic overflow in the fmeter_update() routine. * * Given the simple 32 bit integer arithmetic used, this meter works * best for reporting rates between one per millisecond (msec) and * one per 32 (approx) seconds. At constant rates faster than one * per msec it maxes out at values just under 1,000,000. At constant * rates between one per msec, and one per second it will stabilize * to a value N*1000, where N is the rate of events per second. * At constant rates between one per second and one per 32 seconds, * it will be choppy, moving up on the seconds that have an event, * and then decaying until the next event. At rates slower than * about one in 32 seconds, it decays all the way back to zero between * each event. */ #define FM_COEF 933 /* coefficient for half-life of 10 secs */ #define FM_MAXTICKS ((u32)99) /* useless computing more ticks than this */ #define FM_MAXCNT 1000000 /* limit cnt to avoid overflow */ #define FM_SCALE 1000 /* faux fixed point scale */ /* Initialize a frequency meter */ static void fmeter_init(struct fmeter *fmp) { fmp->cnt = 0; fmp->val = 0; fmp->time = 0; spin_lock_init(&fmp->lock); } /* Internal meter update - process cnt events and update value */ static void fmeter_update(struct fmeter *fmp) { time64_t now; u32 ticks; now = ktime_get_seconds(); ticks = now - fmp->time; if (ticks == 0) return; ticks = min(FM_MAXTICKS, ticks); while (ticks-- > 0) fmp->val = (FM_COEF * fmp->val) / FM_SCALE; fmp->time = now; fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE; fmp->cnt = 0; } /* Process any previous ticks, then bump cnt by one (times scale). */ static void fmeter_markevent(struct fmeter *fmp) { spin_lock(&fmp->lock); fmeter_update(fmp); fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE); spin_unlock(&fmp->lock); } /* Process any previous ticks, then return current value. */ static int fmeter_getrate(struct fmeter *fmp) { int val; spin_lock(&fmp->lock); fmeter_update(fmp); val = fmp->val; spin_unlock(&fmp->lock); return val; } static struct cpuset *cpuset_attach_old_cs; static void reset_migrate_dl_data(struct cpuset *cs) { cs->nr_migrate_dl_tasks = 0; cs->sum_migrate_dl_bw = 0; } /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs, *oldcs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); oldcs = cpuset_attach_old_cs; cs = css_cs(css); mutex_lock(&cpuset_mutex); /* allow moving tasks into an empty cpuset if on default hierarchy */ ret = -ENOSPC; if (!is_in_v2_mode() && (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task); if (ret) goto out_unlock; ret = security_task_setscheduler(task); if (ret) goto out_unlock; if (dl_task(task)) { cs->nr_migrate_dl_tasks++; cs->sum_migrate_dl_bw += task->dl.dl_bw; } } if (!cs->nr_migrate_dl_tasks) goto out_success; if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) { int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus); if (unlikely(cpu >= nr_cpu_ids)) { reset_migrate_dl_data(cs); ret = -EINVAL; goto out_unlock; } ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw); if (ret) { reset_migrate_dl_data(cs); goto out_unlock; } } out_success: /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; ret = 0; out_unlock: mutex_unlock(&cpuset_mutex); return ret; } static void cpuset_cancel_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs; cgroup_taskset_first(tset, &css); cs = css_cs(css); mutex_lock(&cpuset_mutex); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); if (cs->nr_migrate_dl_tasks) { int cpu = cpumask_any(cs->effective_cpus); dl_bw_free(cpu, cs->sum_migrate_dl_bw); reset_migrate_dl_data(cs); } mutex_unlock(&cpuset_mutex); } /* * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ static cpumask_var_t cpus_attach; static void cpuset_attach(struct cgroup_taskset *tset) { /* static buf protected by cpuset_mutex */ static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; struct cgroup_subsys_state *css; struct cpuset *cs; struct cpuset *oldcs = cpuset_attach_old_cs; cgroup_taskset_first(tset, &css); cs = css_cs(css); lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ mutex_lock(&cpuset_mutex); /* prepare for attach */ if (cs == &top_cpuset) cpumask_copy(cpus_attach, cpu_possible_mask); else guarantee_online_cpus(cs, cpus_attach); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cgroup_taskset_for_each(task, css, tset) { /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here */ WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach)); cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to); cpuset_update_task_spread_flag(cs, task); } /* * Change mm for all threadgroup leaders. This is expensive and may * sleep and should be moved outside migration path proper. */ cpuset_attach_nodemask_to = cs->effective_mems; cgroup_taskset_for_each_leader(leader, css, tset) { struct mm_struct *mm = get_task_mm(leader); if (mm) { mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); /* * old_mems_allowed is the same with mems_allowed * here, except if this task is being moved * automatically due to hotplug. In that case * @mems_allowed has been updated and is empty, so * @old_mems_allowed is the right nodesets that we * migrate mm from. */ if (is_memory_migrate(cs)) cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, &cpuset_attach_nodemask_to); else mmput(mm); } } cs->old_mems_allowed = cpuset_attach_nodemask_to; if (cs->nr_migrate_dl_tasks) { cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks; oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks; reset_migrate_dl_data(cs); } cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); mutex_unlock(&cpuset_mutex); } /* The various types of files and directories in a cpuset file system */ typedef enum { FILE_MEMORY_MIGRATE, FILE_CPULIST, FILE_MEMLIST, FILE_EFFECTIVE_CPULIST, FILE_EFFECTIVE_MEMLIST, FILE_SUBPARTS_CPULIST, FILE_CPU_EXCLUSIVE, FILE_MEM_EXCLUSIVE, FILE_MEM_HARDWALL, FILE_SCHED_LOAD_BALANCE, FILE_PARTITION_ROOT, FILE_SCHED_RELAX_DOMAIN_LEVEL, FILE_MEMORY_PRESSURE_ENABLED, FILE_MEMORY_PRESSURE, FILE_SPREAD_PAGE, FILE_SPREAD_SLAB, } cpuset_filetype_t; static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = 0; get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) { retval = -ENODEV; goto out_unlock; } switch (type) { case FILE_CPU_EXCLUSIVE: retval = update_flag(CS_CPU_EXCLUSIVE, cs, val); break; case FILE_MEM_EXCLUSIVE: retval = update_flag(CS_MEM_EXCLUSIVE, cs, val); break; case FILE_MEM_HARDWALL: retval = update_flag(CS_MEM_HARDWALL, cs, val); break; case FILE_SCHED_LOAD_BALANCE: retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val); break; case FILE_MEMORY_MIGRATE: retval = update_flag(CS_MEMORY_MIGRATE, cs, val); break; case FILE_MEMORY_PRESSURE_ENABLED: cpuset_memory_pressure_enabled = !!val; break; case FILE_SPREAD_PAGE: retval = update_flag(CS_SPREAD_PAGE, cs, val); break; case FILE_SPREAD_SLAB: retval = update_flag(CS_SPREAD_SLAB, cs, val); break; default: retval = -EINVAL; break; } out_unlock: mutex_unlock(&cpuset_mutex); put_online_cpus(); return retval; } static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 val) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = -ENODEV; get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: retval = update_relax_domain_level(cs, val); break; default: retval = -EINVAL; break; } out_unlock: mutex_unlock(&cpuset_mutex); put_online_cpus(); return retval; } /* * Common handling for a write to a "cpus" or "mems" file. */ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); struct cpuset *trialcs; int retval = -ENODEV; buf = strstrip(buf); /* * CPU or memory hotunplug may leave @cs w/o any execution * resources, in which case the hotplug code asynchronously updates * configuration and transfers all tasks to the nearest ancestor * which can execute. * * As writes to "cpus" or "mems" may restore @cs's execution * resources, wait for the previously scheduled operations before * proceeding, so that we don't end up keep removing tasks added * after execution capability is restored. * * cpuset_hotplug_work calls back into cgroup core via * cgroup_transfer_tasks() and waiting for it from a cgroupfs * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after * grabbing cpuset_mutex anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); kernfs_break_active_protection(of->kn); flush_work(&cpuset_hotplug_work); get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; trialcs = alloc_trial_cpuset(cs); if (!trialcs) { retval = -ENOMEM; goto out_unlock; } switch (of_cft(of)->private) { case FILE_CPULIST: retval = update_cpumask(cs, trialcs, buf); break; case FILE_MEMLIST: retval = update_nodemask(cs, trialcs, buf); break; default: retval = -EINVAL; break; } free_cpuset(trialcs); out_unlock: mutex_unlock(&cpuset_mutex); put_online_cpus(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } /* * These ascii lists should be read in a single call, by using a user * buffer large enough to hold the entire map. If read in smaller * chunks, there is no guarantee of atomicity. Since the display format * used, list of ranges of sequential numbers, is variable length, * and since these maps can change value dynamically, one could read * gibberish by doing partial reads while a list was changing. */ static int cpuset_common_seq_show(struct seq_file *sf, void *v) { struct cpuset *cs = css_cs(seq_css(sf)); cpuset_filetype_t type = seq_cft(sf)->private; int ret = 0; spin_lock_irq(&callback_lock); switch (type) { case FILE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed)); break; case FILE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed)); break; case FILE_EFFECTIVE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus)); break; case FILE_EFFECTIVE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems)); break; case FILE_SUBPARTS_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->subparts_cpus)); break; default: ret = -EINVAL; } spin_unlock_irq(&callback_lock); return ret; } static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_CPU_EXCLUSIVE: return is_cpu_exclusive(cs); case FILE_MEM_EXCLUSIVE: return is_mem_exclusive(cs); case FILE_MEM_HARDWALL: return is_mem_hardwall(cs); case FILE_SCHED_LOAD_BALANCE: return is_sched_load_balance(cs); case FILE_MEMORY_MIGRATE: return is_memory_migrate(cs); case FILE_MEMORY_PRESSURE_ENABLED: return cpuset_memory_pressure_enabled; case FILE_MEMORY_PRESSURE: return fmeter_getrate(&cs->fmeter); case FILE_SPREAD_PAGE: return is_spread_page(cs); case FILE_SPREAD_SLAB: return is_spread_slab(cs); default: BUG(); } /* Unreachable but makes gcc happy */ return 0; } static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: return cs->relax_domain_level; default: BUG(); } /* Unrechable but makes gcc happy */ return 0; } static int sched_partition_show(struct seq_file *seq, void *v) { struct cpuset *cs = css_cs(seq_css(seq)); switch (cs->partition_root_state) { case PRS_ENABLED: seq_puts(seq, "root\n"); break; case PRS_DISABLED: seq_puts(seq, "member\n"); break; case PRS_ERROR: seq_puts(seq, "root invalid\n"); break; } return 0; } static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); int val; int retval = -ENODEV; buf = strstrip(buf); /* * Convert "root" to ENABLED, and convert "member" to DISABLED. */ if (!strcmp(buf, "root")) val = PRS_ENABLED; else if (!strcmp(buf, "member")) val = PRS_DISABLED; else return -EINVAL; css_get(&cs->css); get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; retval = update_prstate(cs, val); out_unlock: mutex_unlock(&cpuset_mutex); put_online_cpus(); css_put(&cs->css); return retval ?: nbytes; } /* * for the common functions, 'private' gives the type of file */ static struct cftype legacy_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, }, { .name = "effective_cpus", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "effective_mems", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpu_exclusive", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_CPU_EXCLUSIVE, }, { .name = "mem_exclusive", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEM_EXCLUSIVE, }, { .name = "mem_hardwall", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEM_HARDWALL, }, { .name = "sched_load_balance", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SCHED_LOAD_BALANCE, }, { .name = "sched_relax_domain_level", .read_s64 = cpuset_read_s64, .write_s64 = cpuset_write_s64, .private = FILE_SCHED_RELAX_DOMAIN_LEVEL, }, { .name = "memory_migrate", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_MIGRATE, }, { .name = "memory_pressure", .read_u64 = cpuset_read_u64, .private = FILE_MEMORY_PRESSURE, }, { .name = "memory_spread_page", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_PAGE, }, { .name = "memory_spread_slab", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_SLAB, }, { .name = "memory_pressure_enabled", .flags = CFTYPE_ONLY_ON_ROOT, .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_PRESSURE_ENABLED, }, { } /* terminate */ }; /* * This is currently a minimal set for the default hierarchy. It can be * expanded later on by migrating more features and control files from v1. */ static struct cftype dfl_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "mems.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpus.partition", .seq_show = sched_partition_show, .write = sched_partition_write, .private = FILE_PARTITION_ROOT, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.subpartitions", .seq_show = cpuset_common_seq_show, .private = FILE_SUBPARTS_CPULIST, .flags = CFTYPE_DEBUG, }, { } /* terminate */ }; /* * cpuset_css_alloc - allocate a cpuset css * cgrp: control group that the new cpuset will be part of */ static struct cgroup_subsys_state * cpuset_css_alloc(struct cgroup_subsys_state *parent_css) { struct cpuset *cs; if (!parent_css) return &top_cpuset.css; cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); if (alloc_cpumasks(cs, NULL)) { kfree(cs); return ERR_PTR(-ENOMEM); } set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); nodes_clear(cs->mems_allowed); nodes_clear(cs->effective_mems); fmeter_init(&cs->fmeter); cs->relax_domain_level = -1; return &cs->css; } static int cpuset_css_online(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); struct cpuset *parent = parent_cs(cs); struct cpuset *tmp_cs; struct cgroup_subsys_state *pos_css; if (!parent) return 0; get_online_cpus(); mutex_lock(&cpuset_mutex); set_bit(CS_ONLINE, &cs->flags); if (is_spread_page(parent)) set_bit(CS_SPREAD_PAGE, &cs->flags); if (is_spread_slab(parent)) set_bit(CS_SPREAD_SLAB, &cs->flags); cpuset_inc(); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(cs->effective_cpus, parent->effective_cpus); cs->effective_mems = parent->effective_mems; cs->use_parent_ecpus = true; parent->child_ecpus_count++; } spin_unlock_irq(&callback_lock); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; /* * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is * set. This flag handling is implemented in cgroup core for * histrical reasons - the flag may be specified during mount. * * Currently, if any sibling cpusets have exclusive cpus or mem, we * refuse to clone the configuration - thereby refusing the task to * be entered, and as a result refusing the sys_unshare() or * clone() which initiated it. If this becomes a problem for some * users who wish to allow that scenario, then this could be * changed to grant parent->cpus_allowed-sibling_cpus_exclusive * (and likewise for mems) to the new cgroup. */ rcu_read_lock(); cpuset_for_each_child(tmp_cs, pos_css, parent) { if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) { rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); spin_lock_irq(&callback_lock); cs->mems_allowed = parent->mems_allowed; cs->effective_mems = parent->mems_allowed; cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); cpumask_copy(cs->effective_cpus, parent->cpus_allowed); spin_unlock_irq(&callback_lock); out_unlock: mutex_unlock(&cpuset_mutex); put_online_cpus(); return 0; } /* * If the cpuset being removed has its flag 'sched_load_balance' * enabled, then simulate turning sched_load_balance off, which * will call rebuild_sched_domains_locked(). That is not needed * in the default hierarchy where only changes in partition * will cause repartitioning. * * If the cpuset has the 'sched.partition' flag enabled, simulate * turning 'sched.partition" off. */ static void cpuset_css_offline(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); get_online_cpus(); mutex_lock(&cpuset_mutex); if (is_partition_root(cs)) update_prstate(cs, 0); if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && is_sched_load_balance(cs)) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); if (cs->use_parent_ecpus) { struct cpuset *parent = parent_cs(cs); cs->use_parent_ecpus = false; parent->child_ecpus_count--; } cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); mutex_unlock(&cpuset_mutex); put_online_cpus(); } static void cpuset_css_free(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); free_cpuset(cs); } static void cpuset_bind(struct cgroup_subsys_state *root_css) { mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); top_cpuset.mems_allowed = node_possible_map; } else { cpumask_copy(top_cpuset.cpus_allowed, top_cpuset.effective_cpus); top_cpuset.mems_allowed = top_cpuset.effective_mems; } spin_unlock_irq(&callback_lock); mutex_unlock(&cpuset_mutex); } /* * Make sure the new task conform to the current state of its parent, * which could have been changed by cpuset just after it inherits the * state from the parent and before it sits on the cgroup's task list. */ static void cpuset_fork(struct task_struct *task) { if (task_css_is_root(task, cpuset_cgrp_id)) return; set_cpus_allowed_ptr(task, current->cpus_ptr); task->mems_allowed = current->mems_allowed; } struct cgroup_subsys cpuset_cgrp_subsys = { .css_alloc = cpuset_css_alloc, .css_online = cpuset_css_online, .css_offline = cpuset_css_offline, .css_free = cpuset_css_free, .can_attach = cpuset_can_attach, .cancel_attach = cpuset_cancel_attach, .attach = cpuset_attach, .post_attach = cpuset_post_attach, .bind = cpuset_bind, .fork = cpuset_fork, .legacy_cftypes = legacy_files, .dfl_cftypes = dfl_files, .early_init = true, .threaded = true, }; /** * cpuset_init - initialize cpusets at system boot * * Description: Initialize top_cpuset **/ int __init cpuset_init(void) { BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); cpumask_setall(top_cpuset.effective_cpus); nodes_setall(top_cpuset.effective_mems); fmeter_init(&top_cpuset.fmeter); set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); top_cpuset.relax_domain_level = -1; BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)); return 0; } /* * If CPU and/or memory hotplug handlers, below, unplug any CPUs * or memory nodes, we need to walk over the cpuset hierarchy, * removing that CPU or node from all cpusets. If this removes the * last CPU or node from a cpuset, then move the tasks in the empty * cpuset to its next-highest non-empty parent. */ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) { struct cpuset *parent; /* * Find its next-highest non-empty parent, (top cpuset * has online cpus, so can't be empty). */ parent = parent_cs(cs); while (cpumask_empty(parent->cpus_allowed) || nodes_empty(parent->mems_allowed)) parent = parent_cs(parent); if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) { pr_err("cpuset: failed to transfer tasks out of empty cpuset "); pr_cont_cgroup_name(cs->css.cgroup); pr_cont("\n"); } } static void hotplug_update_tasks_legacy(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { bool is_empty; spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, new_cpus); cpumask_copy(cs->effective_cpus, new_cpus); cs->mems_allowed = *new_mems; cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); /* * Don't call update_tasks_cpumask() if the cpuset becomes empty, * as the tasks will be migratecd to an ancestor. */ if (cpus_updated && !cpumask_empty(cs->cpus_allowed)) update_tasks_cpumask(cs); if (mems_updated && !nodes_empty(cs->mems_allowed)) update_tasks_nodemask(cs); is_empty = cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed); mutex_unlock(&cpuset_mutex); /* * Move tasks to the nearest ancestor with execution resources, * This is full cgroup operation which will also call back into * cpuset. Should be done outside any lock. */ if (is_empty) remove_tasks_in_empty_cpuset(cs); mutex_lock(&cpuset_mutex); } static void hotplug_update_tasks(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { if (cpumask_empty(new_cpus)) cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; spin_lock_irq(&callback_lock); cpumask_copy(cs->effective_cpus, new_cpus); cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); if (cpus_updated) update_tasks_cpumask(cs); if (mems_updated) update_tasks_nodemask(cs); } static bool force_rebuild; void cpuset_force_rebuild(void) { force_rebuild = true; } /** * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug * @cs: cpuset in interest * @tmp: the tmpmasks structure pointer * * Compare @cs's cpu and mem masks against top_cpuset and if some have gone * offline, update @cs accordingly. If @cs ends up with no CPU or memory, * all its tasks are moved to the nearest ancestor with both resources. */ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated; bool mems_updated; struct cpuset *parent; retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); mutex_lock(&cpuset_mutex); /* * We have raced with task attaching. We wait until attaching * is finished, so we won't attach a task to an empty cpuset. */ if (cs->attach_in_progress) { mutex_unlock(&cpuset_mutex); goto retry; } parent = parent_cs(cs); compute_effective_cpumask(&new_cpus, cs, parent); nodes_and(new_mems, cs->mems_allowed, parent->effective_mems); if (cs->nr_subparts_cpus) /* * Make sure that CPUs allocated to child partitions * do not show up in effective_cpus. */ cpumask_andnot(&new_cpus, &new_cpus, cs->subparts_cpus); if (!tmp || !cs->partition_root_state) goto update_tasks; /* * In the unlikely event that a partition root has empty * effective_cpus or its parent becomes erroneous, we have to * transition it to the erroneous state. */ if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || (parent->partition_root_state == PRS_ERROR))) { if (cs->nr_subparts_cpus) { spin_lock_irq(&callback_lock); cs->nr_subparts_cpus = 0; cpumask_clear(cs->subparts_cpus); spin_unlock_irq(&callback_lock); compute_effective_cpumask(&new_cpus, cs, parent); } /* * If the effective_cpus is empty because the child * partitions take away all the CPUs, we can keep * the current partition and let the child partitions * fight for available CPUs. */ if ((parent->partition_root_state == PRS_ERROR) || cpumask_empty(&new_cpus)) { update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); spin_lock_irq(&callback_lock); cs->partition_root_state = PRS_ERROR; spin_unlock_irq(&callback_lock); } cpuset_force_rebuild(); } /* * On the other hand, an erroneous partition root may be transitioned * back to a regular one or a partition root with no CPU allocated * from the parent may change to erroneous. */ if (is_partition_root(parent) && ((cs->partition_root_state == PRS_ERROR) || !cpumask_intersects(&new_cpus, parent->subparts_cpus)) && update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp)) cpuset_force_rebuild(); update_tasks: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); mems_updated = !nodes_equal(new_mems, cs->effective_mems); if (mems_updated) check_insane_mems_config(&new_mems); if (is_in_v2_mode()) hotplug_update_tasks(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); else hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); mutex_unlock(&cpuset_mutex); } /** * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset * * This function is called after either CPU or memory configuration has * changed and updates cpuset accordingly. The top_cpuset is always * synchronized to cpu_active_mask and N_MEMORY, which is necessary in * order to make cpusets transparent (of no affect) on systems that are * actively using CPU hotplug but making no active use of cpusets. * * Non-root cpusets are only affected by offlining. If any CPUs or memory * nodes have been taken down, cpuset_hotplug_update_tasks() is invoked on * all descendants. * * Note that CPU offlining during suspend is ignored. We don't modify * cpusets across suspend/resume cycles at all. */ static void cpuset_hotplug_workfn(struct work_struct *work) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; bool on_dfl = is_in_v2_mode(); struct tmpmasks tmp, *ptmp = NULL; if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp; mutex_lock(&cpuset_mutex); /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); new_mems = node_states[N_MEMORY]; /* * If subparts_cpus is populated, it is likely that the check below * will produce a false positive on cpus_updated when the cpu list * isn't changed. It is extra work, but it is better to be safe. */ cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus); mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); /* * In the rare case that hotplug removes all the cpus in subparts_cpus, * we assumed that cpus are updated. */ if (!cpus_updated && top_cpuset.nr_subparts_cpus) cpus_updated = true; /* synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); /* * Make sure that CPUs allocated to child partitions * do not show up in effective_cpus. If no CPU is left, * we clear the subparts_cpus & let the child partitions * fight for the CPUs again. */ if (top_cpuset.nr_subparts_cpus) { if (cpumask_subset(&new_cpus, top_cpuset.subparts_cpus)) { top_cpuset.nr_subparts_cpus = 0; cpumask_clear(top_cpuset.subparts_cpus); } else { cpumask_andnot(&new_cpus, &new_cpus, top_cpuset.subparts_cpus); } } cpumask_copy(top_cpuset.effective_cpus, &new_cpus); spin_unlock_irq(&callback_lock); /* we don't mess with cpumasks of tasks in top_cpuset */ } /* synchronize mems_allowed to N_MEMORY */ if (mems_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) top_cpuset.mems_allowed = new_mems; top_cpuset.effective_mems = new_mems; spin_unlock_irq(&callback_lock); update_tasks_nodemask(&top_cpuset); } mutex_unlock(&cpuset_mutex); /* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { struct cpuset *cs; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cs == &top_cpuset || !css_tryget_online(&cs->css)) continue; rcu_read_unlock(); cpuset_hotplug_update_tasks(cs, ptmp); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } /* rebuild sched domains if cpus_allowed has changed */ if (cpus_updated || force_rebuild) { force_rebuild = false; rebuild_sched_domains(); } free_cpumasks(NULL, ptmp); } void cpuset_update_active_cpus(void) { /* * We're inside cpu hotplug critical region which usually nests * inside cgroup synchronization. Bounce actual hotplug processing * to a work item to avoid reverse locking order. */ schedule_work(&cpuset_hotplug_work); } void cpuset_wait_for_hotplug(void) { flush_work(&cpuset_hotplug_work); } /* * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. * Call this routine anytime after node_states[N_MEMORY] changes. * See cpuset_update_active_cpus() for CPU hotplug handling. */ static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { schedule_work(&cpuset_hotplug_work); return NOTIFY_OK; } static struct notifier_block cpuset_track_online_nodes_nb = { .notifier_call = cpuset_track_online_nodes, .priority = 10, /* ??! */ }; /** * cpuset_init_smp - initialize cpus_allowed * * Description: Finish top cpuset after cpu, node maps are initialized */ void __init cpuset_init_smp(void) { /* * cpus_allowd/mems_allowed set to v2 values in the initial * cpuset_bind() call will be reset to v1 values in another * cpuset_bind() call when v1 cpuset is mounted. */ top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); top_cpuset.effective_mems = node_states[N_MEMORY]; register_hotmemory_notifier(&cpuset_track_online_nodes_nb); cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); BUG_ON(!cpuset_migrate_mm_wq); } /** * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. * * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of cpu_online_mask, even if this means going outside the * tasks cpuset. **/ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { unsigned long flags; spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_cpus(task_cs(tsk), pmask); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); } /** * cpuset_cpus_allowed_fallback - final fallback before complete catastrophe. * @tsk: pointer to task_struct with which the scheduler is struggling * * Description: In the case that the scheduler cannot find an allowed cpu in * tsk->cpus_allowed, we fall back to task_cs(tsk)->cpus_allowed. In legacy * mode however, this value is the same as task_cs(tsk)->effective_cpus, * which will not contain a sane cpumask during cases such as cpu hotplugging. * This is the absolute last resort for the scheduler and it is only used if * _every_ other avenue has been traveled. **/ void cpuset_cpus_allowed_fallback(struct task_struct *tsk) { rcu_read_lock(); do_set_cpus_allowed(tsk, is_in_v2_mode() ? task_cs(tsk)->cpus_allowed : cpu_possible_mask); rcu_read_unlock(); /* * We own tsk->cpus_allowed, nobody can change it under us. * * But we used cs && cs->cpus_allowed lockless and thus can * race with cgroup_attach_task() or update_cpumask() and get * the wrong tsk->cpus_allowed. However, both cases imply the * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr() * which takes task_rq_lock(). * * If we are called after it dropped the lock we must see all * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary * set any mask even if it is not right from task_cs() pov, * the pending set_cpus_allowed_ptr() will fix things. * * select_fallback_rq() will fix things ups and set cpu_possible_mask * if required. */ } void __init cpuset_init_current_mems_allowed(void) { nodes_setall(current->mems_allowed); } /** * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed. * * Description: Returns the nodemask_t mems_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of node_states[N_MEMORY], even if this means going outside the * tasks cpuset. **/ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) { nodemask_t mask; unsigned long flags; spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_mems(task_cs(tsk), &mask); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); return mask; } /** * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed * @nodemask: the nodemask to be checked * * Are any of the nodes in the nodemask allowed in current->mems_allowed? */ int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return nodes_intersects(*nodemask, current->mems_allowed); } /* * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or * mem_hardwall ancestor to the specified cpuset. Call holding * callback_lock. If no ancestor is mem_exclusive or mem_hardwall * (an unusual configuration), then returns the root cpuset. */ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) { while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && parent_cs(cs)) cs = parent_cs(cs); return cs; } /** * cpuset_node_allowed - Can we allocate on a memory node? * @node: is this an allowed node? * @gfp_mask: memory allocation flags * * If we're in interrupt, yes, we can always allocate. If @node is set in * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, * yes. If current has access to memory reserves as an oom victim, yes. * Otherwise, no. * * GFP_USER allocations are marked with the __GFP_HARDWALL bit, * and do not allow allocations outside the current tasks cpuset * unless the task has been OOM killed. * GFP_KERNEL allocations are not so marked, so can escape to the * nearest enclosing hardwalled ancestor cpuset. * * Scanning up parent cpusets requires callback_lock. The * __alloc_pages() routine only calls here with __GFP_HARDWALL bit * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the * current tasks mems_allowed came up empty on the first pass over * the zonelist. So only GFP_KERNEL allocations, if all nodes in the * cpuset are short of memory, might require taking the callback_lock. * * The first call here from mm/page_alloc:get_page_from_freelist() * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, * so no allocation on a node outside the cpuset is allowed (unless * in interrupt, of course). * * The second pass through get_page_from_freelist() doesn't even call * here for GFP_ATOMIC calls. For those calls, the __alloc_pages() * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set * in alloc_flags. That logic and the checks below have the combined * affect that: * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok * tsk_is_oom_victim - any node ok * GFP_KERNEL - any node in enclosing hardwalled cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. */ bool __cpuset_node_allowed(int node, gfp_t gfp_mask) { struct cpuset *cs; /* current cpuset ancestors */ int allowed; /* is allocation in zone z allowed? */ unsigned long flags; if (in_interrupt()) return true; if (node_isset(node, current->mems_allowed)) return true; /* * Allow tasks that have access to memory reserves because they have * been OOM killed to get memory anywhere. */ if (unlikely(tsk_is_oom_victim(current))) return true; if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ return false; if (current->flags & PF_EXITING) /* Let dying task have memory */ return true; /* Not hardwall and node outside mems_allowed: scan up cpusets */ spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); cs = nearest_hardwall_ancestor(task_cs(current)); allowed = node_isset(node, cs->mems_allowed); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); return allowed; } /** * cpuset_mem_spread_node() - On which node to begin search for a file page * cpuset_slab_spread_node() - On which node to begin search for a slab page * * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for * tasks in a cpuset with is_spread_page or is_spread_slab set), * and if the memory allocation used cpuset_mem_spread_node() * to determine on which node to start looking, as it will for * certain page cache or slab cache pages such as used for file * system buffers and inode caches, then instead of starting on the * local node to look for a free page, rather spread the starting * node around the tasks mems_allowed nodes. * * We don't have to worry about the returned node being offline * because "it can't happen", and even if it did, it would be ok. * * The routines calling guarantee_online_mems() are careful to * only set nodes in task->mems_allowed that are online. So it * should not be possible for the following code to return an * offline node. But if it did, that would be ok, as this routine * is not returning the node where the allocation must be, only * the node where the search should start. The zonelist passed to * __alloc_pages() will include all nodes. If the slab allocator * is passed an offline node, it will fall back to the local node. * See kmem_cache_alloc_node(). */ static int cpuset_spread_node(int *rotor) { return *rotor = next_node_in(*rotor, current->mems_allowed); } int cpuset_mem_spread_node(void) { if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) current->cpuset_mem_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } int cpuset_slab_spread_node(void) { if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) current->cpuset_slab_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); } EXPORT_SYMBOL_GPL(cpuset_mem_spread_node); /** * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's? * @tsk1: pointer to task_struct of some task. * @tsk2: pointer to task_struct of some other task. * * Description: Return true if @tsk1's mems_allowed intersects the * mems_allowed of @tsk2. Used by the OOM killer to determine if * one of the task's memory usage might impact the memory available * to the other. **/ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); } /** * cpuset_print_current_mems_allowed - prints current's cpuset and mems_allowed * * Description: Prints current's name, cpuset name, and cached copy of its * mems_allowed to the kernel log. */ void cpuset_print_current_mems_allowed(void) { struct cgroup *cgrp; rcu_read_lock(); cgrp = task_cs(current)->css.cgroup; pr_cont(",cpuset="); pr_cont_cgroup_name(cgrp); pr_cont(",mems_allowed=%*pbl", nodemask_pr_args(¤t->mems_allowed)); rcu_read_unlock(); } /* * Collection of memory_pressure is suppressed unless * this flag is enabled by writing "1" to the special * cpuset file 'memory_pressure_enabled' in the root cpuset. */ int cpuset_memory_pressure_enabled __read_mostly; /** * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. * * Keep a running average of the rate of synchronous (direct) * page reclaim efforts initiated by tasks in each cpuset. * * This represents the rate at which some task in the cpuset * ran low on memory on all nodes it was allowed to use, and * had to enter the kernels page reclaim code in an effort to * create more free memory by tossing clean pages or swapping * or writing dirty pages. * * Display to user space in the per-cpuset read-only file * "memory_pressure". Value displayed is an integer * representing the recent rate of entry into the synchronous * (direct) page reclaim by any task attached to the cpuset. **/ void __cpuset_memory_pressure_bump(void) { rcu_read_lock(); fmeter_markevent(&task_cs(current)->fmeter); rcu_read_unlock(); } #ifdef CONFIG_PROC_PID_CPUSET /* * proc_cpuset_show() * - Print tasks cpuset path into seq_file. * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, * and we take cpuset_mutex, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { char *buf; struct cgroup_subsys_state *css; int retval; retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; rcu_read_lock(); spin_lock_irq(&css_set_lock); css = task_css(tsk, cpuset_cgrp_id); retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX, current->nsproxy->cgroup_ns); spin_unlock_irq(&css_set_lock); rcu_read_unlock(); if (retval >= PATH_MAX) retval = -ENAMETOOLONG; if (retval < 0) goto out_free; seq_puts(m, buf); seq_putc(m, '\n'); retval = 0; out_free: kfree(buf); out: return retval; } #endif /* CONFIG_PROC_PID_CPUSET */ /* Display task mems_allowed in /proc/<pid>/status file. */ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Mems_allowed:\t%*pb\n", nodemask_pr_args(&task->mems_allowed)); seq_printf(m, "Mems_allowed_list:\t%*pbl\n", nodemask_pr_args(&task->mems_allowed)); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <net/sock.h> #include <linux/init_task.h> #include "internal.h" unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) #define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int copy_words) { unsigned int nwords = fdt_words(nfdt); bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, copy_words, nwords); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". */ static struct fdtable *alloc_fdtable(unsigned int slots_wanted) { struct fdtable *fdt; unsigned int nr; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. Since we called only * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab * already gives BITS_PER_LONG slots), the above boils down to * 1. use the smallest power of two large enough to give us that many * slots. * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is * 256 slots (i.e. 1Kb fd array). * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there * and we are never going to be asked for 64 or less. */ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256) nr = 256; else nr = roundup_pow_of_two(slots_wanted); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) { nr = round_down(sysctl_nr_open, BITS_PER_LONG); if (nr < slots_wanted) return ERR_PTR(-EMFILE); } /* * Check if the allocation size would exceed INT_MAX. kvmalloc_array() * and kvmalloc() will warn if the allocation size is greater than * INT_MAX, as filp_cachep objects are not __GFP_NOWARN. * * This can happen when sysctl_nr_open is set to a very high value and * a process tries to use a file descriptor near that limit. For example, * if sysctl_nr_open is set to 1073741816 (0x3ffffff8) - which is what * systemd typically sets it to - then trying to use a file descriptor * close to that value will require allocating a file descriptor table * that exceeds 8GB in size. */ if (unlikely(nr > INT_MAX / sizeof(struct file *))) return ERR_PTR(-EMFILE); fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return ERR_PTR(-ENOMEM); } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 1 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr + 1); /* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (IS_ERR(new_fdt)) return PTR_ERR(new_fdt); cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */ smp_wmb(); return 1; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 when nothing done; 1 when files were * expanded and execution may have blocked. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int expanded = 0; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return expanded; /* Can we expand? */ if (nr >= sysctl_nr_open) return -EMFILE; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); expanded = 1; wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* All good, so we try */ files->resize_in_progress = true; expanded = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return expanded; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->close_on_exec); } static inline void __clear_close_on_exec(unsigned int fd, struct fdtable *fdt) { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt) { __set_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); __clear_bit(fd / BITS_PER_LONG, fdt->full_fds_bits); } static unsigned int count_open_files(struct fdtable *fdt) { unsigned int size = fdt->max_fds; unsigned int i; /* Find the last open fd */ for (i = size / BITS_PER_LONG; i > 0; ) { if (fdt->open_fds[--i]) break; } i = (i + 1) * BITS_PER_LONG; return i; } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * 'max_fds' will normally already be properly aligned, but it * turns out that in the close_range() -> __close_range() -> * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end * up having a 'max_fds' value that isn't already aligned. * * Rather than make close_range() have to worry about this, * just make that BITS_PER_LONG alignment be part of a sane * fdtable size. Becuase that's really what it is. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds) { unsigned int count; count = count_open_files(fdt); if (max_fds < NR_OPEN_DEFAULT) max_fds = NR_OPEN_DEFAULT; return ALIGN(min(count, max_fds), BITS_PER_LONG); } /* * Allocate a new files structure and copy contents from the * passed in files structure. * errorp will be valid only when the returned files_struct is NULL. */ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; *errorp = -ENOMEM; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) goto out; atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files); if (IS_ERR(new_fdt)) { *errorp = PTR_ERR(new_fdt); goto out_release; } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, max_fds); } copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; for (i = open_files; i != 0; i--) { struct file *f = *old_fds++; if (f) { get_file(f); } else { /* * The fd may be claimed in the fd bitmap but not yet * instantiated in the files array if a sibling thread * is partway through open(). So make sure that this * fd is available to the new process. */ __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; out_release: kmem_cache_free(files_cachep, newf); out: return NULL; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file * file = xchg(&fdt->fd[i], NULL); if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } struct files_struct *get_files_struct(struct task_struct *task) { struct files_struct *files; task_lock(task); files = task->files; if (files) atomic_inc(&files->count); task_unlock(task); return files; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */ unsigned int maxbit = maxfd / BITS_PER_LONG; unsigned int bitbit = start / BITS_PER_LONG; bitbit = find_next_zero_bit(fdt->full_fds_bits, maxbit, bitbit) * BITS_PER_LONG; if (bitbit >= maxfd) return maxfd; if (bitbit > start) start = bitbit; return find_next_zero_bit(fdt->open_fds, maxfd, start); } /* * allocate a file descriptor, mark it busy. */ static int alloc_fd(unsigned start, unsigned end, unsigned flags) { struct files_struct *files = current->files; unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (fd < fdt->max_fds) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (fd >= end) goto out; error = expand_files(files, fd); if (error < 0) goto out; /* * If we needed to expand the fs array we * might have blocked - try again. */ if (error) goto repeat; if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); error = fd; #if 1 /* Sanity check */ if (rcu_access_pointer(fdt->fd[fd]) != NULL) { printk(KERN_WARNING "alloc_fd: slot %d not NULL!\n", fd); rcu_assign_pointer(fdt->fd[fd], NULL); } #endif out: spin_unlock(&files->file_lock); return error; } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return alloc_fd(0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array. * * The VFS is full of places where we drop the files lock between * setting the open_fds bitmap and installing the file in the file * array. At any such point, we are vulnerable to a dup2() race * installing a file in the array before us. We need to detect this and * fput() the struct file we are about to overwrite in this case. * * It should never happen - if we allow dup2() do it, _really_ bad things * will follow. * * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); BUG_ON(fdt->fd[fd] != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } EXPORT_SYMBOL(fd_install); static struct file *pick_file(struct files_struct *files, unsigned fd) { struct file *file = NULL; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_unlock; fd = array_index_nospec(fd, fdt->max_fds); file = fdt->fd[fd]; if (!file) goto out_unlock; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); out_unlock: spin_unlock(&files->file_lock); return file; } int close_fd(unsigned fd) { struct files_struct *files = current->files; struct file *file; file = pick_file(files, fd); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(close_fd); /* for ksys_close() */ /** * __close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. */ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags) { unsigned int cur_max; struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~CLOSE_RANGE_UNSHARE) return -EINVAL; if (fd > max_fd) return -EINVAL; rcu_read_lock(); cur_max = files_fdtable(cur_fds)->max_fds; rcu_read_unlock(); /* cap to last valid index into fdtable */ cur_max--; if (flags & CLOSE_RANGE_UNSHARE) { int ret; unsigned int max_unshare_fds = NR_OPEN_MAX; /* * If the requested range is greater than the current maximum, * we're closing everything so only copy all file descriptors * beneath the lowest file descriptor. */ if (max_fd >= cur_max) max_unshare_fds = fd; ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds); if (ret) return ret; /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ if (fds) swap(cur_fds, fds); } max_fd = min(max_fd, cur_max); while (fd <= max_fd) { struct file *file; file = pick_file(cur_fds, fd++); if (!file) continue; filp_close(file, cur_fds); cond_resched(); } if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /* * See close_fd_get_file() below, this variant assumes current->files->file_lock * is held. */ int __close_fd_get_file(unsigned int fd, struct file **res) { struct files_struct *files = current->files; struct file *file; struct fdtable *fdt; fdt = files_fdtable(files); if (fd >= fdt->max_fds) goto out_err; file = fdt->fd[fd]; if (!file) goto out_err; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); get_file(file); *res = file; return 0; out_err: *res = NULL; return -ENOENT; } /* * variant of close_fd that gets a ref on the file for later fput. * The caller must ensure that filp_close() called on the file, and then * an fput(). */ int close_fd_get_file(unsigned int fd, struct file **res) { struct files_struct *files = current->files; int ret; spin_lock(&files->file_lock); ret = __close_fd_get_file(fd, res); spin_unlock(&files->file_lock); return ret; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask, unsigned int refs) { struct file *file; rcu_read_lock(); loop: file = files_lookup_fd_rcu(files, fd); if (file) { /* File object ref couldn't be taken. * dup2() atomicity guarantee is the reason * we loop to catch the new file (or NULL pointer) */ if (file->f_mode & mask) file = NULL; else if (!get_file_rcu_many(file, refs)) goto loop; else if (files_lookup_fd_raw(files, fd) != file) { fput_many(file, refs); goto loop; } } rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs) { return __fget_files(current->files, fd, mask, refs); } struct file *fget_many(unsigned int fd, unsigned int refs) { return __fget(fd, FMODE_PATH, refs); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH, 1); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0, 1); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0, 1); task_unlock(task); return file; } struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; struct file *file = NULL; task_lock(task); files = task->files; if (files) file = files_lookup_fd_rcu(files, fd); task_unlock(task); return file; } struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *ret_fd) { /* Must be called with rcu_read_lock held */ struct files_struct *files; unsigned int fd = *ret_fd; struct file *file = NULL; task_lock(task); files = task->files; if (files) { for (; fd < files_fdtable(files)->max_fds; fd++) { file = files_lookup_fd_rcu(files, fd); if (file) break; } } task_unlock(task); *ret_fd = fd; return file; } /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. */ static unsigned long __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; if (atomic_read(&files->count) == 1) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return 0; return (unsigned long)file; } else { file = __fget(fd, mask, 1); if (!file) return 0; return FDPUT_FPUT | (unsigned long)file; } } unsigned long __fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(__fdget); unsigned long __fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } /* * Try to avoid f_pos locking. We only need it if the * file is marked for FMODE_ATOMIC_POS, and it can be * accessed multiple ways. * * Always do it for directories, because pidfd_getfd() * can make a file accessible even if it otherwise would * not be, and for directories this is a correctness * issue, not a "POSIX requirement". */ static inline bool file_needs_f_pos_lock(struct file *file) { return (file->f_mode & FMODE_ATOMIC_POS) && (file_count(file) > 1 || S_ISDIR(file_inode(file)->i_mode)); } unsigned long __fdget_pos(unsigned int fd) { unsigned long v = __fdget(fd); struct file *file = (struct file *)(v & ~3); if (file && file_needs_f_pos_lock(file)) { v |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } return v; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); if (flag) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { struct files_struct *files = current->files; struct fdtable *fdt; bool res; rcu_read_lock(); fdt = files_fdtable(files); res = close_on_exec(fd, fdt); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * We need to detect attempts to do dup2() over allocated but still * not finished descriptor. NB: OpenBSD avoids that at the price of * extra work in their equivalent of fget() - they insert struct * file immediately after grabbing descriptor, mark it larval if * more work (e.g. actual opening) is needed and make sure that * fget() treats larval files as absent. Potentially interesting, * but while extra work in fget() is trivial, locking implications * and amount of surgery on open()-related paths in VFS are not. * FreeBSD fails with -EBADF in the same situation, NetBSD "solution" * deadlocks in rather amusing ways, AFAICS. All of that is out of * scope of POSIX or SUS, since neither considers shared descriptor * tables and this condition does not arise without those. */ fdt = files_fdtable(files); fd = array_index_nospec(fd, fdt->max_fds); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt); if (flags & O_CLOEXEC) __set_close_on_exec(fd, fdt); else __clear_close_on_exec(fd, fdt); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return close_fd(fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; return do_dup2(files, file, fd, flags); out_unlock: spin_unlock(&files->file_lock); return err; } /** * __receive_fd() - Install received file into file descriptor table * * @fd: fd to install into (if negative, a new fd will be allocated) * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags) { int new_fd; int error; error = security_file_receive(file); if (error) return error; if (fd < 0) { new_fd = get_unused_fd_flags(o_flags); if (new_fd < 0) return new_fd; } else { new_fd = fd; } if (ufd) { error = put_user(new_fd, ufd); if (error) { if (fd < 0) put_unused_fd(new_fd); return error; } } if (fd < 0) { fd_install(new_fd, get_file(file)); } else { error = replace_fd(new_fd, file, o_flags); if (error) return error; } /* Bump the sock usage counts, if any. */ __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = files_lookup_fd_locked(files, oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; int retval = oldfd; rcu_read_lock(); if (!files_lookup_fd_rcu(files, oldfd)) retval = -EBADF; rcu_read_unlock(); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { unsigned long nofile = rlimit(RLIMIT_NOFILE); int err; if (from >= nofile) return -EINVAL; err = alloc_fd(from, nofile, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMSTAT_H #define _LINUX_VMSTAT_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/mmzone.h> #include <linux/vm_event_item.h> #include <linux/atomic.h> #include <linux/static_key.h> #include <linux/mmdebug.h> extern int sysctl_stat_interval; #ifdef CONFIG_NUMA #define ENABLE_NUMA_STAT 1 #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); #endif struct reclaim_stat { unsigned nr_dirty; unsigned nr_unqueued_dirty; unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; unsigned nr_pageout; unsigned nr_activate[ANON_AND_FILE]; unsigned nr_ref_keep; unsigned nr_unmap_fail; unsigned nr_lazyfree_fail; }; enum writeback_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, NR_VM_WRITEBACK_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. * * Counters should only be incremented and no critical kernel component * should rely on the counter values. * * Counters are handled completely inline. On many platforms the code * generated will simply be the increment of a global address. */ struct vm_event_state { unsigned long event[NR_VM_EVENT_ITEMS]; }; DECLARE_PER_CPU(struct vm_event_state, vm_event_states); /* * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the * local_irq_disable overhead. */ static inline void __count_vm_event(enum vm_event_item item) { raw_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) { this_cpu_inc(vm_event_states.event[item]); } static inline void __count_vm_events(enum vm_event_item item, long delta) { raw_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) { this_cpu_add(vm_event_states.event[item], delta); } extern void all_vm_events(unsigned long *); extern void vm_events_fold_cpu(int cpu); #else /* Disable counters */ static inline void count_vm_event(enum vm_event_item item) { } static inline void count_vm_events(enum vm_event_item item, long delta) { } static inline void __count_vm_event(enum vm_event_item item) { } static inline void __count_vm_events(enum vm_event_item item, long delta) { } static inline void all_vm_events(unsigned long *ret) { } static inline void vm_events_fold_cpu(int cpu) { } #endif /* CONFIG_VM_EVENT_COUNTERS */ #ifdef CONFIG_NUMA_BALANCING #define count_vm_numa_event(x) count_vm_event(x) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_DEBUG_TLBFLUSH #define count_vm_tlb_event(x) count_vm_event(x) #define count_vm_tlb_events(x, y) count_vm_events(x, y) #else #define count_vm_tlb_event(x) do {} while (0) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif #ifdef CONFIG_DEBUG_VM_VMACACHE #define count_vm_vmacache_event(x) count_vm_event(x) #else #define count_vm_vmacache_event(x) do {} while (0) #endif #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) /* * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; #ifdef CONFIG_NUMA static inline void zone_numa_state_add(long x, struct zone *zone, enum numa_stat_item item) { atomic_long_add(x, &zone->vm_numa_stat[item]); atomic_long_add(x, &vm_numa_stat[item]); } static inline unsigned long global_numa_state(enum numa_stat_item item) { long x = atomic_long_read(&vm_numa_stat[item]); return x; } static inline unsigned long zone_numa_state_snapshot(struct zone *zone, enum numa_stat_item item) { long x = atomic_long_read(&zone->vm_numa_stat[item]); int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item]; return x; } #endif /* CONFIG_NUMA */ static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { atomic_long_add(x, &zone->vm_stat[item]); atomic_long_add(x, &vm_zone_stat[item]); } static inline void node_page_state_add(long x, struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_add(x, &pgdat->vm_stat[item]); atomic_long_add(x, &vm_node_stat[item]); } static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state_pages(enum node_stat_item item) { long x = atomic_long_read(&vm_node_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state(enum node_stat_item item) { VM_WARN_ON_ONCE(vmstat_item_in_bytes(item)); return global_node_page_state_pages(item); } static inline unsigned long zone_page_state(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * More accurate version that also considers the currently pending * deltas. For that we need to loop over all cpus to find the current * deltas. There is no synchronization so the result cannot be * exactly accurate either. */ static inline unsigned long zone_page_state_snapshot(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; #endif return x; } #ifdef CONFIG_NUMA extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item); extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long); void __inc_node_page_state(struct page *, enum node_stat_item); void __dec_node_page_state(struct page *, enum node_stat_item); void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); void mod_node_page_state(struct pglist_data *, enum node_stat_item, long); void inc_node_page_state(struct page *, enum node_stat_item); void dec_node_page_state(struct page *, enum node_stat_item); extern void inc_node_state(struct pglist_data *, enum node_stat_item); extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void __inc_node_state(struct pglist_data *, enum node_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_node_state(struct pglist_data *, enum node_stat_item); void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); void set_pgdat_percpu_threshold(pg_data_t *pgdat, int (*calculate_pressure)(struct zone *)); #else /* CONFIG_SMP */ /* * We do not maintain differentials in a single processor configuration. * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { if (vmstat_item_in_bytes(item)) { VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); delta >>= PAGE_SHIFT; } node_page_state_add(delta, pgdat, item); } static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_inc(&zone->vm_stat[item]); atomic_long_inc(&vm_zone_stat[item]); } static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_inc(&pgdat->vm_stat[item]); atomic_long_inc(&vm_node_stat[item]); } static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_dec(&zone->vm_stat[item]); atomic_long_dec(&vm_zone_stat[item]); } static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_dec(&pgdat->vm_stat[item]); atomic_long_dec(&vm_node_stat[item]); } static inline void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } static inline void __inc_node_page_state(struct page *page, enum node_stat_item item) { __inc_node_state(page_pgdat(page), item); } static inline void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } static inline void __dec_node_page_state(struct page *page, enum node_stat_item item) { __dec_node_state(page_pgdat(page), item); } /* * We only use atomic operations to update counters. So there is no need to * disable interrupts. */ #define inc_zone_page_state __inc_zone_page_state #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state #define inc_node_page_state __inc_node_page_state #define dec_node_page_state __dec_node_page_state #define mod_node_page_state __mod_node_page_state #define inc_zone_state __inc_zone_state #define inc_node_state __inc_node_state #define dec_zone_state __dec_zone_state #define set_pgdat_percpu_threshold(pgdat, callback) { } static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) { } #endif /* CONFIG_SMP */ static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, int migratetype) { __mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages); if (is_migrate_cma(migratetype)) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); } extern const char * const vmstat_text[]; static inline const char *zone_stat_name(enum zone_stat_item item) { return vmstat_text[item]; } #ifdef CONFIG_NUMA static inline const char *numa_stat_name(enum numa_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + item]; } #endif /* CONFIG_NUMA */ static inline const char *node_stat_name(enum node_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_STAT_ITEMS + item]; } static inline const char *lru_list_name(enum lru_list lru) { return node_stat_name(NR_LRU_BASE + (enum node_stat_item)lru) + 3; // skip "nr_" } static inline const char *writeback_stat_name(enum writeback_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_STAT_ITEMS + NR_VM_NODE_STAT_ITEMS + item]; } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_STAT_ITEMS + NR_VM_NODE_STAT_ITEMS + NR_VM_WRITEBACK_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ #endif /* _LINUX_VMSTAT_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel timekeeping code and accessor functions. Based on code from * timer.c, moved in commit 8524070b7982. */ #include <linux/timekeeper_internal.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/nmi.h> #include <linux/sched.h> #include <linux/sched/loadavg.h> #include <linux/sched/clock.h> #include <linux/syscore_ops.h> #include <linux/clocksource.h> #include <linux/jiffies.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> #include <linux/compiler.h> #include <linux/audit.h> #include <linux/random.h> #include "tick-internal.h" #include "ntp_internal.h" #include "timekeeping_internal.h" #define TK_CLEAR_NTP (1 << 0) #define TK_MIRROR (1 << 1) #define TK_CLOCK_WAS_SET (1 << 2) enum timekeeping_adv_mode { /* Update timekeeper when a tick has passed */ TK_ADV_TICK, /* Update timekeeper on a direct frequency change */ TK_ADV_FREQ }; DEFINE_RAW_SPINLOCK(timekeeper_lock); /* * The most important data for readout fits into a single 64 byte * cache line. */ static struct { seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; } tk_core ____cacheline_aligned = { .seq = SEQCNT_RAW_SPINLOCK_ZERO(tk_core.seq, &timekeeper_lock), }; static struct timekeeper shadow_timekeeper; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; /** * struct tk_fast - NMI safe timekeeper * @seq: Sequence counter for protecting updates. The lowest bit * is the index for the tk_read_base array * @base: tk_read_base array. Access is indexed by the lowest bit of * @seq. * * See @update_fast_timekeeper() below. */ struct tk_fast { seqcount_latch_t seq; struct tk_read_base base[2]; }; /* Suspend-time cycles value for halted fast timekeeper. */ static u64 cycles_at_suspend; static u64 dummy_clock_read(struct clocksource *cs) { if (timekeeping_suspended) return cycles_at_suspend; return local_clock(); } static struct clocksource dummy_clock = { .read = dummy_clock_read, }; /* * Boot time initialization which allows local_clock() to be utilized * during early boot when clocksources are not available. local_clock() * returns nanoseconds already so no conversion is required, hence mult=1 * and shift=0. When the first proper clocksource is installed then * the fast time keepers are updated with the correct values. */ #define FAST_TK_INIT \ { \ .clock = &dummy_clock, \ .mask = CLOCKSOURCE_MASK(64), \ .mult = 1, \ .shift = 0, \ } static struct tk_fast tk_fast_mono ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static struct tk_fast tk_fast_raw ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) { tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift; tk->raw_sec++; } } static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp)); tk->wall_to_monotonic = wtm; set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); tk->offs_real = timespec64_to_ktime(tmp); tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0)); } static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { tk->offs_boot = ktime_add(tk->offs_boot, delta); /* * Timespec representation for VDSO update to avoid 64bit division * on every update. */ tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot); } /* * tk_clock_read - atomic clocksource read() helper * * This helper is necessary to use in the read paths because, while the * seqcount ensures we don't return a bad value while structures are updated, * it doesn't protect from potential crashes. There is the possibility that * the tkr's clocksource may change between the read reference, and the * clock reference passed to the read function. This can cause crashes if * the wrong clocksource is passed to the wrong read function. * This isn't necessary to use when holding the timekeeper_lock or doing * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); return clock->read(clock); } #ifdef CONFIG_DEBUG_TIMEKEEPING #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ static void timekeeping_check_update(struct timekeeper *tk, u64 offset) { u64 max_cycles = tk->tkr_mono.clock->max_cycles; const char *name = tk->tkr_mono.clock->name; if (offset > max_cycles) { printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n", offset, name, max_cycles); printk_deferred(" timekeeping: Your kernel is sick, but tries to cope by capping time updates\n"); } else { if (offset > (max_cycles >> 1)) { printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the '%s' clock's 50%% safety margin (%lld)\n", offset, name, max_cycles >> 1); printk_deferred(" timekeeping: Your kernel is still fine, but is feeling a bit nervous\n"); } } if (tk->underflow_seen) { if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); tk->last_warning = jiffies; } tk->underflow_seen = 0; } if (tk->overflow_seen) { if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); tk->last_warning = jiffies; } tk->overflow_seen = 0; } } static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { struct timekeeper *tk = &tk_core.timekeeper; u64 now, last, mask, max, delta; unsigned int seq; /* * Since we're called holding a seqcount, the data may shift * under us while we're doing the calculation. This can cause * false positives, since we'd note a problem but throw the * results away. So nest another seqcount here to atomically * grab the points we are checking with. */ do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(tkr); last = tkr->cycle_last; mask = tkr->mask; max = tkr->clock->max_cycles; } while (read_seqcount_retry(&tk_core.seq, seq)); delta = clocksource_delta(now, last, mask); /* * Try to catch underflows by checking if we are seeing small * mask-relative negative values. */ if (unlikely((~delta & mask) < (mask >> 3))) { tk->underflow_seen = 1; delta = 0; } /* Cap delta value to the max_cycles values to avoid mult overflows */ if (unlikely(delta > max)) { tk->overflow_seen = 1; delta = tkr->clock->max_cycles; } return delta; } #else static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) { u64 cycle_now, delta; /* read clocksource */ cycle_now = tk_clock_read(tkr); /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); return delta; } #endif /** * tk_setup_internals - Set up internals to use clocksource clock. * * @tk: The target timekeeper to setup. * @clock: Pointer to clocksource. * * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment * pair and interval request. * * Unless you're the timekeeping code, you should not be using this! */ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) { u64 interval; u64 tmp, ntpinterval; struct clocksource *old_clock; ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.mask = clock->mask; tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; ntpinterval = tmp; tmp += clock->mult/2; do_div(tmp, clock->mult); if (tmp == 0) tmp = 1; interval = (u64) tmp; tk->cycle_interval = interval; /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) { tk->tkr_mono.xtime_nsec >>= -shift_change; tk->tkr_raw.xtime_nsec >>= -shift_change; } else { tk->tkr_mono.xtime_nsec <<= shift_change; tk->tkr_raw.xtime_nsec <<= shift_change; } } tk->tkr_mono.shift = clock->shift; tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ tk->tkr_mono.mult = clock->mult; tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; tk->skip_second_overflow = 0; } /* Timekeeper helper functions. */ #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET static u32 default_arch_gettimeoffset(void) { return 0; } u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset; #else static inline u32 arch_gettimeoffset(void) { return 0; } #endif static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta) { u64 nsec; nsec = delta * tkr->mult + tkr->xtime_nsec; nsec >>= tkr->shift; /* If arch requires, add in get_arch_timeoffset() */ return nsec + arch_gettimeoffset(); } static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { u64 delta; delta = timekeeping_get_delta(tkr); return timekeeping_delta_to_ns(tkr, delta); } static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { u64 delta; /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); return timekeeping_delta_to_ns(tkr, delta); } /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update * * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. * * Employ the latch technique; see @raw_write_seqcount_latch. * * So if a NMI hits the update of base[0] then it will use base[1] * which is still consistent. In the worst case this can result is a * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ static void update_fast_timekeeper(const struct tk_read_base *tkr, struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ raw_write_seqcount_latch(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ raw_write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); } /** * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic * * This timestamp is not guaranteed to be monotonic across an update. * The timestamp is calculated by: * * now = base_mono + clock_delta * slope * * So if the update lowers the slope, readers who are forced to the * not yet updated second array are still using the old steeper slope. * * tmono * ^ * | o n * | o n * | u * | o * |o * |12345678---> reader order * * o = old slope * u = update * n = new slope * * So reader 6 will observe time going backwards versus reader 5. * * While other CPUs are likely to be able observe that, the only way * for a CPU local observation is when an NMI hits in the middle of * the update. Timestamps taken from that NMI context might be ahead * of the following timestamps. Callers need to be aware of that and * deal with it. */ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); now += timekeeping_delta_to_ns(tkr, clocksource_delta( tk_clock_read(tkr), tkr->cycle_last, tkr->mask)); } while (read_seqcount_latch_retry(&tkf->seq, seq)); return now; } u64 ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); u64 ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); /** * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. * * To keep it NMI safe since we're accessing from tracing, we're not using a * separate timekeeper with updates to monotonic clock and boot offset * protected with seqcounts. This has the following minor side effects: * * (1) Its possible that a timestamp be taken after the boot offset is updated * but before the timekeeper is updated. If this happens, the new boot offset * is added to the old timekeeping making the clock appear to update slightly * earlier: * CPU 0 CPU 1 * timekeeping_inject_sleeptime64() * __timekeeping_inject_sleeptime(tk, delta); * timestamp(); * timekeeping_update(tk, TK_CLEAR_NTP...); * * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be * partially updated. Since the tk->offs_boot update is a rare event, this * should be a rare occurrence which postprocessing should be able to handle. */ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot)); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); /* * See comment for __ktime_get_fast_ns() vs. timestamp ordering */ static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) { struct tk_read_base *tkr; u64 basem, baser, delta; unsigned int seq; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); delta = timekeeping_delta_to_ns(tkr, clocksource_delta(tk_clock_read(tkr), tkr->cycle_last, tkr->mask)); } while (read_seqcount_latch_retry(&tkf->seq, seq)); if (mono) *mono = basem + delta; return baser + delta; } /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. */ u64 ktime_get_real_fast_ns(void) { return __ktime_get_real_fast(&tk_fast_mono, NULL); } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); /** * ktime_get_fast_timestamps: - NMI safe timestamps * @snapshot: Pointer to timestamp storage * * Stores clock monotonic, boottime and realtime timestamps. * * Boot time is a racy access on 32bit systems if the sleep time injection * happens late during resume and not in timekeeping_resume(). That could * be avoided by expanding struct tk_read_base with boot offset for 32bit * and adding more overhead to the update. As this is a hard to observe * once per resume event which can be filtered with reasonable effort using * the accurate mono/real timestamps, it's probably not worth the trouble. * * Aside of that it might be possible on 32 and 64 bit to observe the * following when the sleep time injection happens late: * * CPU 0 CPU 1 * timekeeping_resume() * ktime_get_fast_timestamps() * mono, real = __ktime_get_real_fast() * inject_sleep_time() * update boot offset * boot = mono + bootoffset; * * That means that boot time already has the sleep time adjustment, but * real time does not. On the next readout both are in sync again. * * Preventing this for 64bit is not really feasible without destroying the * careful cache layout of the timekeeper because the sequence count and * struct tk_read_base would then need two cache lines instead of one. * * Access to the time keeper clock source is disabled accross the innermost * steps of suspend/resume. The accessors still work, but the timestamps * are frozen until time keeping is resumed which happens very early. * * For regular suspend/resume there is no observable difference vs. sched * clock, but it might affect some of the nasty low level debug printks. * * OTOH, access to sched clock is not guaranteed accross suspend/resume on * all systems either so it depends on the hardware in use. * * If that turns out to be a real problem then this could be mitigated by * using sched clock in a similar way as during early boot. But it's not as * trivial as on early boot because it needs some careful protection * against the clock monotonic timestamp jumping backwards on resume. */ void ktime_get_fast_timestamps(struct ktime_timestamps *snapshot) { struct timekeeper *tk = &tk_core.timekeeper; snapshot->real = __ktime_get_real_fast(&tk_fast_mono, &snapshot->mono); snapshot->boot = snapshot->mono + ktime_to_ns(data_race(tk->offs_boot)); } /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. * * It generally is unsafe to access the clocksource after timekeeping has been * suspended, so take a snapshot of the readout base of @tk and use it as the * fast timekeeper's readout base while suspended. It will return the same * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); tkr_dummy.clock = &dummy_clock; tkr_dummy.base_real = tkr->base + tk->offs_real; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** * pvclock_gtod_register_notifier - register a pvclock timedata update listener */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; int ret; raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); update_pvclock_gtod(tk, true); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); /** * pvclock_gtod_unregister_notifier - unregister a pvclock * timedata update listener */ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) { unsigned long flags; int ret; raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* * tk_update_leap_state - helper to update the next_leap_ktime */ static inline void tk_update_leap_state(struct timekeeper *tk) { tk->next_leap_ktime = ntp_get_next_leap(); if (tk->next_leap_ktime != KTIME_MAX) /* Convert to monotonic time */ tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real); } /* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) { u64 seconds; u32 nsec; /* * The xtime based monotonic readout is: * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); * The ktime based monotonic readout is: * nsec = base_mono + now(); * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; /* Update the monotonic raw base */ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } /* must hold timekeeper_lock */ static void timekeeping_update(struct timekeeper *tk, unsigned int action) { if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); } tk_update_leap_state(tk); tk_update_ktime_data(tk); update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real; update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); if (action & TK_CLOCK_WAS_SET) tk->clock_was_set_seq++; /* * The mirroring of the data to the shadow-timekeeper needs * to happen last here to ensure we don't over-write the * timekeeper structure on the next update with stale data */ if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); } /** * timekeeping_forward_now - update clock to the current time * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ static void timekeeping_forward_now(struct timekeeper *tk) { u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult; /* If arch requires, add in get_arch_timeoffset() */ tk->tkr_mono.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_mono.shift; tk->tkr_raw.xtime_nsec += delta * tk->tkr_raw.mult; /* If arch requires, add in get_arch_timeoffset() */ tk->tkr_raw.xtime_nsec += (u64)arch_gettimeoffset() << tk->tkr_raw.shift; tk_normalize_xtime(tk); } /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec64 (WARN if suspended). */ void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_real_ts64); ktime_t ktime_get(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); u32 ktime_get_resolution_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u32 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return nsecs; } EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; ktime_t ktime_get_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); /** * ktime_mono_to_any() - convert mononotic time to any other time * @tmono: time to convert. * @offs: which offset to use */ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t tconv; do { seq = read_seqcount_begin(&tk_core.seq); tconv = ktime_add(tmono, *offset); } while (read_seqcount_retry(&tk_core.seq, seq)); return tconv; } EXPORT_SYMBOL_GPL(ktime_mono_to_any); /** * ktime_get_raw - Returns the raw monotonic time in ktime_t format */ ktime_t ktime_get_raw(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_raw.base; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_raw); /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable * * The function calculates the monotonic clock from the realtime * clock and the wall_to_monotonic offset and stores the result * in normalized timespec64 format in the variable pointed to by @ts. */ void ktime_get_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono; unsigned int seq; u64 nsec; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_sec += tomono.tv_sec; ts->tv_nsec = 0; timespec64_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts64); /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * * Returns the seconds portion of CLOCK_MONOTONIC with a single non * serialized read. tk->ktime_sec is of type 'unsigned long' so this * works on both 32 and 64 bit systems. On 32 bit systems the readout * covers ~136 years of uptime which should be enough to prevent * premature wrap arounds. */ time64_t ktime_get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; WARN_ON(timekeeping_suspended); return tk->ktime_sec; } EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * * Returns the wall clock seconds since 1970. This replaces the * get_seconds() interface which is not y2038 safe on 32bit systems. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence * counter to provide "atomic" access to the 64bit tk->xtime_sec * value. */ time64_t ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; time64_t seconds; unsigned int seq; if (IS_ENABLED(CONFIG_64BIT)) return tk->xtime_sec; do { seq = read_seqcount_begin(&tk_core.seq); seconds = tk->xtime_sec; } while (read_seqcount_retry(&tk_core.seq, seq)); return seconds; } EXPORT_SYMBOL_GPL(ktime_get_real_seconds); /** * __ktime_get_real_seconds - The same as ktime_get_real_seconds * but without the sequence counter protect. This internal function * is called just when timekeeping lock is already held. */ noinstr time64_t __ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } /** * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter * @systime_snapshot: pointer to struct receiving the system time snapshot */ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base_raw; ktime_t base_real; u64 nsec_raw; u64 nsec_real; u64 now; WARN_ON_ONCE(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); } while (read_seqcount_retry(&tk_core.seq, seq)); systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); } EXPORT_SYMBOL_GPL(ktime_get_snapshot); /* Scale base by mult/div checking for overflow */ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) { u64 tmp, rem; tmp = div64_u64_rem(*base, div, &rem); if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } /** * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval * @history: Snapshot representing start of history * @partial_history_cycles: Cycle offset into history (fractional part) * @total_history_cycles: Total history length in cycles * @discontinuity: True indicates clock was set on history period * @ts: Cross timestamp that should be adjusted using * partial/total ratio * * Helper function used by get_device_system_crosststamp() to correct the * crosstimestamp corresponding to the start of the current interval to the * system counter value (timestamp point) provided by the driver. The * total_history_* quantities are the total history starting at the provided * reference point and ending at the start of the current interval. The cycle * count between the driver timestamp point and the start of the current * interval is partial_history_cycles. */ static int adjust_historical_crosststamp(struct system_time_snapshot *history, u64 partial_history_cycles, u64 total_history_cycles, bool discontinuity, struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 corr_raw, corr_real; bool interp_forward; int ret; if (total_history_cycles == 0 || partial_history_cycles == 0) return 0; /* Interpolate shortest distance from beginning or end of history */ interp_forward = partial_history_cycles > total_history_cycles / 2; partial_history_cycles = interp_forward ? total_history_cycles - partial_history_cycles : partial_history_cycles; /* * Scale the monotonic raw time delta by: * partial_history_cycles / total_history_cycles */ corr_raw = (u64)ktime_to_ns( ktime_sub(ts->sys_monoraw, history->raw)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_raw); if (ret) return ret; /* * If there is a discontinuity in the history, scale monotonic raw * correction by: * mult(real)/mult(raw) yielding the realtime correction * Otherwise, calculate the realtime correction similar to monotonic * raw calculation */ if (discontinuity) { corr_real = mul_u64_u32_div (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); } else { corr_real = (u64)ktime_to_ns( ktime_sub(ts->sys_realtime, history->real)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_real); if (ret) return ret; } /* Fixup monotonic raw and real time time values */ if (interp_forward) { ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); ts->sys_realtime = ktime_add_ns(history->real, corr_real); } else { ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); } return 0; } /* * timestamp_in_interval - true if ts is chronologically in [start, end] * * True if ts occurs chronologically at or after start, and before or at end. */ static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { if (ts >= start && ts <= end) return true; if (start > end && (ts >= start || ts <= end)) return true; return false; } /** * get_device_system_crosststamp - Synchronously capture system/device timestamp * @get_time_fn: Callback to get simultaneous device time and * system counter from the device driver * @ctx: Context passed to get_time_fn() * @history_begin: Historical reference point used to interpolate system * time when counter provided by the driver is before the current interval * @xtstamp: Receives simultaneously captured system and device time * * Reads a timestamp from a device and correlates it to system time */ int get_device_system_crosststamp(int (*get_time_fn) (ktime_t *device_time, struct system_counterval_t *sys_counterval, void *ctx), void *ctx, struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { struct system_counterval_t system_counterval; struct timekeeper *tk = &tk_core.timekeeper; u64 cycles, now, interval_start; unsigned int clock_was_set_seq = 0; ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; unsigned int seq; bool do_interp; int ret; do { seq = read_seqcount_begin(&tk_core.seq); /* * Try to synchronously capture device time and a system * counter value calling back into the device driver */ ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); if (ret) return ret; /* * Verify that the clocksource associated with the captured * system counter value is the same as the currently installed * timekeeper clocksource */ if (tk->tkr_mono.clock != system_counterval.cs) return -ENODEV; cycles = system_counterval.cycles; /* * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; do_interp = true; } else { do_interp = false; } base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); /* * Interpolate if necessary, adjusting back from the start of the * current interval */ if (do_interp) { u64 partial_history_cycles, total_history_cycles; bool discontinuity; /* * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || !timestamp_in_interval(history_begin->cycles, cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; total_history_cycles = cycles - history_begin->cycles; discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq; ret = adjust_historical_crosststamp(history_begin, partial_history_cycles, total_history_cycles, discontinuity, xtstamp); if (ret) return ret; } return 0; } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time * * Sets the time of day to the new time and update NTP and notify hrtimers */ int do_settimeofday64(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts_delta, xt; unsigned long flags; int ret = 0; if (!timespec64_valid_settod(ts)) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); xt = tk_xtime(tk); ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL; goto out; } tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); tk_set_xtime(tk, ts); out: timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ clock_was_set(); if (!ret) { audit_tk_injoffset(ts_delta); add_device_randomness(ts, sizeof(*ts)); } return ret; } EXPORT_SYMBOL(do_settimeofday64); /** * timekeeping_inject_offset - Adds or subtracts from the current time. * @tv: pointer to the timespec variable containing the offset * * Adds or subtracts an offset value from the current time. */ static int timekeeping_inject_offset(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 tmp; int ret = 0; if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tk), *ts); if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 || !timespec64_valid_settod(&tmp)) { ret = -EINVAL; goto error; } tk_xtime_add(tk, ts); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *ts)); error: /* even if we error out, we forwarded the time, so call update */ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ clock_was_set(); return ret; } /* * Indicates if there is an offset between the system clock and the hardware * clock/persistent clock/rtc. */ int persistent_clock_is_local; /* * Adjust the time obtained from the CMOS to be UTC time instead of * local time. * * This is ugly, but preferable to the alternatives. Otherwise we * would either need to write a program to do it in /etc/rc (and risk * confusion if the program gets run more than once; it would also be * hard to make the program warp the clock precisely n hours) or * compile in the timezone information into the kernel. Bad, bad.... * * - TYT, 1992-01-01 * * The best thing to do is to keep the CMOS clock in universal time (UTC) * as real UNIX machines always do it. This avoids all headaches about * daylight saving times and warping kernel clocks. */ void timekeeping_warp_clock(void) { if (sys_tz.tz_minuteswest != 0) { struct timespec64 adjust; persistent_clock_is_local = 1; adjust.tv_sec = sys_tz.tz_minuteswest * 60; adjust.tv_nsec = 0; timekeeping_inject_offset(&adjust); } } /** * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic * */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) { tk->tai_offset = tai_offset; tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } /** * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource */ static int change_clocksource(void *data) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *new, *old; unsigned long flags; new = (struct clocksource *) data; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* * If the cs is in module, get a module reference. Succeeds * for built-in code (owner == NULL) as well. */ if (try_module_get(new->owner)) { if (!new->enable || new->enable(new) == 0) { old = tk->tkr_mono.clock; tk_setup_internals(tk, new); if (old->disable) old->disable(old); module_put(old->owner); } else { module_put(new->owner); } } timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return 0; } /** * timekeeping_notify - Install a new clock source * @clock: pointer to the clock source * * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; if (tk->tkr_mono.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); return tk->tkr_mono.clock == clock ? 0 : -1; } /** * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec * @ts: pointer to the timespec64 to be set * * Returns the raw monotonic time (completely un-modified by ntp) */ void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->raw_sec; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_raw_ts64); /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; int ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred */ u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * read_persistent_clock64 - Return time from the persistent clock. * * Weak dummy function for arches that do not yet support it. * Reads the time from the battery backed persistent clock. * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ void __weak read_persistent_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; } /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. * * Weak dummy function for arches that do not yet support it. * wall_time - current time as returned by persistent clock * boot_offset - offset that is defined as wall_time - boot_time * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't * support dedicated boot time clock will provide the best estimate of the * boot time. */ void __weak __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, struct timespec64 *boot_offset) { read_persistent_clock64(wall_time); *boot_offset = ns_to_timespec64(local_clock()); } /* * Flag reflecting whether timekeeping_resume() has injected sleeptime. * * The flag starts of false and is only set when a suspend reaches * timekeeping_suspend(), timekeeping_resume() sets it to false when the * timekeeper clocksource is not stopping across suspend and has been * used to update sleep time. If the timekeeper clocksource has stopped * then the flag stays true and is used by the RTC resume code to decide * whether sleeptime must be injected and if so the flag gets false then. * * If a suspend fails before reaching timekeeping_resume() then the flag * stays false and prevents erroneous sleeptime injection. */ static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ void __init timekeeping_init(void) { struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock; unsigned long flags; read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { pr_warn("Persistent clock returned invalid value"); wall_time = (struct timespec64){0}; } if (timespec64_compare(&wall_time, &boot_offset) < 0) boot_offset = (struct timespec64){0}; /* * We want set wall_to_mono, so the following is true: * wall time + wall_to_mono = boot time */ wall_to_mono = timespec64_sub(boot_offset, wall_time); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); ntp_init(); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); tk_setup_internals(tk, clock); tk_set_xtime(tk, &wall_time); tk->raw_sec = 0; tk_set_wall_to_mono(tk, wall_to_mono); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } /* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @delta: pointer to a timespec delta value * * Takes a timespec offset measuring a suspend interval and properly * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) /** * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource * 2) persistent clock (ie: RTC accessible when irqs are off) * 3) RTC * * 1) and 2) are used by timekeeping, 3) by RTC subsystem. * If system has neither 1) nor 2), 3) will be used finally. * * * If timekeeping has injected sleeptime via either 1) or 2), * 3) becomes needless, so in this case we don't need to call * rtc_resume(), and this is what timekeeping_rtc_skipresume() * means. */ bool timekeeping_rtc_skipresume(void) { return !suspend_timing_needed; } /** * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). * * But if system has 2), 2) will definitely be used, so in this * case we don't need to call rtc_suspend(), and this is what * timekeeping_rtc_skipsuspend() means. */ bool timekeeping_rtc_skipsuspend(void) { return persistent_clock_exists; } /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); suspend_timing_needed = false; timekeeping_forward_now(tk); __timekeeping_inject_sleeptime(tk, delta); timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* signal hrtimers about time change */ clock_was_set(); } #endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. */ void timekeeping_resume(void) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; u64 cycle_now, nsec; bool inject_sleeptime = false; read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); /* * After system resumes, we need to calculate the suspended time and * compensate it for the OS time. There are 3 sources that could be * used: Nonstop clocksource during suspend, persistent clock and rtc * device. * * One specific platform may have 1 or 2 or all of them, and the * preference will be: * suspend-nonstop clocksource -> persistent clock -> rtc * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tk->tkr_mono); nsec = clocksource_stop_suspend_timing(clock, cycle_now); if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); inject_sleeptime = true; } if (inject_sleeptime) { suspend_timing_needed = false; __timekeeping_inject_sleeptime(tk, &ts_delta); } /* Re-base the last cycle value */ tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); touch_softlockup_watchdog(); tick_resume(); hrtimers_resume(); } int timekeeping_suspend(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; struct clocksource *curr_clock; u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at * timekeeping_init by its return value, so if we see a valid * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; suspend_timing_needed = true; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; /* * Since we've called forward_now, cycle_last stores the value * just read from the current clocksource. Save this to potentially * use in suspend timing. */ curr_clock = tk->tkr_mono.clock; cycle_now = tk->tkr_mono.cycle_last; clocksource_start_suspend_timing(curr_clock, cycle_now); if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, * which each can add ~1 second drift error, * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction * has occurred and set old_delta to the current delta. */ old_delta = delta; } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = timespec64_add(timekeeping_suspend_time, delta_delta); } } timekeeping_update(tk, TK_MIRROR); halt_fast_timekeeper(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); tick_suspend(); clocksource_suspend(); clockevents_suspend(); return 0; } /* sysfs resume/suspend bits for timekeeping */ static struct syscore_ops timekeeping_syscore_ops = { .resume = timekeeping_resume, .suspend = timekeeping_suspend, }; static int __init timekeeping_init_ops(void) { register_syscore_ops(&timekeeping_syscore_ops); return 0; } device_initcall(timekeeping_init_ops); /* * Apply a multiplier adjustment to the timekeeper */ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, s64 offset, s32 mult_adj) { s64 interval = tk->cycle_interval; if (mult_adj == 0) { return; } else if (mult_adj == -1) { interval = -interval; offset = -offset; } else if (mult_adj != 1) { interval *= mult_adj; offset *= mult_adj; } /* * So the following can be confusing. * * To keep things simple, lets assume mult_adj == 1 for now. * * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier * by one, this causes the xtime_interval to be incremented by * one cycle_interval. This is because: * xtime_interval = cycle_interval * mult * So if mult is being incremented by one: * xtime_interval = cycle_interval * (mult + 1) * Its the same as: * xtime_interval = (cycle_interval * mult) + cycle_interval * Which can be shortened to: * xtime_interval += cycle_interval * * So offset stores the non-accumulated cycles. Thus the current * time (in shifted nanoseconds) is: * now = (offset * adj) + xtime_nsec * Now, even though we're adjusting the clock frequency, we have * to keep time consistent. In other words, we can't jump back * in time, and we also want to avoid jumping forward in time. * * So given the same offset value, we need the time to be the same * both before and after the freq adjustment. * now = (offset * adj_1) + xtime_nsec_1 * now = (offset * adj_2) + xtime_nsec_2 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_2) + xtime_nsec_2 * And we know: * adj_2 = adj_1 + 1 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * (adj_1+1)) + xtime_nsec_2 * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_1) + offset + xtime_nsec_2 * Canceling the sides: * xtime_nsec_1 = offset + xtime_nsec_2 * Which gives us: * xtime_nsec_2 = xtime_nsec_1 - offset * Which simplfies to: * xtime_nsec -= offset */ if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; tk->tkr_mono.xtime_nsec -= offset; } /* * Adjust the timekeeper's multiplier to the correct frequency * and also to reduce the accumulated error value. */ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { u32 mult; /* * Determine the multiplier from the current NTP tick length. * Avoid expensive division when the tick length doesn't change. */ if (likely(tk->ntp_tick == ntp_tick_length())) { mult = tk->tkr_mono.mult - tk->ntp_err_mult; } else { tk->ntp_tick = ntp_tick_length(); mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) - tk->xtime_remainder, tk->cycle_interval); } /* * If the clock is behind the NTP time, increase the multiplier by 1 * to catch up with it. If it's ahead and there was a remainder in the * tick division, the clock will slow down. Otherwise it will stay * ahead until the tick length changes to a non-divisible value. */ tk->ntp_err_mult = tk->ntp_error > 0 ? 1 : 0; mult += tk->ntp_err_mult; timekeeping_apply_adjustment(tk, offset, mult - tk->tkr_mono.mult); if (unlikely(tk->tkr_mono.clock->maxadj && (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource * in the code above, its possible the required corrective factor to * xtime_nsec could cause it to underflow. * * Now, since we have already accumulated the second and the NTP * subsystem has been notified via second_overflow(), we need to skip * the next update. */ if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { tk->tkr_mono.xtime_nsec += (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec--; tk->skip_second_overflow = 1; } } /** * accumulate_nsecs_to_secs - Accumulates nsecs into secs * * Helper function that accumulates the nsecs greater than a second * from the xtime_nsec field to the xtime_secs field. * It also calls into the NTP code to handle leapsecond processing. * */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* * Skip NTP update if this second was accumulated before, * i.e. xtime_nsec underflowed in timekeeping_adjust() */ if (unlikely(tk->skip_second_overflow)) { tk->skip_second_overflow = 0; continue; } /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); if (unlikely(leap)) { struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_set = TK_CLOCK_WAS_SET; } } return clock_set; } /** * logarithmic_accumulation - shifted accumulation of cycles * * This functions accumulates a shifted interval of cycles into * a shifted interval nanoseconds. Allows for O(log) accumulation * loop. * * Returns the unconsumed cycles. */ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) return offset; /* Accumulate one shifted interval */ offset -= interval; tk->tkr_mono.cycle_last += interval; tk->tkr_raw.cycle_last += interval; tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { tk->tkr_raw.xtime_nsec -= snsec_per_sec; tk->raw_sec++; } /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length */ static void timekeeping_advance(enum timekeeping_adv_mode mode) { struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; u64 offset; int shift = 0, maxshift; unsigned int clock_set = 0; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) goto out; #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; if (mode != TK_ADV_TICK) goto out; #else offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) goto out; #endif /* Do some additional sanity checking */ timekeeping_check_update(tk, offset); /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, * we calculate the largest doubling multiple of cycle_intervals * that is smaller than the offset. We then accumulate that * chunk in one go, and then try to consume the next smaller * doubled multiple. */ shift = ilog2(offset) - ilog2(tk->cycle_interval); shift = max(0, shift); /* Bound shift to one less than what overflows tick_length */ maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { offset = logarithmic_accumulation(tk, offset, shift, &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); /* * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ clock_set |= accumulate_nsecs_to_secs(tk); write_seqcount_begin(&tk_core.seq); /* * Update the real timekeeper. * * We could avoid this memcpy by switching pointers, but that * requires changes to all other timekeeper usage sites as * well, i.e. move the timekeeper pointer getter into the * spinlocked/seqcount protected sections. And we trade this * memcpy under the tk_core.seq against one before we start * updating. */ timekeeping_update(tk, clock_set); memcpy(real_tk, tk, sizeof(*tk)); /* The memcpy must come last. Do not put anything here! */ write_seqcount_end(&tk_core.seq); out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (clock_set) /* Have to call _delayed version, since in irq context*/ clock_was_set_delayed(); } /** * update_wall_time - Uses the current clocksource to increment the wall time * */ void update_wall_time(void) { timekeeping_advance(TK_ADV_TICK); } /** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); /* * Must hold jiffies_lock */ void do_timer(unsigned long ticks) { jiffies_64 += ticks; calc_global_load(); } /** * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the * sequence number in @cwsseq and timekeeper.clock_was_set_seq are * different. * * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); base = ktime_add_ns(base, nsecs); if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } /* Handle leapsecond insertion adjustments */ if (unlikely(base >= tk->next_leap_ktime)) *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0)); } while (read_seqcount_retry(&tk_core.seq, seq)); return base; } /** * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ static int timekeeping_validate_timex(const struct __kernel_timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; if (!(txc->modes & ADJ_OFFSET_READONLY) && !capable(CAP_SYS_TIME)) return -EPERM; } else { /* In order to modify anything, you gotta be super-user! */ if (txc->modes && !capable(CAP_SYS_TIME)) return -EPERM; /* * if the quartz is off by more than 10% then * something is VERY wrong! */ if (txc->modes & ADJ_TICK && (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; } if (txc->modes & ADJ_SETOFFSET) { /* In order to inject time, you gotta be super-user! */ if (!capable(CAP_SYS_TIME)) return -EPERM; /* * Validate if a timespec/timeval used to inject a time * offset is valid. Offsets can be postive or negative, so * we don't check tv_sec. The value of the timeval/timespec * is the sum of its fields,but *NOTE*: * The field tv_usec/tv_nsec must always be non-negative and * we can't have more nanoseconds/microseconds than a second. */ if (txc->time.tv_usec < 0) return -EINVAL; if (txc->modes & ADJ_NANO) { if (txc->time.tv_usec >= NSEC_PER_SEC) return -EINVAL; } else { if (txc->time.tv_usec >= USEC_PER_SEC) return -EINVAL; } } /* * Check for potential multiplication overflows that can * only happen on 64-bit systems: */ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { if (LLONG_MIN / PPM_SCALE > txc->freq) return -EINVAL; if (LLONG_MAX / PPM_SCALE < txc->freq) return -EINVAL; } return 0; } /** * random_get_entropy_fallback - Returns the raw clock source value, * used by random.c for platforms with no valid random_get_entropy(). */ unsigned long random_get_entropy_fallback(void) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; struct clocksource *clock = READ_ONCE(tkr->clock); if (unlikely(timekeeping_suspended || !clock)) return 0; return clock->read(clock); } EXPORT_SYMBOL_GPL(random_get_entropy_fallback); /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ int do_adjtimex(struct __kernel_timex *txc) { struct timekeeper *tk = &tk_core.timekeeper; struct audit_ntp_data ad; unsigned long flags; struct timespec64 ts; s32 orig_tai, tai; int ret; /* Validate the data before disabling interrupts */ ret = timekeeping_validate_timex(txc); if (ret) return ret; add_device_randomness(txc, sizeof(*txc)); if (txc->modes & ADJ_SETOFFSET) { struct timespec64 delta; delta.tv_sec = txc->time.tv_sec; delta.tv_nsec = txc->time.tv_usec; if (!(txc->modes & ADJ_NANO)) delta.tv_nsec *= 1000; ret = timekeeping_inject_offset(&delta); if (ret) return ret; audit_tk_injoffset(delta); } audit_ntp_init(&ad); ktime_get_real_ts64(&ts); add_device_randomness(&ts, sizeof(ts)); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); orig_tai = tai = tk->tai_offset; ret = __do_adjtimex(txc, &ts, &tai, &ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tk, tai); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); } tk_update_leap_state(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); audit_ntp_log(&ad); /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) timekeeping_advance(TK_ADV_FREQ); if (tai != orig_tai) clock_was_set(); ntp_notify_cmos_timer(); return ret; } #ifdef CONFIG_NTP_PPS /** * hardpps() - Accessor function to NTP __hardpps function */ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); __hardpps(phase_ts, raw_ts); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } EXPORT_SYMBOL(hardpps); #endif /* CONFIG_NTP_PPS */ /** * xtime_update() - advances the timekeeping infrastructure * @ticks: number of ticks, that have elapsed since the last call. * * Must be called with interrupts disabled. */ void xtime_update(unsigned long ticks) { raw_spin_lock(&jiffies_lock); write_seqcount_begin(&jiffies_seq); do_timer(ticks); write_seqcount_end(&jiffies_seq); raw_spin_unlock(&jiffies_lock); update_wall_time(); } |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the symbol table type. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include "symtab.h" static unsigned int symhash(const void *key) { const char *p, *keyp; unsigned int size; unsigned int val; val = 0; keyp = key; size = strlen(keyp); for (p = keyp; (p - keyp) < size; p++) val = (val << 4 | (val >> (8*sizeof(unsigned int)-4))) ^ (*p); return val; } static int symcmp(const void *key1, const void *key2) { const char *keyp1, *keyp2; keyp1 = key1; keyp2 = key2; return strcmp(keyp1, keyp2); } static const struct hashtab_key_params symtab_key_params = { .hash = symhash, .cmp = symcmp, }; int symtab_init(struct symtab *s, unsigned int size) { s->nprim = 0; return hashtab_init(&s->table, size); } int symtab_insert(struct symtab *s, char *name, void *datum) { return hashtab_insert(&s->table, name, datum, symtab_key_params); } void *symtab_search(struct symtab *s, const char *name) { return hashtab_search(&s->table, name, symtab_key_params); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM x86_fpu #if !defined(_TRACE_FPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FPU_H #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(x86_fpu, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu), TP_STRUCT__entry( __field(struct fpu *, fpu) __field(bool, load_fpu) __field(u64, xfeatures) __field(u64, xcomp_bv) ), TP_fast_assign( __entry->fpu = fpu; __entry->load_fpu = test_thread_flag(TIF_NEED_FPU_LOAD); if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { __entry->xfeatures = fpu->state.xsave.header.xfeatures; __entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv; } ), TP_printk("x86/fpu: %p load: %d xfeatures: %llx xcomp_bv: %llx", __entry->fpu, __entry->load_fpu, __entry->xfeatures, __entry->xcomp_bv ) ); DEFINE_EVENT(x86_fpu, x86_fpu_before_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_after_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_before_restore, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_after_restore, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_regs_activated, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_init_state, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_dropped, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_copy_src, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_copy_dst, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_xstate_check_failed, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH asm/trace/ #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE fpu #endif /* _TRACE_FPU_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_BL_H #define _LINUX_LIST_BL_H #include <linux/list.h> #include <linux/bit_spinlock.h> /* * Special version of lists, where head of the list has a lock in the lowest * bit. This is useful for scalable hash tables without increasing memory * footprint overhead. * * For modification operations, the 0 bit of hlist_bl_head->first * pointer must be set. * * With some small modifications, this can easily be adapted to store several * arbitrary bits (not just a single lock bit), if the need arises to store * some fast and compact auxiliary data. */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define LIST_BL_LOCKMASK 1UL #else #define LIST_BL_LOCKMASK 0UL #endif #ifdef CONFIG_DEBUG_LIST #define LIST_BL_BUG_ON(x) BUG_ON(x) #else #define LIST_BL_BUG_ON(x) #endif struct hlist_bl_head { struct hlist_bl_node *first; }; struct hlist_bl_node { struct hlist_bl_node *next, **pprev; }; #define INIT_HLIST_BL_HEAD(ptr) \ ((ptr)->first = NULL) static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) { h->next = NULL; h->pprev = NULL; } #define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member) static inline bool hlist_bl_unhashed(const struct hlist_bl_node *h) { return !h->pprev; } static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)h->first & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_set_first(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK); } static inline bool hlist_bl_empty(const struct hlist_bl_head *h) { return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_add_head(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; hlist_bl_set_first(h, n); } static inline void hlist_bl_add_before(struct hlist_bl_node *n, struct hlist_bl_node *next) { struct hlist_bl_node **pprev = next->pprev; n->pprev = pprev; n->next = next; next->pprev = &n->next; /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((uintptr_t)n | ((uintptr_t)*pprev & LIST_BL_LOCKMASK))); } static inline void hlist_bl_add_behind(struct hlist_bl_node *n, struct hlist_bl_node *prev) { n->next = prev->next; n->pprev = &prev->next; prev->next = n; if (n->next) n->next->pprev = &n->next; } static inline void __hlist_bl_del(struct hlist_bl_node *n) { struct hlist_bl_node *next = n->next; struct hlist_bl_node **pprev = n->pprev; LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((unsigned long)next | ((unsigned long)*pprev & LIST_BL_LOCKMASK))); if (next) next->pprev = pprev; } static inline void hlist_bl_del(struct hlist_bl_node *n) { __hlist_bl_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } static inline void hlist_bl_del_init(struct hlist_bl_node *n) { if (!hlist_bl_unhashed(n)) { __hlist_bl_del(n); INIT_HLIST_BL_NODE(n); } } static inline void hlist_bl_lock(struct hlist_bl_head *b) { bit_spin_lock(0, (unsigned long *)b); } static inline void hlist_bl_unlock(struct hlist_bl_head *b) { __bit_spin_unlock(0, (unsigned long *)b); } static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) { return bit_spin_is_locked(0, (unsigned long *)b); } /** * hlist_bl_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * */ #define hlist_bl_for_each_entry(tpos, pos, head, member) \ for (pos = hlist_bl_first(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_bl_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @n: another &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_bl_for_each_entry_safe(tpos, pos, n, head, member) \ for (pos = hlist_bl_first(head); \ pos && ({ n = pos->next; 1; }) && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = n) #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 | /* SPDX-License-Identifier: GPL-2.0 */ /* * workqueue.h --- work queue handling for Linux. */ #ifndef _LINUX_WORKQUEUE_H #define _LINUX_WORKQUEUE_H #include <linux/timer.h> #include <linux/linkage.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/threads.h> #include <linux/atomic.h> #include <linux/cpumask.h> #include <linux/rcupdate.h> struct workqueue_struct; struct work_struct; typedef void (*work_func_t)(struct work_struct *work); void delayed_work_timer_fn(struct timer_list *t); /* * The first word is the work queue pointer and the flags rolled into * one */ #define work_data_bits(work) ((unsigned long *)(&(work)->data)) enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ WORK_STRUCT_INACTIVE_BIT= 1, /* work item is inactive */ WORK_STRUCT_PWQ_BIT = 2, /* data points to pwq */ WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */ WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */ #else WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ #endif WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT, WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, #else WORK_STRUCT_STATIC = 0, #endif /* * The last color is no color used for works which don't * participate in workqueue flushing. */ WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS) - 1, WORK_NO_COLOR = WORK_NR_COLORS, /* not bound to any CPU, prefer the local CPU */ WORK_CPU_UNBOUND = NR_CPUS, /* * Reserve 8 bits off of pwq pointer w/ debugobjects turned off. * This makes pwqs aligned to 256 bytes and allows 15 workqueue * flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, /* data contains off-queue information when !WORK_STRUCT_PWQ */ WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE, /* * When a work item is off queue, its high bits point to the last * pool it was on. Cap at 31 bits and use the highest number to * indicate that no pool is associated. */ WORK_OFFQ_FLAG_BITS = 1, WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, WORK_BUSY_RUNNING = 1 << 1, /* maximum string length for set_worker_desc() */ WORKER_DESC_LEN = 24, }; /* Convenience constants - of type 'unsigned long', not 'enum'! */ #define WORK_OFFQ_CANCELING (1ul << __WORK_OFFQ_CANCELING) #define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) #define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) #define WORK_STRUCT_FLAG_MASK ((1ul << WORK_STRUCT_FLAG_BITS) - 1) #define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) struct work_struct { atomic_long_t data; struct list_head entry; work_func_t func; #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif }; #define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)) struct delayed_work { struct work_struct work; struct timer_list timer; /* target workqueue and CPU ->timer uses to queue ->work */ struct workqueue_struct *wq; int cpu; }; struct rcu_work { struct work_struct work; struct rcu_head rcu; /* target workqueue ->rcu uses to queue ->work */ struct workqueue_struct *wq; }; /** * struct workqueue_attrs - A struct for workqueue attributes. * * This can be used to change attributes of an unbound workqueue. */ struct workqueue_attrs { /** * @nice: nice level */ int nice; /** * @cpumask: allowed CPUs */ cpumask_var_t cpumask; /** * @no_numa: disable NUMA affinity * * Unlike other fields, ``no_numa`` isn't a property of a worker_pool. It * only modifies how :c:func:`apply_workqueue_attrs` select pools and thus * doesn't participate in pool hash calculations or equality comparisons. */ bool no_numa; }; static inline struct delayed_work *to_delayed_work(struct work_struct *work) { return container_of(work, struct delayed_work, work); } static inline struct rcu_work *to_rcu_work(struct work_struct *work) { return container_of(work, struct rcu_work, work); } struct execute_work { struct work_struct work; }; #ifdef CONFIG_LOCKDEP /* * NB: because we have to copy the lockdep_map, setting _key * here is required, otherwise it could get initialised to the * copy of the lockdep_map! */ #define __WORK_INIT_LOCKDEP_MAP(n, k) \ .lockdep_map = STATIC_LOCKDEP_MAP_INIT(n, k), #else #define __WORK_INIT_LOCKDEP_MAP(n, k) #endif #define __WORK_INITIALIZER(n, f) { \ .data = WORK_DATA_STATIC_INIT(), \ .entry = { &(n).entry, &(n).entry }, \ .func = (f), \ __WORK_INIT_LOCKDEP_MAP(#n, &(n)) \ } #define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ .work = __WORK_INITIALIZER((n).work, (f)), \ .timer = __TIMER_INITIALIZER(delayed_work_timer_fn,\ (tflags) | TIMER_IRQSAFE), \ } #define DECLARE_WORK(n, f) \ struct work_struct n = __WORK_INITIALIZER(n, f) #define DECLARE_DELAYED_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0) #define DECLARE_DEFERRABLE_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, TIMER_DEFERRABLE) #ifdef CONFIG_DEBUG_OBJECTS_WORK extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); extern void destroy_delayed_work_on_stack(struct delayed_work *work); static inline unsigned int work_static(struct work_struct *work) { return *work_data_bits(work) & WORK_STRUCT_STATIC; } #else static inline void __init_work(struct work_struct *work, int onstack) { } static inline void destroy_work_on_stack(struct work_struct *work) { } static inline void destroy_delayed_work_on_stack(struct delayed_work *work) { } static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif /* * initialize all of a work item in one go * * NOTE! No point in using "atomic_long_set()": using a direct * assignment of the work data initializer allows the compiler * to generate better code. */ #ifdef CONFIG_LOCKDEP #define __INIT_WORK(_work, _func, _onstack) \ do { \ static struct lock_class_key __key; \ \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, &__key, 0); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #else #define __INIT_WORK(_work, _func, _onstack) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #endif #define INIT_WORK(_work, _func) \ __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ __INIT_WORK((_work), (_func), 1) #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ INIT_WORK(&(_work)->work, (_func)); \ __init_timer(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define __INIT_DELAYED_WORK_ONSTACK(_work, _func, _tflags) \ do { \ INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ __init_timer_on_stack(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define INIT_DELAYED_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, 0) #define INIT_DELAYED_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, 0) #define INIT_DEFERRABLE_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, TIMER_DEFERRABLE) #define INIT_DEFERRABLE_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, TIMER_DEFERRABLE) #define INIT_RCU_WORK(_work, _func) \ INIT_WORK(&(_work)->work, (_func)) #define INIT_RCU_WORK_ONSTACK(_work, _func) \ INIT_WORK_ONSTACK(&(_work)->work, (_func)) /** * work_pending - Find out whether a work item is currently pending * @work: The work item in question */ #define work_pending(work) \ test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) /** * delayed_work_pending - Find out whether a delayable work item is currently * pending * @w: The work item in question */ #define delayed_work_pending(w) \ work_pending(&(w)->work) /* * Workqueue flags and constants. For details, please refer to * Documentation/core-api/workqueue.rst. */ enum { WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu intensive workqueue */ WQ_SYSFS = 1 << 6, /* visible in sysfs, see wq_sysfs_register() */ /* * Per-cpu workqueues are generally preferred because they tend to * show better performance thanks to cache locality. Per-cpu * workqueues exclude the scheduler from choosing the CPU to * execute the worker threads, which has an unfortunate side effect * of increasing power consumption. * * The scheduler considers a CPU idle if it doesn't have any task * to execute and tries to keep idle cores idle to conserve power; * however, for example, a per-cpu work item scheduled from an * interrupt handler on an idle CPU will force the scheduler to * excute the work item on that CPU breaking the idleness, which in * turn may lead to more scheduling choices which are sub-optimal * in terms of power consumption. * * Workqueues marked with WQ_POWER_EFFICIENT are per-cpu by default * but become unbound if workqueue.power_efficient kernel param is * specified. Per-cpu workqueues which are identified to * contribute significantly to power-consumption are identified and * marked with this flag and enabling the power_efficient mode * leads to noticeable power saving at the cost of small * performance disadvantage. * * http://thread.gmane.org/gmane.linux.kernel/1480396 */ WQ_POWER_EFFICIENT = 1 << 7, __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, }; /* unbound wq's aren't per-cpu, scale max_active according to #cpus */ #define WQ_UNBOUND_MAX_ACTIVE \ max_t(int, WQ_MAX_ACTIVE, num_possible_cpus() * WQ_MAX_UNBOUND_PER_CPU) /* * System-wide workqueues which are always present. * * system_wq is the one used by schedule[_delayed]_work[_on](). * Multi-CPU multi-threaded. There are users which expect relatively * short queue flush time. Don't queue works which can run for too * long. * * system_highpri_wq is similar to system_wq but for work items which * require WQ_HIGHPRI. * * system_long_wq is similar to system_wq but may host long running * works. Queue flushing might take relatively long. * * system_unbound_wq is unbound workqueue. Workers are not bound to * any specific CPU, not concurrency managed, and all queued works are * executed immediately as long as max_active limit is not reached and * resources are available. * * system_freezable_wq is equivalent to system_wq except that it's * freezable. * * *_power_efficient_wq are inclined towards saving power and converted * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise, * they are same as their non-power-efficient counterparts - e.g. * system_power_efficient_wq is identical to system_wq if * 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info. */ extern struct workqueue_struct *system_wq; extern struct workqueue_struct *system_highpri_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; /** * alloc_workqueue - allocate a workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default * remaining args: args for @fmt * * Allocate a workqueue with the specified parameters. For detailed * information on WQ_* flags, please refer to * Documentation/core-api/workqueue.rst. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ struct workqueue_struct *alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...); /** * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @args...: args for @fmt * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are * implemented as unbound workqueues with @max_active of one. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | \ __WQ_ORDERED_EXPLICIT | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name)) #define create_freezable_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \ WQ_MEM_RECLAIM, 1, (name)) #define create_singlethread_workqueue(name) \ alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name) extern void destroy_workqueue(struct workqueue_struct *wq); struct workqueue_attrs *alloc_workqueue_attrs(void); void free_workqueue_attrs(struct workqueue_attrs *attrs); int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs); int workqueue_set_unbound_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork); extern void flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern bool flush_rcu_work(struct rcu_work *rwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); extern struct work_struct *current_work(void); extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_workqueue_state(void); extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); /** * queue_work - queue work on a workqueue * @wq: workqueue to use * @work: work to queue * * Returns %false if @work was already on a queue, %true otherwise. * * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. * * Memory-ordering properties: If it returns %true, guarantees that all stores * preceding the call to queue_work() in the program order will be visible from * the CPU which will execute @work by the time such work executes, e.g., * * { x is initially 0 } * * CPU0 CPU1 * * WRITE_ONCE(x, 1); [ @work is being executed ] * r0 = queue_work(wq, work); r1 = READ_ONCE(x); * * Forbids: r0 == true && r1 == 0 */ static inline bool queue_work(struct workqueue_struct *wq, struct work_struct *work) { return queue_work_on(WORK_CPU_UNBOUND, wq, work); } /** * queue_delayed_work - queue work on a workqueue after delay * @wq: workqueue to use * @dwork: delayable work to queue * @delay: number of jiffies to wait before queueing * * Equivalent to queue_delayed_work_on() but tries to use the local CPU. */ static inline bool queue_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * mod_delayed_work - modify delay of or queue a delayed work * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * mod_delayed_work_on() on local CPU. */ static inline bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * schedule_work_on - put work task on a specific cpu * @cpu: cpu to put the work task on * @work: job to be done * * This puts a job on a specific cpu */ static inline bool schedule_work_on(int cpu, struct work_struct *work) { return queue_work_on(cpu, system_wq, work); } /** * schedule_work - put work task in global workqueue * @work: job to be done * * Returns %false if @work was already on the kernel-global workqueue and * %true otherwise. * * This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. * * Shares the same memory-ordering properties of queue_work(), cf. the * DocBook header of queue_work(). */ static inline bool schedule_work(struct work_struct *work) { return queue_work(system_wq, work); } /** * flush_scheduled_work - ensure that any scheduled work has run to completion. * * Forces execution of the kernel-global workqueue and blocks until its * completion. * * Think twice before calling this function! It's very easy to get into * trouble if you don't take great care. Either of the following situations * will lead to deadlock: * * One of the work items currently on the workqueue needs to acquire * a lock held by your code or its caller. * * Your code is running in the context of a work routine. * * They will be detected by lockdep when they occur, but the first might not * occur very often. It depends on what work items are on the workqueue and * what locks they need, which you have no control over. * * In most situations flushing the entire workqueue is overkill; you merely * need to know that a particular work item isn't queued and isn't running. * In such cases you should use cancel_delayed_work_sync() or * cancel_work_sync() instead. */ static inline void flush_scheduled_work(void) { flush_workqueue(system_wq); } /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use * @dwork: job to be done * @delay: number of jiffies to wait * * After waiting for a given time this puts a job in the kernel-global * workqueue on the specified CPU. */ static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(cpu, system_wq, dwork, delay); } /** * schedule_delayed_work - put work task in global workqueue after delay * @dwork: job to be done * @delay: number of jiffies to wait or 0 for immediate execution * * After waiting for a given time this puts a job in the kernel-global * workqueue. */ static inline bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work(system_wq, dwork, delay); } #ifndef CONFIG_SMP static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } #else long work_on_cpu(int cpu, long (*fn)(void *), void *arg); long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER extern void freeze_workqueues_begin(void); extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ #ifdef CONFIG_SYSFS int workqueue_sysfs_register(struct workqueue_struct *wq); #else /* CONFIG_SYSFS */ static inline int workqueue_sysfs_register(struct workqueue_struct *wq) { return 0; } #endif /* CONFIG_SYSFS */ #ifdef CONFIG_WQ_WATCHDOG void wq_watchdog_touch(int cpu); #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_touch(int cpu) { } #endif /* CONFIG_WQ_WATCHDOG */ #ifdef CONFIG_SMP int workqueue_prepare_cpu(unsigned int cpu); int workqueue_online_cpu(unsigned int cpu); int workqueue_offline_cpu(unsigned int cpu); #endif void __init workqueue_init_early(void); void __init workqueue_init(void); #endif |
| 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 | // SPDX-License-Identifier: GPL-2.0-only /* * This implements the various checks for CONFIG_HARDENED_USERCOPY*, * which are designed to protect kernel memory from needless exposure * and overwrite under many unintended conditions. This code is based * on PAX_USERCOPY, which is: * * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source * Security Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/thread_info.h> #include <linux/atomic.h> #include <linux/jump_label.h> #include <asm/sections.h> /* * Checks if a given pointer and length is contained by the current * stack frame (if possible). * * Returns: * NOT_STACK: not at all on the stack * GOOD_FRAME: fully within a valid stack frame * GOOD_STACK: fully on the stack (when can't do frame-checking) * BAD_STACK: error condition (invalid stack position or bad stack frame) */ static noinline int check_stack_object(const void *obj, unsigned long len) { const void * const stack = task_stack_page(current); const void * const stackend = stack + THREAD_SIZE; int ret; /* Object is not on the stack at all. */ if (obj + len <= stack || stackend <= obj) return NOT_STACK; /* * Reject: object partially overlaps the stack (passing the * check above means at least one end is within the stack, * so if this check fails, the other end is outside the stack). */ if (obj < stack || stackend < obj + len) return BAD_STACK; /* Check if object is safely within a valid frame. */ ret = arch_within_stack_frames(stack, stackend, obj, len); if (ret) return ret; return GOOD_STACK; } /* * If these functions are reached, then CONFIG_HARDENED_USERCOPY has found * an unexpected state during a copy_from_user() or copy_to_user() call. * There are several checks being performed on the buffer by the * __check_object_size() function. Normal stack buffer usage should never * trip the checks, and kernel text addressing will always trip the check. * For cache objects, it is checking that only the whitelisted range of * bytes for a given cache is being accessed (via the cache's usersize and * useroffset fields). To adjust a cache whitelist, use the usercopy-aware * kmem_cache_create_usercopy() function to create the cache (and * carefully audit the whitelist range). */ void usercopy_warn(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len) { WARN_ONCE(1, "Bad or missing usercopy whitelist? Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", to_user ? "exposure" : "overwrite", to_user ? "from" : "to", name ? : "unknown?!", detail ? " '" : "", detail ? : "", detail ? "'" : "", offset, len); } void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len) { pr_emerg("Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", to_user ? "exposure" : "overwrite", to_user ? "from" : "to", name ? : "unknown?!", detail ? " '" : "", detail ? : "", detail ? "'" : "", offset, len); /* * For greater effect, it would be nice to do do_group_exit(), * but BUG() actually hooks all the lock-breaking and per-arch * Oops code, so that is used here instead. */ BUG(); } /* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */ static bool overlaps(const unsigned long ptr, unsigned long n, unsigned long low, unsigned long high) { const unsigned long check_low = ptr; unsigned long check_high = check_low + n; /* Does not overlap if entirely above or entirely below. */ if (check_low >= high || check_high <= low) return false; return true; } /* Is this address range in the kernel text area? */ static inline void check_kernel_text_object(const unsigned long ptr, unsigned long n, bool to_user) { unsigned long textlow = (unsigned long)_stext; unsigned long texthigh = (unsigned long)_etext; unsigned long textlow_linear, texthigh_linear; if (overlaps(ptr, n, textlow, texthigh)) usercopy_abort("kernel text", NULL, to_user, ptr - textlow, n); /* * Some architectures have virtual memory mappings with a secondary * mapping of the kernel text, i.e. there is more than one virtual * kernel address that points to the kernel image. It is usually * when there is a separate linear physical memory mapping, in that * __pa() is not just the reverse of __va(). This can be detected * and checked: */ textlow_linear = (unsigned long)lm_alias(textlow); /* No different mapping: we're done. */ if (textlow_linear == textlow) return; /* Check the secondary mapping... */ texthigh_linear = (unsigned long)lm_alias(texthigh); if (overlaps(ptr, n, textlow_linear, texthigh_linear)) usercopy_abort("linear kernel text", NULL, to_user, ptr - textlow_linear, n); } static inline void check_bogus_address(const unsigned long ptr, unsigned long n, bool to_user) { /* Reject if object wraps past end of memory. */ if (ptr + (n - 1) < ptr) usercopy_abort("wrapped address", NULL, to_user, 0, ptr + n); /* Reject if NULL or ZERO-allocation. */ if (ZERO_OR_NULL_PTR(ptr)) usercopy_abort("null address", NULL, to_user, ptr, n); } /* Checks for allocs that are marked in some way as spanning multiple pages. */ static inline void check_page_span(const void *ptr, unsigned long n, struct page *page, bool to_user) { #ifdef CONFIG_HARDENED_USERCOPY_PAGESPAN const void *end = ptr + n - 1; struct page *endpage; bool is_reserved, is_cma; /* * Sometimes the kernel data regions are not marked Reserved (see * check below). And sometimes [_sdata,_edata) does not cover * rodata and/or bss, so check each range explicitly. */ /* Allow reads of kernel rodata region (if not marked as Reserved). */ if (ptr >= (const void *)__start_rodata && end <= (const void *)__end_rodata) { if (!to_user) usercopy_abort("rodata", NULL, to_user, 0, n); return; } /* Allow kernel data region (if not marked as Reserved). */ if (ptr >= (const void *)_sdata && end <= (const void *)_edata) return; /* Allow kernel bss region (if not marked as Reserved). */ if (ptr >= (const void *)__bss_start && end <= (const void *)__bss_stop) return; /* Is the object wholly within one base page? */ if (likely(((unsigned long)ptr & (unsigned long)PAGE_MASK) == ((unsigned long)end & (unsigned long)PAGE_MASK))) return; /* Allow if fully inside the same compound (__GFP_COMP) page. */ endpage = virt_to_head_page(end); if (likely(endpage == page)) return; /* * Reject if range is entirely either Reserved (i.e. special or * device memory), or CMA. Otherwise, reject since the object spans * several independently allocated pages. */ is_reserved = PageReserved(page); is_cma = is_migrate_cma_page(page); if (!is_reserved && !is_cma) usercopy_abort("spans multiple pages", NULL, to_user, 0, n); for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) { page = virt_to_head_page(ptr); if (is_reserved && !PageReserved(page)) usercopy_abort("spans Reserved and non-Reserved pages", NULL, to_user, 0, n); if (is_cma && !is_migrate_cma_page(page)) usercopy_abort("spans CMA and non-CMA pages", NULL, to_user, 0, n); } #endif } static inline void check_heap_object(const void *ptr, unsigned long n, bool to_user) { struct page *page; if (!virt_addr_valid(ptr)) return; /* * When CONFIG_HIGHMEM=y, kmap_to_page() will give either the * highmem page or fallback to virt_to_page(). The following * is effectively a highmem-aware virt_to_head_page(). */ page = compound_head(kmap_to_page((void *)ptr)); if (PageSlab(page)) { /* Check slab allocator for flags and size. */ __check_heap_object(ptr, n, page, to_user); } else { /* Verify object does not incorrectly span multiple pages. */ check_page_span(ptr, n, page, to_user); } } static DEFINE_STATIC_KEY_FALSE_RO(bypass_usercopy_checks); /* * Validates that the given object is: * - not bogus address * - fully contained by stack (or stack frame, when available) * - fully within SLAB object (or object whitelist area, when available) * - not in kernel text */ void __check_object_size(const void *ptr, unsigned long n, bool to_user) { if (static_branch_unlikely(&bypass_usercopy_checks)) return; /* Skip all tests if size is zero. */ if (!n) return; /* Check for invalid addresses. */ check_bogus_address((const unsigned long)ptr, n, to_user); /* Check for bad stack object. */ switch (check_stack_object(ptr, n)) { case NOT_STACK: /* Object is not touching the current process stack. */ break; case GOOD_FRAME: case GOOD_STACK: /* * Object is either in the correct frame (when it * is possible to check) or just generally on the * process stack (when frame checking not available). */ return; default: usercopy_abort("process stack", NULL, to_user, 0, n); } /* Check for bad heap object. */ check_heap_object(ptr, n, to_user); /* Check for object in kernel to avoid text exposure. */ check_kernel_text_object((const unsigned long)ptr, n, to_user); } EXPORT_SYMBOL(__check_object_size); static bool enable_checks __initdata = true; static int __init parse_hardened_usercopy(char *str) { if (strtobool(str, &enable_checks)) pr_warn("Invalid option string for hardened_usercopy: '%s'\n", str); return 1; } __setup("hardened_usercopy=", parse_hardened_usercopy); static int __init set_hardened_usercopy(void) { if (enable_checks == false) static_branch_enable(&bypass_usercopy_checks); return 1; } late_initcall(set_hardened_usercopy); |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 | /* SPDX-License-Identifier: GPL-2.0 */ /* * descriptor table internals; you almost certainly want file.h instead. */ #ifndef __LINUX_FDTABLE_H #define __LINUX_FDTABLE_H #include <linux/posix_types.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/atomic.h> /* * The default fd array needs to be at least BITS_PER_LONG, * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG #define NR_OPEN_MAX ~0U struct fdtable { unsigned int max_fds; struct file __rcu **fd; /* current fd array */ unsigned long *close_on_exec; unsigned long *open_fds; unsigned long *full_fds_bits; struct rcu_head rcu; }; static inline bool close_on_exec(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->close_on_exec); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Open file table structure */ struct files_struct { /* * read mostly part */ atomic_t count; bool resize_in_progress; wait_queue_head_t resize_wait; struct fdtable __rcu *fdt; struct fdtable fdtab; /* * written part on a separate cache line in SMP */ spinlock_t file_lock ____cacheline_aligned_in_smp; unsigned int next_fd; unsigned long close_on_exec_init[1]; unsigned long open_fds_init[1]; unsigned long full_fds_bits_init[1]; struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; struct file_operations; struct vfsmount; struct dentry; #define rcu_dereference_check_fdtable(files, fdtfd) \ rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock)) #define files_fdtable(files) \ rcu_dereference_check_fdtable((files), (files)->fdt) /* * The caller must ensure that fd table isn't shared or hold rcu or file lock */ static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = rcu_dereference_raw(files->fdt); if (fd < fdt->max_fds) { fd = array_index_nospec(fd, fdt->max_fds); return rcu_dereference_raw(fdt->fd[fd]); } return NULL; } static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return files_lookup_fd_raw(files, fd); } static inline struct file *files_lookup_fd_rcu(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious rcu_dereference_check() usage"); return files_lookup_fd_raw(files, fd); } static inline struct file *lookup_fd_rcu(unsigned int fd) { return files_lookup_fd_rcu(current->files, fd); } struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd); struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *fd); struct task_struct; struct files_struct *get_files_struct(struct task_struct *); void put_files_struct(struct files_struct *fs); int unshare_files(void); struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), const void *); extern int close_fd(unsigned int fd); extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); extern int close_fd_get_file(unsigned int fd, struct file **res); extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds, struct files_struct **new_fdp); extern struct kmem_cache *files_cachep; #endif /* __LINUX_FDTABLE_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 1997 Linus Torvalds * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation) */ #include <linux/export.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/backing-dev.h> #include <linux/hash.h> #include <linux/swap.h> #include <linux/security.h> #include <linux/cdev.h> #include <linux/memblock.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/mount.h> #include <linux/posix_acl.h> #include <linux/prefetch.h> #include <linux/buffer_head.h> /* for inode_has_buffers */ #include <linux/ratelimit.h> #include <linux/list_lru.h> #include <linux/iversion.h> #include <trace/events/writeback.h> #include "internal.h" /* * Inode locking rules: * * inode->i_lock protects: * inode->i_state, inode->i_hash, __iget() * Inode LRU list locks protect: * inode->i_sb->s_inode_lru, inode->i_lru * inode->i_sb->s_inode_list_lock protects: * inode->i_sb->s_inodes, inode->i_sb_list * bdi->wb.list_lock protects: * bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list * inode_hash_lock protects: * inode_hashtable, inode->i_hash * * Lock ordering: * * inode->i_sb->s_inode_list_lock * inode->i_lock * Inode LRU list locks * * bdi->wb.list_lock * inode->i_lock * * inode_hash_lock * inode->i_sb->s_inode_list_lock * inode->i_lock * * iunique_lock * inode_hash_lock */ static unsigned int i_hash_mask __read_mostly; static unsigned int i_hash_shift __read_mostly; static struct hlist_head *inode_hashtable __read_mostly; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock); /* * Empty aops. Can be used for the cases where the user does not * define any of the address_space operations. */ const struct address_space_operations empty_aops = { }; EXPORT_SYMBOL(empty_aops); /* * Statistics gathering.. */ struct inodes_stat_t inodes_stat; static DEFINE_PER_CPU(unsigned long, nr_inodes); static DEFINE_PER_CPU(unsigned long, nr_unused); static struct kmem_cache *inode_cachep __read_mostly; static long get_nr_inodes(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_inodes, i); return sum < 0 ? 0 : sum; } static inline long get_nr_inodes_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_unused, i); return sum < 0 ? 0 : sum; } long get_nr_dirty_inodes(void) { /* not actually dirty inodes, but a wild approximation */ long nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; } /* * Handle nr_inode sysctl */ #ifdef CONFIG_SYSCTL int proc_nr_inodes(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif static int no_open(struct inode *inode, struct file *file) { return -ENXIO; } /** * inode_init_always - perform inode structure initialisation * @sb: superblock inode belongs to * @inode: inode to initialise * * These are initializations that need to be done on every inode * allocation as the fields are not initialised by slab allocation. */ int inode_init_always(struct super_block *sb, struct inode *inode) { static const struct inode_operations empty_iops; static const struct file_operations no_open_fops = {.open = no_open}; struct address_space *const mapping = &inode->i_data; inode->i_sb = sb; inode->i_blkbits = sb->s_blocksize_bits; inode->i_flags = 0; atomic64_set(&inode->i_sequence, 0); atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; inode->i_fop = &no_open_fops; inode->__i_nlink = 1; inode->i_opflags = 0; if (sb->s_xattr) inode->i_opflags |= IOP_XATTR; i_uid_write(inode, 0); i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); inode->i_size = 0; inode->i_write_hint = WRITE_LIFE_NOT_SET; inode->i_blocks = 0; inode->i_bytes = 0; inode->i_generation = 0; inode->i_pipe = NULL; inode->i_bdev = NULL; inode->i_cdev = NULL; inode->i_link = NULL; inode->i_dir_seq = 0; inode->i_rdev = 0; inode->dirtied_when = 0; #ifdef CONFIG_CGROUP_WRITEBACK inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; #endif spin_lock_init(&inode->i_lock); lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key); atomic_set(&inode->i_dio_count, 0); mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; if (sb->s_type->fs_flags & FS_THP_SUPPORT) __set_bit(AS_THP_SUPPORT, &mapping->flags); mapping->wb_err = 0; atomic_set(&mapping->i_mmap_writable, 0); #ifdef CONFIG_READ_ONLY_THP_FOR_FS atomic_set(&mapping->nr_thps, 0); #endif mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); mapping->private_data = NULL; mapping->writeback_index = 0; inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ #ifdef CONFIG_FS_POSIX_ACL inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; #endif #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; #endif inode->i_flctx = NULL; if (unlikely(security_inode_alloc(inode))) return -ENOMEM; this_cpu_inc(nr_inodes); return 0; } EXPORT_SYMBOL(inode_init_always); void free_inode_nonrcu(struct inode *inode) { kmem_cache_free(inode_cachep, inode); } EXPORT_SYMBOL(free_inode_nonrcu); static void i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); if (inode->free_inode) inode->free_inode(inode); else free_inode_nonrcu(inode); } static struct inode *alloc_inode(struct super_block *sb) { const struct super_operations *ops = sb->s_op; struct inode *inode; if (ops->alloc_inode) inode = ops->alloc_inode(sb); else inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL); if (!inode) return NULL; if (unlikely(inode_init_always(sb, inode))) { if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return NULL; } inode->free_inode = ops->free_inode; i_callback(&inode->i_rcu); return NULL; } return inode; } void __destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); inode_detach_wb(inode); security_inode_free(inode); fsnotify_inode_delete(inode); locks_free_lock_context(inode); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); } #ifdef CONFIG_FS_POSIX_ACL if (inode->i_acl && !is_uncached_acl(inode->i_acl)) posix_acl_release(inode->i_acl); if (inode->i_default_acl && !is_uncached_acl(inode->i_default_acl)) posix_acl_release(inode->i_default_acl); #endif this_cpu_dec(nr_inodes); } EXPORT_SYMBOL(__destroy_inode); static void destroy_inode(struct inode *inode) { const struct super_operations *ops = inode->i_sb->s_op; BUG_ON(!list_empty(&inode->i_lru)); __destroy_inode(inode); if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return; } inode->free_inode = ops->free_inode; call_rcu(&inode->i_rcu, i_callback); } /** * drop_nlink - directly drop an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. In cases * where we are attempting to track writes to the * filesystem, a decrement to zero means an imminent * write when the file is truncated and actually unlinked * on the filesystem. */ void drop_nlink(struct inode *inode) { WARN_ON(inode->i_nlink == 0); inode->__i_nlink--; if (!inode->i_nlink) atomic_long_inc(&inode->i_sb->s_remove_count); } EXPORT_SYMBOL(drop_nlink); /** * clear_nlink - directly zero an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. See * drop_nlink() for why we care about i_nlink hitting zero. */ void clear_nlink(struct inode *inode) { if (inode->i_nlink) { inode->__i_nlink = 0; atomic_long_inc(&inode->i_sb->s_remove_count); } } EXPORT_SYMBOL(clear_nlink); /** * set_nlink - directly set an inode's link count * @inode: inode * @nlink: new nlink (should be non-zero) * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. */ void set_nlink(struct inode *inode, unsigned int nlink) { if (!nlink) { clear_nlink(inode); } else { /* Yes, some filesystems do change nlink from zero to one */ if (inode->i_nlink == 0) atomic_long_dec(&inode->i_sb->s_remove_count); inode->__i_nlink = nlink; } } EXPORT_SYMBOL(set_nlink); /** * inc_nlink - directly increment an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. Currently, * it is only here for parity with dec_nlink(). */ void inc_nlink(struct inode *inode) { if (unlikely(inode->i_nlink == 0)) { WARN_ON(!(inode->i_state & I_LINKABLE)); atomic_long_dec(&inode->i_sb->s_remove_count); } inode->__i_nlink++; } EXPORT_SYMBOL(inc_nlink); static void __address_space_init_once(struct address_space *mapping) { xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); mapping->i_mmap = RB_ROOT_CACHED; } void address_space_init_once(struct address_space *mapping) { memset(mapping, 0, sizeof(*mapping)); __address_space_init_once(mapping); } EXPORT_SYMBOL(address_space_init_once); /* * These are initializations that only need to be done * once, because the fields are idempotent across use * of the inode, so let the slab aware of that. */ void inode_init_once(struct inode *inode) { memset(inode, 0, sizeof(*inode)); INIT_HLIST_NODE(&inode->i_hash); INIT_LIST_HEAD(&inode->i_devices); INIT_LIST_HEAD(&inode->i_io_list); INIT_LIST_HEAD(&inode->i_wb_list); INIT_LIST_HEAD(&inode->i_lru); __address_space_init_once(&inode->i_data); i_size_ordered_init(inode); } EXPORT_SYMBOL(inode_init_once); static void init_once(void *foo) { struct inode *inode = (struct inode *) foo; inode_init_once(inode); } /* * inode->i_lock must be held */ void __iget(struct inode *inode) { atomic_inc(&inode->i_count); } /* * get additional reference to inode; caller must already hold one. */ void ihold(struct inode *inode) { WARN_ON(atomic_inc_return(&inode->i_count) < 2); } EXPORT_SYMBOL(ihold); static void inode_lru_list_add(struct inode *inode) { if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); else inode->i_state |= I_REFERENCED; } /* * Add inode to LRU if needed (inode is unused and clean). * * Needs inode->i_lock held. */ void inode_add_lru(struct inode *inode) { if (!(inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) && !atomic_read(&inode->i_count) && inode->i_sb->s_flags & SB_ACTIVE) inode_lru_list_add(inode); } static void inode_lru_list_del(struct inode *inode) { if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); } static void inode_pin_lru_isolating(struct inode *inode) { lockdep_assert_held(&inode->i_lock); WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); inode->i_state |= I_LRU_ISOLATING; } static void inode_unpin_lru_isolating(struct inode *inode) { spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); inode->i_state &= ~I_LRU_ISOLATING; smp_mb(); wake_up_bit(&inode->i_state, __I_LRU_ISOLATING); spin_unlock(&inode->i_lock); } static void inode_wait_for_lru_isolating(struct inode *inode) { spin_lock(&inode->i_lock); if (inode->i_state & I_LRU_ISOLATING) { DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING); wait_queue_head_t *wqh; wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING); spin_unlock(&inode->i_lock); __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); spin_lock(&inode->i_lock); WARN_ON(inode->i_state & I_LRU_ISOLATING); } spin_unlock(&inode->i_lock); } /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add */ void inode_sb_list_add(struct inode *inode) { spin_lock(&inode->i_sb->s_inode_list_lock); list_add(&inode->i_sb_list, &inode->i_sb->s_inodes); spin_unlock(&inode->i_sb->s_inode_list_lock); } EXPORT_SYMBOL_GPL(inode_sb_list_add); static inline void inode_sb_list_del(struct inode *inode) { if (!list_empty(&inode->i_sb_list)) { spin_lock(&inode->i_sb->s_inode_list_lock); list_del_init(&inode->i_sb_list); spin_unlock(&inode->i_sb->s_inode_list_lock); } } static unsigned long hash(struct super_block *sb, unsigned long hashval) { unsigned long tmp; tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) / L1_CACHE_BYTES; tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift); return tmp & i_hash_mask; } /** * __insert_inode_hash - hash an inode * @inode: unhashed inode * @hashval: unsigned long value used to locate this object in the * inode_hashtable. * * Add an inode to the inode hash for this superblock. */ void __insert_inode_hash(struct inode *inode, unsigned long hashval) { struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval); spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_add_head_rcu(&inode->i_hash, b); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__insert_inode_hash); /** * __remove_inode_hash - remove an inode from the hash * @inode: inode to unhash * * Remove an inode from the superblock. */ void __remove_inode_hash(struct inode *inode) { spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_del_init_rcu(&inode->i_hash); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__remove_inode_hash); void clear_inode(struct inode *inode) { /* * We have to cycle the i_pages lock here because reclaim can be in the * process of removing the last page (in __delete_from_page_cache()) * and we must not free the mapping under it. */ xa_lock_irq(&inode->i_data.i_pages); BUG_ON(inode->i_data.nrpages); BUG_ON(inode->i_data.nrexceptional); xa_unlock_irq(&inode->i_data.i_pages); BUG_ON(!list_empty(&inode->i_data.private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); BUG_ON(!list_empty(&inode->i_wb_list)); /* don't need i_lock here, no concurrent mods to i_state */ inode->i_state = I_FREEING | I_CLEAR; } EXPORT_SYMBOL(clear_inode); /* * Free the inode passed in, removing it from the lists it is still connected * to. We remove any pages still attached to the inode and wait for any IO that * is still in progress before finally destroying the inode. * * An inode must already be marked I_FREEING so that we avoid the inode being * moved back onto lists if we race with other code that manipulates the lists * (e.g. writeback_single_inode). The caller is responsible for setting this. * * An inode must already be removed from the LRU list before being evicted from * the cache. This should occur atomically with setting the I_FREEING state * flag, so no inodes here should ever be on the LRU when being evicted. */ static void evict(struct inode *inode) { const struct super_operations *op = inode->i_sb->s_op; BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(!list_empty(&inode->i_lru)); if (!list_empty(&inode->i_io_list)) inode_io_list_del(inode); inode_sb_list_del(inode); inode_wait_for_lru_isolating(inode); /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since * the inode has I_FREEING set, flusher thread won't start new work on * the inode. We just have to wait for running writeback to finish. */ inode_wait_for_writeback(inode); if (op->evict_inode) { op->evict_inode(inode); } else { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } if (S_ISBLK(inode->i_mode) && inode->i_bdev) bd_forget(inode); if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(inode); remove_inode_hash(inode); spin_lock(&inode->i_lock); wake_up_bit(&inode->i_state, __I_NEW); BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); spin_unlock(&inode->i_lock); destroy_inode(inode); } /* * dispose_list - dispose of the contents of a local list * @head: the head of the list to free * * Dispose-list gets a local list with local inodes in it, so it doesn't * need to worry about list corruption and SMP locks. */ static void dispose_list(struct list_head *head) { while (!list_empty(head)) { struct inode *inode; inode = list_first_entry(head, struct inode, i_lru); list_del_init(&inode->i_lru); evict(inode); cond_resched(); } } /** * evict_inodes - evict all evictable inodes for a superblock * @sb: superblock to operate on * * Make sure that no inodes with zero refcount are retained. This is * called by superblock shutdown after having SB_ACTIVE flag removed, * so any inode reaching zero refcount during or after that call will * be immediately evicted. */ void evict_inodes(struct super_block *sb) { struct inode *inode, *next; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { if (atomic_read(&inode->i_count)) continue; spin_lock(&inode->i_lock); if (atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); continue; } if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); /* * We can have a ton of inodes to evict at unmount time given * enough memory, check to see if we need to go to sleep for a * bit so we don't livelock. */ if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); } EXPORT_SYMBOL_GPL(evict_inodes); /** * invalidate_inodes - attempt to free all inodes on a superblock * @sb: superblock to operate on * @kill_dirty: flag to guide handling of dirty inodes * * Attempts to free all inodes for a given superblock. If there were any * busy inodes return a non-zero value, else zero. * If @kill_dirty is set, discard dirty inodes too, otherwise treat * them as busy. */ int invalidate_inodes(struct super_block *sb, bool kill_dirty) { int busy = 0; struct inode *inode, *next; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } if (inode->i_state & I_DIRTY_ALL && !kill_dirty) { spin_unlock(&inode->i_lock); busy = 1; continue; } if (atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); busy = 1; continue; } inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); return busy; } /* * Isolate the inode from the LRU in preparation for freeing it. * * Any inodes which are pinned purely because of attached pagecache have their * pagecache removed. If the inode has metadata buffers attached to * mapping->private_list then try to remove them. * * If the inode has the I_REFERENCED flag set, then it means that it has been * used recently - the flag is set in iput_final(). When we encounter such an * inode, clear the flag and move it to the back of the LRU so it gets another * pass through the LRU before it gets reclaimed. This is necessary because of * the fact we are doing lazy LRU updates to minimise lock contention so the * LRU does not have strict ordering. Hence we don't want to reclaim inodes * with this flag set because they are the inodes that are out of order. */ static enum lru_status inode_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct inode *inode = container_of(item, struct inode, i_lru); /* * we are inverting the lru lock/inode->i_lock here, so use a trylock. * If we fail to get the lock, just skip it. */ if (!spin_trylock(&inode->i_lock)) return LRU_SKIP; /* * Referenced or dirty inodes are still in use. Give them another pass * through the LRU as we canot reclaim them now. */ if (atomic_read(&inode->i_count) || (inode->i_state & ~I_REFERENCED)) { list_lru_isolate(lru, &inode->i_lru); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* recently referenced inodes get one more pass */ if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; } if (inode_has_buffers(inode) || inode->i_data.nrpages) { inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { unsigned long reap; reap = invalidate_mapping_pages(&inode->i_data, 0, -1); if (current_is_kswapd()) __count_vm_events(KSWAPD_INODESTEAL, reap); else __count_vm_events(PGINODESTEAL, reap); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += reap; } inode_unpin_lru_isolating(inode); spin_lock(lru_lock); return LRU_RETRY; } WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; list_lru_isolate_move(lru, &inode->i_lru, freeable); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* * Walk the superblock inode LRU for freeable inodes and attempt to free them. * This is called from the superblock shrinker function with a number of inodes * to trim from the LRU. Inodes to be freed are moved to a temporary list and * then are freed outside inode_lock by dispose_list(). */ long prune_icache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(freeable); long freed; freed = list_lru_shrink_walk(&sb->s_inode_lru, sc, inode_lru_isolate, &freeable); dispose_list(&freeable); return freed; } static void __wait_on_freeing_inode(struct inode *inode); /* * Called with the inode lock held. */ static struct inode *find_inode(struct super_block *sb, struct hlist_head *head, int (*test)(struct inode *, void *), void *data) { struct inode *inode = NULL; repeat: hlist_for_each_entry(inode, head, i_hash) { if (inode->i_sb != sb) continue; if (!test(inode, data)) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE)) { __wait_on_freeing_inode(inode); goto repeat; } if (unlikely(inode->i_state & I_CREATING)) { spin_unlock(&inode->i_lock); return ERR_PTR(-ESTALE); } __iget(inode); spin_unlock(&inode->i_lock); return inode; } return NULL; } /* * find_inode_fast is the fast path version of find_inode, see the comment at * iget_locked for details. */ static struct inode *find_inode_fast(struct super_block *sb, struct hlist_head *head, unsigned long ino) { struct inode *inode = NULL; repeat: hlist_for_each_entry(inode, head, i_hash) { if (inode->i_ino != ino) continue; if (inode->i_sb != sb) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE)) { __wait_on_freeing_inode(inode); goto repeat; } if (unlikely(inode->i_state & I_CREATING)) { spin_unlock(&inode->i_lock); return ERR_PTR(-ESTALE); } __iget(inode); spin_unlock(&inode->i_lock); return inode; } return NULL; } /* * Each cpu owns a range of LAST_INO_BATCH numbers. * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations, * to renew the exhausted range. * * This does not significantly increase overflow rate because every CPU can * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the * 2^32 range, and is a worst-case. Even a 50% wastage would only increase * overflow rate by 2x, which does not seem too significant. * * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ #define LAST_INO_BATCH 1024 static DEFINE_PER_CPU(unsigned int, last_ino); unsigned int get_next_ino(void) { unsigned int *p = &get_cpu_var(last_ino); unsigned int res = *p; #ifdef CONFIG_SMP if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) { static atomic_t shared_last_ino; int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino); res = next - LAST_INO_BATCH; } #endif res++; /* get_next_ino should not provide a 0 inode number */ if (unlikely(!res)) res++; *p = res; put_cpu_var(last_ino); return res; } EXPORT_SYMBOL(get_next_ino); /** * new_inode_pseudo - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. * Inode wont be chained in superblock s_inodes list * This means : * - fs can't be unmount * - quotas, fsnotify, writeback can't work */ struct inode *new_inode_pseudo(struct super_block *sb) { struct inode *inode = alloc_inode(sb); if (inode) { spin_lock(&inode->i_lock); inode->i_state = 0; spin_unlock(&inode->i_lock); INIT_LIST_HEAD(&inode->i_sb_list); } return inode; } /** * new_inode - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. The default gfp_mask * for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE. * If HIGHMEM pages are unsuitable or it is known that pages allocated * for the page cache are not reclaimable or migratable, * mapping_set_gfp_mask() must be called with suitable flags on the * newly created inode's mapping * */ struct inode *new_inode(struct super_block *sb) { struct inode *inode; spin_lock_prefetch(&sb->s_inode_list_lock); inode = new_inode_pseudo(sb); if (inode) inode_sb_list_add(inode); return inode; } EXPORT_SYMBOL(new_inode); #ifdef CONFIG_DEBUG_LOCK_ALLOC void lockdep_annotate_inode_mutex_key(struct inode *inode) { if (S_ISDIR(inode->i_mode)) { struct file_system_type *type = inode->i_sb->s_type; /* Set new key only if filesystem hasn't already changed it */ if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) { /* * ensure nobody is actually holding i_mutex */ // mutex_destroy(&inode->i_mutex); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &type->i_mutex_dir_key); } } } EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key); #endif /** * unlock_new_inode - clear the I_NEW state and wake up any waiters * @inode: new inode to unlock * * Called when the inode is fully initialised to clear the new state of the * inode and wake up anyone waiting for the inode to finish initialisation. */ void unlock_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(unlock_new_inode); void discard_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); iput(inode); } EXPORT_SYMBOL(discard_new_inode); /** * lock_two_inodes - lock two inodes (may be regular files but also dirs) * * Lock any non-NULL argument. The caller must make sure that if he is passing * in two directories, one is not ancestor of the other. Zero, one or two * objects may be locked by this function. * * @inode1: first inode to lock * @inode2: second inode to lock * @subclass1: inode lock subclass for the first lock obtained * @subclass2: inode lock subclass for the second lock obtained */ void lock_two_inodes(struct inode *inode1, struct inode *inode2, unsigned subclass1, unsigned subclass2) { if (!inode1 || !inode2) { /* * Make sure @subclass1 will be used for the acquired lock. * This is not strictly necessary (no current caller cares) but * let's keep things consistent. */ if (!inode1) swap(inode1, inode2); goto lock; } /* * If one object is directory and the other is not, we must make sure * to lock directory first as the other object may be its child. */ if (S_ISDIR(inode2->i_mode) == S_ISDIR(inode1->i_mode)) { if (inode1 > inode2) swap(inode1, inode2); } else if (!S_ISDIR(inode1->i_mode)) swap(inode1, inode2); lock: if (inode1) inode_lock_nested(inode1, subclass1); if (inode2 && inode2 != inode1) inode_lock_nested(inode2, subclass2); } /** * lock_two_nondirectories - take two i_mutexes on non-directory objects * * Lock any non-NULL argument that is not a directory. * Zero, one or two objects may be locked by this function. * * @inode1: first inode to lock * @inode2: second inode to lock */ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1 > inode2) swap(inode1, inode2); if (inode1 && !S_ISDIR(inode1->i_mode)) inode_lock(inode1); if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1) inode_lock_nested(inode2, I_MUTEX_NONDIR2); } EXPORT_SYMBOL(lock_two_nondirectories); /** * unlock_two_nondirectories - release locks from lock_two_nondirectories() * @inode1: first inode to unlock * @inode2: second inode to unlock */ void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1 && !S_ISDIR(inode1->i_mode)) inode_unlock(inode1); if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1) inode_unlock(inode2); } EXPORT_SYMBOL(unlock_two_nondirectories); /** * inode_insert5 - obtain an inode from a mounted file system * @inode: pre-allocated inode to use for insert to cache * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present it is return it with an increased reference count. This is * a variant of iget5_locked() for callers that don't want to fail on memory * allocation of inode. * * If the inode is not in cache, insert the pre-allocated inode to cache and * return it locked, hashed, and with the I_NEW flag set. The file system gets * to fill it in before unlocking it via unlock_new_inode(). * * Note both @test and @set are called with the inode_hash_lock held, so can't * sleep. */ struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval); struct inode *old; bool creating = inode->i_state & I_CREATING; again: spin_lock(&inode_hash_lock); old = find_inode(inode->i_sb, head, test, data); if (unlikely(old)) { /* * Uhhuh, somebody else created the same inode under us. * Use the old inode instead of the preallocated one. */ spin_unlock(&inode_hash_lock); if (IS_ERR(old)) return NULL; wait_on_inode(old); if (unlikely(inode_unhashed(old))) { iput(old); goto again; } return old; } if (set && unlikely(set(inode, data))) { inode = NULL; goto unlock; } /* * Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ spin_lock(&inode->i_lock); inode->i_state |= I_NEW; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); if (!creating) inode_sb_list_add(inode); unlock: spin_unlock(&inode_hash_lock); return inode; } EXPORT_SYMBOL(inode_insert5); /** * iget5_locked - obtain an inode from a mounted file system * @sb: super block of file system * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present it is return it with an increased reference count. This is * a generalized version of iget_locked() for file systems where the inode * number is not sufficient for unique identification of an inode. * * If the inode is not in cache, allocate a new inode and return it locked, * hashed, and with the I_NEW flag set. The file system gets to fill it in * before unlocking it via unlock_new_inode(). * * Note both @test and @set are called with the inode_hash_lock held, so can't * sleep. */ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct inode *inode = ilookup5(sb, hashval, test, data); if (!inode) { struct inode *new = alloc_inode(sb); if (new) { new->i_state = 0; inode = inode_insert5(new, hashval, test, set, data); if (unlikely(inode != new)) destroy_inode(new); } } return inode; } EXPORT_SYMBOL(iget5_locked); /** * iget_locked - obtain an inode from a mounted file system * @sb: super block of file system * @ino: inode number to get * * Search for the inode specified by @ino in the inode cache and if present * return it with an increased reference count. This is for file systems * where the inode number is sufficient for unique identification of an inode. * * If the inode is not in cache, allocate a new inode and return it locked, * hashed, and with the I_NEW flag set. The file system gets to fill it in * before unlocking it via unlock_new_inode(). */ struct inode *iget_locked(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: spin_lock(&inode_hash_lock); inode = find_inode_fast(sb, head, ino); spin_unlock(&inode_hash_lock); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } return inode; } inode = alloc_inode(sb); if (inode) { struct inode *old; spin_lock(&inode_hash_lock); /* We released the lock, so.. */ old = find_inode_fast(sb, head, ino); if (!old) { inode->i_ino = ino; spin_lock(&inode->i_lock); inode->i_state = I_NEW; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); inode_sb_list_add(inode); spin_unlock(&inode_hash_lock); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ return inode; } /* * Uhhuh, somebody else created the same inode under * us. Use the old inode instead of the one we just * allocated. */ spin_unlock(&inode_hash_lock); destroy_inode(inode); if (IS_ERR(old)) return NULL; inode = old; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(iget_locked); /* * search the inode cache for a matching inode number. * If we find one, then the inode number we are trying to * allocate is not unique and so we should not use it. * * Returns 1 if the inode number is unique, 0 if it is not. */ static int test_inode_iunique(struct super_block *sb, unsigned long ino) { struct hlist_head *b = inode_hashtable + hash(sb, ino); struct inode *inode; hlist_for_each_entry_rcu(inode, b, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb) return 0; } return 1; } /** * iunique - get a unique inode number * @sb: superblock * @max_reserved: highest reserved inode number * * Obtain an inode number that is unique on the system for a given * superblock. This is used by file systems that have no natural * permanent inode numbering system. An inode number is returned that * is higher than the reserved limit but unique. * * BUGS: * With a large number of inodes live on the file system this function * currently becomes quite slow. */ ino_t iunique(struct super_block *sb, ino_t max_reserved) { /* * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ static DEFINE_SPINLOCK(iunique_lock); static unsigned int counter; ino_t res; rcu_read_lock(); spin_lock(&iunique_lock); do { if (counter <= max_reserved) counter = max_reserved + 1; res = counter++; } while (!test_inode_iunique(sb, res)); spin_unlock(&iunique_lock); rcu_read_unlock(); return res; } EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { spin_lock(&inode->i_lock); if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) { __iget(inode); spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); /* * Handle the case where s_op->clear_inode is not been * called yet, and somebody is calling igrab * while the inode is getting freed. */ inode = NULL; } return inode; } EXPORT_SYMBOL(igrab); /** * ilookup5_nowait - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache. * If the inode is in the cache, the inode is returned with an incremented * reference count. * * Note: I_NEW is not waited upon so you have to be very careful what you do * with the returned inode. You probably should be using ilookup5() instead. * * Note2: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; spin_lock(&inode_hash_lock); inode = find_inode(sb, head, test, data); spin_unlock(&inode_hash_lock); return IS_ERR(inode) ? NULL : inode; } EXPORT_SYMBOL(ilookup5_nowait); /** * ilookup5 - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache, * and if the inode is in the cache, return the inode with an incremented * reference count. Waits on I_NEW before returning the inode. * returned with an incremented reference count. * * This is a generalized version of ilookup() for file systems where the * inode number is not sufficient for unique identification of an inode. * * Note: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *inode; again: inode = ilookup5_nowait(sb, hashval, test, data); if (inode) { wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup5); /** * ilookup - search for an inode in the inode cache * @sb: super block of file system to search * @ino: inode number to search for * * Search for the inode @ino in the inode cache, and if the inode is in the * cache, the inode is returned with an incremented reference count. */ struct inode *ilookup(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: spin_lock(&inode_hash_lock); inode = find_inode_fast(sb, head, ino); spin_unlock(&inode_hash_lock); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup); /** * find_inode_nowait - find an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @match: callback used for comparisons between inodes * @data: opaque data pointer to pass to @match * * Search for the inode specified by @hashval and @data in the inode * cache, where the helper function @match will return 0 if the inode * does not match, 1 if the inode does match, and -1 if the search * should be stopped. The @match function must be responsible for * taking the i_lock spin_lock and checking i_state for an inode being * freed or being initialized, and incrementing the reference count * before returning 1. It also must not sleep, since it is called with * the inode_hash_lock spinlock held. * * This is a even more generalized version of ilookup5() when the * function must never block --- find_inode() can block in * __wait_on_freeing_inode() --- or when the caller can not increment * the reference count because the resulting iput() might cause an * inode eviction. The tradeoff is that the @match funtion must be * very carefully implemented. */ struct inode *find_inode_nowait(struct super_block *sb, unsigned long hashval, int (*match)(struct inode *, unsigned long, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode, *ret_inode = NULL; int mval; spin_lock(&inode_hash_lock); hlist_for_each_entry(inode, head, i_hash) { if (inode->i_sb != sb) continue; mval = match(inode, hashval, data); if (mval == 0) continue; if (mval == 1) ret_inode = inode; goto out; } out: spin_unlock(&inode_hash_lock); return ret_inode; } EXPORT_SYMBOL(find_inode_nowait); /** * find_inode_rcu - find an inode in the inode cache * @sb: Super block of file system to search * @hashval: Key to hash * @test: Function to test match on an inode * @data: Data for test function * * Search for the inode specified by @hashval and @data in the inode cache, * where the helper function @test will return 0 if the inode does not match * and 1 if it does. The @test function must be responsible for taking the * i_lock spin_lock and checking i_state for an inode being freed or being * initialized. * * If successful, this will return the inode for which the @test function * returned 1 and NULL otherwise. * * The @test function is not permitted to take a ref on any inode presented. * It is also not permitted to sleep. * * The caller must hold the RCU read lock. */ struct inode *find_inode_rcu(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious find_inode_rcu() usage"); hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_sb == sb && !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE)) && test(inode, data)) return inode; } return NULL; } EXPORT_SYMBOL(find_inode_rcu); /** * find_inode_by_rcu - Find an inode in the inode cache * @sb: Super block of file system to search * @ino: The inode number to match * * Search for the inode specified by @hashval and @data in the inode cache, * where the helper function @test will return 0 if the inode does not match * and 1 if it does. The @test function must be responsible for taking the * i_lock spin_lock and checking i_state for an inode being freed or being * initialized. * * If successful, this will return the inode for which the @test function * returned 1 and NULL otherwise. * * The @test function is not permitted to take a ref on any inode presented. * It is also not permitted to sleep. * * The caller must hold the RCU read lock. */ struct inode *find_inode_by_ino_rcu(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "suspicious find_inode_by_ino_rcu() usage"); hlist_for_each_entry_rcu(inode, head, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb && !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE))) return inode; } return NULL; } EXPORT_SYMBOL(find_inode_by_ino_rcu); int insert_inode_locked(struct inode *inode) { struct super_block *sb = inode->i_sb; ino_t ino = inode->i_ino; struct hlist_head *head = inode_hashtable + hash(sb, ino); while (1) { struct inode *old = NULL; spin_lock(&inode_hash_lock); hlist_for_each_entry(old, head, i_hash) { if (old->i_ino != ino) continue; if (old->i_sb != sb) continue; spin_lock(&old->i_lock); if (old->i_state & (I_FREEING|I_WILL_FREE)) { spin_unlock(&old->i_lock); continue; } break; } if (likely(!old)) { spin_lock(&inode->i_lock); inode->i_state |= I_NEW | I_CREATING; hlist_add_head_rcu(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); return 0; } if (unlikely(old->i_state & I_CREATING)) { spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); return -EBUSY; } __iget(old); spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); wait_on_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); return -EBUSY; } iput(old); } } EXPORT_SYMBOL(insert_inode_locked); int insert_inode_locked4(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *old; inode->i_state |= I_CREATING; old = inode_insert5(inode, hashval, test, NULL, data); if (old != inode) { iput(old); return -EBUSY; } return 0; } EXPORT_SYMBOL(insert_inode_locked4); int generic_delete_inode(struct inode *inode) { return 1; } EXPORT_SYMBOL(generic_delete_inode); /* * Called when we're dropping the last reference * to an inode. * * Call the FS "drop_inode()" function, defaulting to * the legacy UNIX filesystem behaviour. If it tells * us to evict inode, do so. Otherwise, retain inode * in cache if fs is alive, sync and evict if fs is * shutting down. */ static void iput_final(struct inode *inode) { struct super_block *sb = inode->i_sb; const struct super_operations *op = inode->i_sb->s_op; unsigned long state; int drop; WARN_ON(inode->i_state & I_NEW); if (op->drop_inode) drop = op->drop_inode(inode); else drop = generic_drop_inode(inode); if (!drop && !(inode->i_state & I_DONTCACHE) && (sb->s_flags & SB_ACTIVE)) { inode_add_lru(inode); spin_unlock(&inode->i_lock); return; } state = inode->i_state; if (!drop) { WRITE_ONCE(inode->i_state, state | I_WILL_FREE); spin_unlock(&inode->i_lock); write_inode_now(inode, 1); spin_lock(&inode->i_lock); state = inode->i_state; WARN_ON(state & I_NEW); state &= ~I_WILL_FREE; } WRITE_ONCE(inode->i_state, state | I_FREEING); if (!list_empty(&inode->i_lru)) inode_lru_list_del(inode); spin_unlock(&inode->i_lock); evict(inode); } /** * iput - put an inode * @inode: inode to put * * Puts an inode, dropping its usage count. If the inode use count hits * zero, the inode is then freed and may also be destroyed. * * Consequently, iput() can sleep. */ void iput(struct inode *inode) { if (!inode) return; BUG_ON(inode->i_state & I_CLEAR); retry: if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) { if (inode->i_nlink && (inode->i_state & I_DIRTY_TIME)) { atomic_inc(&inode->i_count); spin_unlock(&inode->i_lock); trace_writeback_lazytime_iput(inode); mark_inode_dirty_sync(inode); goto retry; } iput_final(inode); } } EXPORT_SYMBOL(iput); #ifdef CONFIG_BLOCK /** * bmap - find a block number in a file * @inode: inode owning the block number being requested * @block: pointer containing the block to find * * Replaces the value in ``*block`` with the block number on the device holding * corresponding to the requested block number in the file. * That is, asked for block 4 of inode 1 the function will replace the * 4 in ``*block``, with disk block relative to the disk start that holds that * block of the file. * * Returns -EINVAL in case of error, 0 otherwise. If mapping falls into a * hole, returns 0 and ``*block`` is also set to 0. */ int bmap(struct inode *inode, sector_t *block) { if (!inode->i_mapping->a_ops->bmap) return -EINVAL; *block = inode->i_mapping->a_ops->bmap(inode->i_mapping, *block); return 0; } EXPORT_SYMBOL(bmap); #endif /* * With relative atime, only update atime if the previous atime is * earlier than either the ctime or mtime or if at least a day has * passed since the last atime update. */ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, struct timespec64 now) { if (!(mnt->mnt_flags & MNT_RELATIME)) return 1; /* * Is mtime younger than atime? If yes, update atime: */ if (timespec64_compare(&inode->i_mtime, &inode->i_atime) >= 0) return 1; /* * Is ctime younger than atime? If yes, update atime: */ if (timespec64_compare(&inode->i_ctime, &inode->i_atime) >= 0) return 1; /* * Is the previous atime value older than a day? If yes, * update atime: */ if ((long)(now.tv_sec - inode->i_atime.tv_sec) >= 24*60*60) return 1; /* * Good, we can skip the atime update: */ return 0; } int generic_update_time(struct inode *inode, struct timespec64 *time, int flags) { int iflags = I_DIRTY_TIME; bool dirty = false; if (flags & S_ATIME) inode->i_atime = *time; if (flags & S_VERSION) dirty = inode_maybe_inc_iversion(inode, false); if (flags & S_CTIME) inode->i_ctime = *time; if (flags & S_MTIME) inode->i_mtime = *time; if ((flags & (S_ATIME | S_CTIME | S_MTIME)) && !(inode->i_sb->s_flags & SB_LAZYTIME)) dirty = true; if (dirty) iflags |= I_DIRTY_SYNC; __mark_inode_dirty(inode, iflags); return 0; } EXPORT_SYMBOL(generic_update_time); /* * This does the actual work of updating an inodes time or version. Must have * had called mnt_want_write() before calling this. */ int inode_update_time(struct inode *inode, struct timespec64 *time, int flags) { if (inode->i_op->update_time) return inode->i_op->update_time(inode, time, flags); return generic_update_time(inode, time, flags); } EXPORT_SYMBOL(inode_update_time); /** * touch_atime - update the access time * @path: the &struct path to update * @inode: inode to update * * Update the accessed time on an inode and mark it for writeback. * This function automatically handles read only file systems and media, * as well as the "noatime" flag and inode specific "noatime" markers. */ bool atime_needs_update(const struct path *path, struct inode *inode) { struct vfsmount *mnt = path->mnt; struct timespec64 now; if (inode->i_flags & S_NOATIME) return false; /* Atime updates will likely cause i_uid and i_gid to be written * back improprely if their true value is unknown to the vfs. */ if (HAS_UNMAPPED_ID(inode)) return false; if (IS_NOATIME(inode)) return false; if ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; if (mnt->mnt_flags & MNT_NOATIME) return false; if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; now = current_time(inode); if (!relatime_need_update(mnt, inode, now)) return false; if (timespec64_equal(&inode->i_atime, &now)) return false; return true; } void touch_atime(const struct path *path) { struct vfsmount *mnt = path->mnt; struct inode *inode = d_inode(path->dentry); struct timespec64 now; if (!atime_needs_update(path, inode)) return; if (!sb_start_write_trylock(inode->i_sb)) return; if (__mnt_want_write(mnt) != 0) goto skip_update; /* * File systems can error out when updating inodes if they need to * allocate new space to modify an inode (such is the case for * Btrfs), but since we touch atime while walking down the path we * really don't care if we failed to update the atime of the file, * so just ignore the return value. * We may also fail on filesystems that have the ability to make parts * of the fs read only, e.g. subvolumes in Btrfs. */ now = current_time(inode); inode_update_time(inode, &now, S_ATIME); __mnt_drop_write(mnt); skip_update: sb_end_write(inode->i_sb); } EXPORT_SYMBOL(touch_atime); /* * Return mask of changes for notify_change() that need to be done as a * response to write or truncate. Return 0 if nothing has to be changed. * Negative value on error (change should be denied). */ int dentry_needs_remove_privs(struct dentry *dentry) { struct inode *inode = d_inode(dentry); int mask = 0; int ret; if (IS_NOSEC(inode)) return 0; mask = setattr_should_drop_suidgid(inode); ret = security_inode_need_killpriv(dentry); if (ret < 0) return ret; if (ret) mask |= ATTR_KILL_PRIV; return mask; } static int __remove_privs(struct dentry *dentry, int kill) { struct iattr newattrs; newattrs.ia_valid = ATTR_FORCE | kill; /* * Note we call this on write, so notify_change will not * encounter any conflicting delegations: */ return notify_change(dentry, &newattrs, NULL); } /* * Remove special file priviledges (suid, capabilities) when file is written * to or truncated. */ int file_remove_privs(struct file *file) { struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); int kill; int error = 0; /* * Fast path for nothing security related. * As well for non-regular files, e.g. blkdev inodes. * For example, blkdev_write_iter() might get here * trying to remove privs which it is not allowed to. */ if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(dentry); if (kill < 0) return kill; if (kill) error = __remove_privs(dentry, kill); if (!error) inode_has_no_xattr(inode); return error; } EXPORT_SYMBOL(file_remove_privs); /** * file_update_time - update mtime and ctime time * @file: file accessed * * Update the mtime and ctime members of an inode and mark the inode * for writeback. Note that this function is meant exclusively for * usage in the file write path of filesystems, and filesystems may * choose to explicitly ignore update via this function with the * S_NOCMTIME inode flag, e.g. for network filesystem where these * timestamps are handled by the server. This can return an error for * file systems who need to allocate space in order to update an inode. */ int file_update_time(struct file *file) { struct inode *inode = file_inode(file); struct timespec64 now; int sync_it = 0; int ret; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) return 0; now = current_time(inode); if (!timespec64_equal(&inode->i_mtime, &now)) sync_it = S_MTIME; if (!timespec64_equal(&inode->i_ctime, &now)) sync_it |= S_CTIME; if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode)) sync_it |= S_VERSION; if (!sync_it) return 0; /* Finally allowed to write? Takes lock. */ if (__mnt_want_write_file(file)) return 0; ret = inode_update_time(inode, &now, sync_it); __mnt_drop_write_file(file); return ret; } EXPORT_SYMBOL(file_update_time); /* Caller must hold the file's inode lock */ int file_modified(struct file *file) { int err; /* * Clear the security bits if the process is not being run by root. * This keeps people from modifying setuid and setgid binaries. */ err = file_remove_privs(file); if (err) return err; if (unlikely(file->f_mode & FMODE_NOCMTIME)) return 0; return file_update_time(file); } EXPORT_SYMBOL(file_modified); int inode_needs_sync(struct inode *inode) { if (IS_SYNC(inode)) return 1; if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode)) return 1; return 0; } EXPORT_SYMBOL(inode_needs_sync); /* * If we try to find an inode in the inode hash while it is being * deleted, we have to wait until the filesystem completes its * deletion before reporting that it isn't found. This function waits * until the deletion _might_ have completed. Callers are responsible * to recheck inode state. * * It doesn't matter if I_NEW is not set initially, a call to * wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list * will DTRT. */ static void __wait_on_freeing_inode(struct inode *inode) { wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW); wq = bit_waitqueue(&inode->i_state, __I_NEW); prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); schedule(); finish_wait(wq, &wait.wq_entry); spin_lock(&inode_hash_lock); } static __initdata unsigned long ihash_entries; static int __init set_ihash_entries(char *str) { if (!str) return 0; ihash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("ihash_entries=", set_ihash_entries); /* * Initialize the waitqueues and inode hash table. */ void __init inode_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_EARLY | HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void __init inode_init(void) { /* inode slab cache */ inode_cachep = kmem_cache_create("inode_cache", sizeof(struct inode), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); /* Hash may have been set up in inode_init_early */ if (!hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) { inode->i_mode = mode; if (S_ISCHR(mode)) { inode->i_fop = &def_chr_fops; inode->i_rdev = rdev; } else if (S_ISBLK(mode)) { inode->i_fop = &def_blk_fops; inode->i_rdev = rdev; } else if (S_ISFIFO(mode)) inode->i_fop = &pipefifo_fops; else if (S_ISSOCK(mode)) ; /* leave it no_open_fops */ else printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for" " inode %s:%lu\n", mode, inode->i_sb->s_id, inode->i_ino); } EXPORT_SYMBOL(init_special_inode); /** * inode_init_owner - Init uid,gid,mode for new inode according to posix standards * @inode: New inode * @dir: Directory inode * @mode: mode of the new inode */ void inode_init_owner(struct inode *inode, const struct inode *dir, umode_t mode) { inode->i_uid = current_fsuid(); if (dir && dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; } else inode->i_gid = current_fsgid(); inode->i_mode = mode; } EXPORT_SYMBOL(inode_init_owner); /** * inode_owner_or_capable - check current task permissions to inode * @inode: inode being checked * * Return true if current either has CAP_FOWNER in a namespace with the * inode owner uid mapped, or owns the file. */ bool inode_owner_or_capable(const struct inode *inode) { struct user_namespace *ns; if (uid_eq(current_fsuid(), inode->i_uid)) return true; ns = current_user_ns(); if (kuid_has_mapping(ns, inode->i_uid) && ns_capable(ns, CAP_FOWNER)) return true; return false; } EXPORT_SYMBOL(inode_owner_or_capable); /* * Direct i/o helper functions */ static void __inode_dio_wait(struct inode *inode) { wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); do { prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE); if (atomic_read(&inode->i_dio_count)) schedule(); } while (atomic_read(&inode->i_dio_count)); finish_wait(wq, &q.wq_entry); } /** * inode_dio_wait - wait for outstanding DIO requests to finish * @inode: inode to wait for * * Waits for all pending direct I/O requests to finish so that we can * proceed with a truncate or equivalent operation. * * Must be called under a lock that serializes taking new references * to i_dio_count, usually by inode->i_mutex. */ void inode_dio_wait(struct inode *inode) { if (atomic_read(&inode->i_dio_count)) __inode_dio_wait(inode); } EXPORT_SYMBOL(inode_dio_wait); /* * inode_set_flags - atomically set some inode flags * * Note: the caller should be holding i_mutex, or else be sure that * they have exclusive access to the inode structure (i.e., while the * inode is being instantiated). The reason for the cmpxchg() loop * --- which wouldn't be necessary if all code paths which modify * i_flags actually followed this rule, is that there is at least one * code path which doesn't today so we use cmpxchg() out of an abundance * of caution. * * In the long run, i_mutex is overkill, and we should probably look * at using the i_lock spinlock to protect i_flags, and then make sure * it is so documented in include/linux/fs.h and that all code follows * the locking convention!! */ void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask) { WARN_ON_ONCE(flags & ~mask); set_mask_bits(&inode->i_flags, mask, flags); } EXPORT_SYMBOL(inode_set_flags); void inode_nohighmem(struct inode *inode) { mapping_set_gfp_mask(inode->i_mapping, GFP_USER); } EXPORT_SYMBOL(inode_nohighmem); /** * timestamp_truncate - Truncate timespec to a granularity * @t: Timespec * @inode: inode being updated * * Truncate a timespec to the granularity supported by the fs * containing the inode. Always rounds down. gran must * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). */ struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned int gran = sb->s_time_gran; t.tv_sec = clamp(t.tv_sec, sb->s_time_min, sb->s_time_max); if (unlikely(t.tv_sec == sb->s_time_max || t.tv_sec == sb->s_time_min)) t.tv_nsec = 0; /* Avoid division in the common cases 1 ns and 1 s. */ if (gran == 1) ; /* nothing */ else if (gran == NSEC_PER_SEC) t.tv_nsec = 0; else if (gran > 1 && gran < NSEC_PER_SEC) t.tv_nsec -= t.tv_nsec % gran; else WARN(1, "invalid file time granularity: %u", gran); return t; } EXPORT_SYMBOL(timestamp_truncate); /** * current_time - Return FS time * @inode: inode. * * Return the current time truncated to the time granularity supported by * the fs. * * Note that inode and inode->sb cannot be NULL. * Otherwise, the function warns and returns time without truncation. */ struct timespec64 current_time(struct inode *inode) { struct timespec64 now; ktime_get_coarse_real_ts64(&now); if (unlikely(!inode->i_sb)) { WARN(1, "current_time() called with uninitialized super_block in the inode"); return now; } return timestamp_truncate(now, inode); } EXPORT_SYMBOL(current_time); /* * Generic function to check FS_IOC_SETFLAGS values and reject any invalid * configurations. * * Note: the caller should be holding i_mutex, or else be sure that they have * exclusive access to the inode structure. */ int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags, unsigned int flags) { /* * The IMMUTABLE and APPEND_ONLY flags can only be changed by * the relevant capability. * * This test looks nicer. Thanks to Pauline Middelink */ if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; return fscrypt_prepare_setflags(inode, oldflags, flags); } EXPORT_SYMBOL(vfs_ioc_setflags_prepare); /* * Generic function to check FS_IOC_FSSETXATTR values and reject any invalid * configurations. * * Note: the caller should be holding i_mutex, or else be sure that they have * exclusive access to the inode structure. */ int vfs_ioc_fssetxattr_check(struct inode *inode, const struct fsxattr *old_fa, struct fsxattr *fa) { /* * Can't modify an immutable/append-only file unless we have * appropriate permission. */ if ((old_fa->fsx_xflags ^ fa->fsx_xflags) & (FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; /* * Project Quota ID state is only allowed to change from within the init * namespace. Enforce that restriction only if we are trying to change * the quota ID state. Everything else is allowed in user namespaces. */ if (current_user_ns() != &init_user_ns) { if (old_fa->fsx_projid != fa->fsx_projid) return -EINVAL; if ((old_fa->fsx_xflags ^ fa->fsx_xflags) & FS_XFLAG_PROJINHERIT) return -EINVAL; } /* Check extent size hints. */ if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) && !S_ISDIR(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) && !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return -EINVAL; /* * It is only valid to set the DAX flag on regular files and * directories on filesystems. */ if ((fa->fsx_xflags & FS_XFLAG_DAX) && !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; /* Extent size hints of zero turn off the flags. */ if (fa->fsx_extsize == 0) fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT); if (fa->fsx_cowextsize == 0) fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; return 0; } EXPORT_SYMBOL(vfs_ioc_fssetxattr_check); /** * inode_set_ctime_current - set the ctime to current_time * @inode: inode * * Set the inode->i_ctime to the current value for the inode. Returns * the current value that was assigned to i_ctime. */ struct timespec64 inode_set_ctime_current(struct inode *inode) { struct timespec64 now = current_time(inode); inode_set_ctime(inode, now.tv_sec, now.tv_nsec); return now; } EXPORT_SYMBOL(inode_set_ctime_current); /** * in_group_or_capable - check whether caller is CAP_FSETID privileged * @inode: inode to check * @gid: the new/current gid of @inode * * Check wether @gid is in the caller's group list or if the caller is * privileged with CAP_FSETID over @inode. This can be used to determine * whether the setgid bit can be kept or must be dropped. * * Return: true if the caller is sufficiently privileged, false if not. */ bool in_group_or_capable(const struct inode *inode, kgid_t gid) { if (in_group_p(gid)) return true; if (capable_wrt_inode_uidgid(inode, CAP_FSETID)) return true; return false; } /** * mode_strip_sgid - handle the sgid bit for non-directories * @dir: parent directory inode * @mode: mode of the file to be created in @dir * * If the @mode of the new file has both the S_ISGID and S_IXGRP bit * raised and @dir has the S_ISGID bit raised ensure that the caller is * either in the group of the parent directory or they have CAP_FSETID * in their user namespace and are privileged over the parent directory. * In all other cases, strip the S_ISGID bit from @mode. * * Return: the new mode to use for the file */ umode_t mode_strip_sgid(const struct inode *dir, umode_t mode) { if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP)) return mode; if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID)) return mode; if (in_group_or_capable(dir, dir->i_gid)) return mode; return mode & ~S_ISGID; } EXPORT_SYMBOL(mode_strip_sgid); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the multi-level security (MLS) policy. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * * Support for enhanced MLS infrastructure. * * Copyright (C) 2004-2006 Trusted Computer Solutions, Inc. */ /* * Updated: Hewlett-Packard <paul@paul-moore.com> * * Added support to import/export the MLS label from NetLabel * * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/errno.h> #include <net/netlabel.h> #include "sidtab.h" #include "mls.h" #include "policydb.h" #include "services.h" /* * Return the length in bytes for the MLS fields of the * security context string representation of `context'. */ int mls_compute_context_len(struct policydb *p, struct context *context) { int i, l, len, head, prev; char *nm; struct ebitmap *e; struct ebitmap_node *node; if (!p->mls_enabled) return 0; len = 1; /* for the beginning ":" */ for (l = 0; l < 2; l++) { int index_sens = context->range.level[l].sens; len += strlen(sym_name(p, SYM_LEVELS, index_sens - 1)); /* categories */ head = -2; prev = -2; e = &context->range.level[l].cat; ebitmap_for_each_positive_bit(e, node, i) { if (i - prev > 1) { /* one or more negative bits are skipped */ if (head != prev) { nm = sym_name(p, SYM_CATS, prev); len += strlen(nm) + 1; } nm = sym_name(p, SYM_CATS, i); len += strlen(nm) + 1; head = i; } prev = i; } if (prev != head) { nm = sym_name(p, SYM_CATS, prev); len += strlen(nm) + 1; } if (l == 0) { if (mls_level_eq(&context->range.level[0], &context->range.level[1])) break; else len++; } } return len; } /* * Write the security context string representation of * the MLS fields of `context' into the string `*scontext'. * Update `*scontext' to point to the end of the MLS fields. */ void mls_sid_to_context(struct policydb *p, struct context *context, char **scontext) { char *scontextp, *nm; int i, l, head, prev; struct ebitmap *e; struct ebitmap_node *node; if (!p->mls_enabled) return; scontextp = *scontext; *scontextp = ':'; scontextp++; for (l = 0; l < 2; l++) { strcpy(scontextp, sym_name(p, SYM_LEVELS, context->range.level[l].sens - 1)); scontextp += strlen(scontextp); /* categories */ head = -2; prev = -2; e = &context->range.level[l].cat; ebitmap_for_each_positive_bit(e, node, i) { if (i - prev > 1) { /* one or more negative bits are skipped */ if (prev != head) { if (prev - head > 1) *scontextp++ = '.'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, prev); strcpy(scontextp, nm); scontextp += strlen(nm); } if (prev < 0) *scontextp++ = ':'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, i); strcpy(scontextp, nm); scontextp += strlen(nm); head = i; } prev = i; } if (prev != head) { if (prev - head > 1) *scontextp++ = '.'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, prev); strcpy(scontextp, nm); scontextp += strlen(nm); } if (l == 0) { if (mls_level_eq(&context->range.level[0], &context->range.level[1])) break; else *scontextp++ = '-'; } } *scontext = scontextp; return; } int mls_level_isvalid(struct policydb *p, struct mls_level *l) { struct level_datum *levdatum; if (!l->sens || l->sens > p->p_levels.nprim) return 0; levdatum = symtab_search(&p->p_levels, sym_name(p, SYM_LEVELS, l->sens - 1)); if (!levdatum) return 0; /* * Return 1 iff all the bits set in l->cat are also be set in * levdatum->level->cat and no bit in l->cat is larger than * p->p_cats.nprim. */ return ebitmap_contains(&levdatum->level->cat, &l->cat, p->p_cats.nprim); } int mls_range_isvalid(struct policydb *p, struct mls_range *r) { return (mls_level_isvalid(p, &r->level[0]) && mls_level_isvalid(p, &r->level[1]) && mls_level_dom(&r->level[1], &r->level[0])); } /* * Return 1 if the MLS fields in the security context * structure `c' are valid. Return 0 otherwise. */ int mls_context_isvalid(struct policydb *p, struct context *c) { struct user_datum *usrdatum; if (!p->mls_enabled) return 1; if (!mls_range_isvalid(p, &c->range)) return 0; if (c->role == OBJECT_R_VAL) return 1; /* * User must be authorized for the MLS range. */ if (!c->user || c->user > p->p_users.nprim) return 0; usrdatum = p->user_val_to_struct[c->user - 1]; if (!mls_range_contains(usrdatum->range, c->range)) return 0; /* user may not be associated with range */ return 1; } /* * Set the MLS fields in the security context structure * `context' based on the string representation in * the string `scontext'. * * This function modifies the string in place, inserting * NULL characters to terminate the MLS fields. * * If a def_sid is provided and no MLS field is present, * copy the MLS field of the associated default context. * Used for upgraded to MLS systems where objects may lack * MLS fields. * * Policy read-lock must be held for sidtab lookup. * */ int mls_context_to_sid(struct policydb *pol, char oldc, char *scontext, struct context *context, struct sidtab *s, u32 def_sid) { char *sensitivity, *cur_cat, *next_cat, *rngptr; struct level_datum *levdatum; struct cat_datum *catdatum, *rngdatum; int l, rc, i; char *rangep[2]; if (!pol->mls_enabled) { /* * With no MLS, only return -EINVAL if there is a MLS field * and it did not come from an xattr. */ if (oldc && def_sid == SECSID_NULL) return -EINVAL; return 0; } /* * No MLS component to the security context, try and map to * default if provided. */ if (!oldc) { struct context *defcon; if (def_sid == SECSID_NULL) return -EINVAL; defcon = sidtab_search(s, def_sid); if (!defcon) return -EINVAL; return mls_context_cpy(context, defcon); } /* * If we're dealing with a range, figure out where the two parts * of the range begin. */ rangep[0] = scontext; rangep[1] = strchr(scontext, '-'); if (rangep[1]) { rangep[1][0] = '\0'; rangep[1]++; } /* For each part of the range: */ for (l = 0; l < 2; l++) { /* Split sensitivity and category set. */ sensitivity = rangep[l]; if (sensitivity == NULL) break; next_cat = strchr(sensitivity, ':'); if (next_cat) *(next_cat++) = '\0'; /* Parse sensitivity. */ levdatum = symtab_search(&pol->p_levels, sensitivity); if (!levdatum) return -EINVAL; context->range.level[l].sens = levdatum->level->sens; /* Extract category set. */ while (next_cat != NULL) { cur_cat = next_cat; next_cat = strchr(next_cat, ','); if (next_cat != NULL) *(next_cat++) = '\0'; /* Separate into range if exists */ rngptr = strchr(cur_cat, '.'); if (rngptr != NULL) { /* Remove '.' */ *rngptr++ = '\0'; } catdatum = symtab_search(&pol->p_cats, cur_cat); if (!catdatum) return -EINVAL; rc = ebitmap_set_bit(&context->range.level[l].cat, catdatum->value - 1, 1); if (rc) return rc; /* If range, set all categories in range */ if (rngptr == NULL) continue; rngdatum = symtab_search(&pol->p_cats, rngptr); if (!rngdatum) return -EINVAL; if (catdatum->value >= rngdatum->value) return -EINVAL; for (i = catdatum->value; i < rngdatum->value; i++) { rc = ebitmap_set_bit(&context->range.level[l].cat, i, 1); if (rc) return rc; } } } /* If we didn't see a '-', the range start is also the range end. */ if (rangep[1] == NULL) { context->range.level[1].sens = context->range.level[0].sens; rc = ebitmap_cpy(&context->range.level[1].cat, &context->range.level[0].cat); if (rc) return rc; } return 0; } /* * Set the MLS fields in the security context structure * `context' based on the string representation in * the string `str'. This function will allocate temporary memory with the * given constraints of gfp_mask. */ int mls_from_string(struct policydb *p, char *str, struct context *context, gfp_t gfp_mask) { char *tmpstr; int rc; if (!p->mls_enabled) return -EINVAL; tmpstr = kstrdup(str, gfp_mask); if (!tmpstr) { rc = -ENOMEM; } else { rc = mls_context_to_sid(p, ':', tmpstr, context, NULL, SECSID_NULL); kfree(tmpstr); } return rc; } /* * Copies the MLS range `range' into `context'. */ int mls_range_set(struct context *context, struct mls_range *range) { int l, rc = 0; /* Copy the MLS range into the context */ for (l = 0; l < 2; l++) { context->range.level[l].sens = range->level[l].sens; rc = ebitmap_cpy(&context->range.level[l].cat, &range->level[l].cat); if (rc) break; } return rc; } int mls_setup_user_range(struct policydb *p, struct context *fromcon, struct user_datum *user, struct context *usercon) { if (p->mls_enabled) { struct mls_level *fromcon_sen = &(fromcon->range.level[0]); struct mls_level *fromcon_clr = &(fromcon->range.level[1]); struct mls_level *user_low = &(user->range.level[0]); struct mls_level *user_clr = &(user->range.level[1]); struct mls_level *user_def = &(user->dfltlevel); struct mls_level *usercon_sen = &(usercon->range.level[0]); struct mls_level *usercon_clr = &(usercon->range.level[1]); /* Honor the user's default level if we can */ if (mls_level_between(user_def, fromcon_sen, fromcon_clr)) *usercon_sen = *user_def; else if (mls_level_between(fromcon_sen, user_def, user_clr)) *usercon_sen = *fromcon_sen; else if (mls_level_between(fromcon_clr, user_low, user_def)) *usercon_sen = *user_low; else return -EINVAL; /* Lower the clearance of available contexts if the clearance of "fromcon" is lower than that of the user's default clearance (but only if the "fromcon" clearance dominates the user's computed sensitivity level) */ if (mls_level_dom(user_clr, fromcon_clr)) *usercon_clr = *fromcon_clr; else if (mls_level_dom(fromcon_clr, user_clr)) *usercon_clr = *user_clr; else return -EINVAL; } return 0; } /* * Convert the MLS fields in the security context * structure `oldc' from the values specified in the * policy `oldp' to the values specified in the policy `newp', * storing the resulting context in `newc'. */ int mls_convert_context(struct policydb *oldp, struct policydb *newp, struct context *oldc, struct context *newc) { struct level_datum *levdatum; struct cat_datum *catdatum; struct ebitmap_node *node; int l, i; if (!oldp->mls_enabled || !newp->mls_enabled) return 0; for (l = 0; l < 2; l++) { char *name = sym_name(oldp, SYM_LEVELS, oldc->range.level[l].sens - 1); levdatum = symtab_search(&newp->p_levels, name); if (!levdatum) return -EINVAL; newc->range.level[l].sens = levdatum->level->sens; ebitmap_for_each_positive_bit(&oldc->range.level[l].cat, node, i) { int rc; catdatum = symtab_search(&newp->p_cats, sym_name(oldp, SYM_CATS, i)); if (!catdatum) return -EINVAL; rc = ebitmap_set_bit(&newc->range.level[l].cat, catdatum->value - 1, 1); if (rc) return rc; } } return 0; } int mls_compute_sid(struct policydb *p, struct context *scontext, struct context *tcontext, u16 tclass, u32 specified, struct context *newcontext, bool sock) { struct range_trans rtr; struct mls_range *r; struct class_datum *cladatum; int default_range = 0; if (!p->mls_enabled) return 0; switch (specified) { case AVTAB_TRANSITION: /* Look for a range transition rule. */ rtr.source_type = scontext->type; rtr.target_type = tcontext->type; rtr.target_class = tclass; r = policydb_rangetr_search(p, &rtr); if (r) return mls_range_set(newcontext, r); if (tclass && tclass <= p->p_classes.nprim) { cladatum = p->class_val_to_struct[tclass - 1]; if (cladatum) default_range = cladatum->default_range; } switch (default_range) { case DEFAULT_SOURCE_LOW: return mls_context_cpy_low(newcontext, scontext); case DEFAULT_SOURCE_HIGH: return mls_context_cpy_high(newcontext, scontext); case DEFAULT_SOURCE_LOW_HIGH: return mls_context_cpy(newcontext, scontext); case DEFAULT_TARGET_LOW: return mls_context_cpy_low(newcontext, tcontext); case DEFAULT_TARGET_HIGH: return mls_context_cpy_high(newcontext, tcontext); case DEFAULT_TARGET_LOW_HIGH: return mls_context_cpy(newcontext, tcontext); case DEFAULT_GLBLUB: return mls_context_glblub(newcontext, scontext, tcontext); } fallthrough; case AVTAB_CHANGE: if ((tclass == p->process_class) || sock) /* Use the process MLS attributes. */ return mls_context_cpy(newcontext, scontext); else /* Use the process effective MLS attributes. */ return mls_context_cpy_low(newcontext, scontext); case AVTAB_MEMBER: /* Use the process effective MLS attributes. */ return mls_context_cpy_low(newcontext, scontext); } return -EINVAL; } #ifdef CONFIG_NETLABEL /** * mls_export_netlbl_lvl - Export the MLS sensitivity levels to NetLabel * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context copy the low MLS sensitivity level into the * NetLabel MLS sensitivity level field. * */ void mls_export_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { if (!p->mls_enabled) return; secattr->attr.mls.lvl = context->range.level[0].sens - 1; secattr->flags |= NETLBL_SECATTR_MLS_LVL; } /** * mls_import_netlbl_lvl - Import the NetLabel MLS sensitivity levels * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context and the NetLabel security attributes, copy the * NetLabel MLS sensitivity level into the context. * */ void mls_import_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { if (!p->mls_enabled) return; context->range.level[0].sens = secattr->attr.mls.lvl + 1; context->range.level[1].sens = context->range.level[0].sens; } /** * mls_export_netlbl_cat - Export the MLS categories to NetLabel * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context copy the low MLS categories into the NetLabel * MLS category field. Returns zero on success, negative values on failure. * */ int mls_export_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { int rc; if (!p->mls_enabled) return 0; rc = ebitmap_netlbl_export(&context->range.level[0].cat, &secattr->attr.mls.cat); if (rc == 0 && secattr->attr.mls.cat != NULL) secattr->flags |= NETLBL_SECATTR_MLS_CAT; return rc; } /** * mls_import_netlbl_cat - Import the MLS categories from NetLabel * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Copy the NetLabel security attributes into the SELinux context; since the * NetLabel security attribute only contains a single MLS category use it for * both the low and high categories of the context. Returns zero on success, * negative values on failure. * */ int mls_import_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { int rc; if (!p->mls_enabled) return 0; rc = ebitmap_netlbl_import(&context->range.level[0].cat, secattr->attr.mls.cat); if (rc) goto import_netlbl_cat_failure; memcpy(&context->range.level[1].cat, &context->range.level[0].cat, sizeof(context->range.level[0].cat)); return 0; import_netlbl_cat_failure: ebitmap_destroy(&context->range.level[0].cat); return rc; } #endif /* CONFIG_NETLABEL */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Tracing hooks * * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. * * This file defines hook entry points called by core code where * user tracing/debugging support might need to do something. These * entry points are called tracehook_*(). Each hook declared below * has a detailed kerneldoc comment giving the context (locking et * al) from which it is called, and the meaning of its return value. * * Each function here typically has only one call site, so it is ok * to have some nontrivial tracehook_*() inlines. In all cases, the * fast path when no tracing is enabled should be very short. * * The purpose of this file and the tracehook_* layer is to consolidate * the interface that the kernel core and arch code uses to enable any * user debugging or tracing facility (such as ptrace). The interfaces * here are carefully documented so that maintainers of core and arch * code do not need to think about the implementation details of the * tracing facilities. Likewise, maintainers of the tracing code do not * need to understand all the calling core or arch code in detail, just * documented circumstances of each call, such as locking conditions. * * If the calling core code changes so that locking is different, then * it is ok to change the interface documented here. The maintainer of * core code changing should notify the maintainers of the tracing code * that they need to work out the change. * * Some tracehook_*() inlines take arguments that the current tracing * implementations might not necessarily use. These function signatures * are chosen to pass in all the information that is on hand in the * caller and might conceivably be relevant to a tracer, so that the * core code won't have to be updated when tracing adds more features. * If a call site changes so that some of those parameters are no longer * already on hand without extra work, then the tracehook_* interface * can change so there is no make-work burden on the core code. The * maintainer of core code changing should notify the maintainers of the * tracing code that they need to work out the change. */ #ifndef _LINUX_TRACEHOOK_H #define _LINUX_TRACEHOOK_H 1 #include <linux/sched.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/task_work.h> #include <linux/memcontrol.h> #include <linux/blk-cgroup.h> struct linux_binprm; /* * ptrace report for syscall entry and exit looks identical. */ static inline int ptrace_report_syscall(struct pt_regs *regs, unsigned long message) { int ptrace = current->ptrace; if (!(ptrace & PT_PTRACED)) return 0; current->ptrace_message = message; ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); /* * this isn't the same as continuing with a signal, but it will do * for normal use. strace only continues with a signal if the * stopping signal is not SIGTRAP. -brl */ if (current->exit_code) { send_sig(current->exit_code, current, 1); current->exit_code = 0; } current->ptrace_message = 0; return fatal_signal_pending(current); } /** * tracehook_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set, * when the current task has just entered the kernel for a system call. * Full user register state is available here. Changing the values * in @regs can affect the system call number and arguments to be tried. * It is safe to block here, preventing the system call from beginning. * * Returns zero normally, or nonzero if the calling arch code should abort * the system call. That must prevent normal entry so no system call is * made. If @task ever returns to user mode after this, its register state * is unspecified, but should be something harmless like an %ENOSYS error * return. It should preserve enough information so that syscall_rollback() * can work (see asm-generic/syscall.h). * * Called without locks, just after entering kernel mode. */ static inline __must_check int tracehook_report_syscall_entry( struct pt_regs *regs) { return ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_ENTRY); } /** * tracehook_report_syscall_exit - task has just finished a system call * @regs: user register state of current task * @step: nonzero if simulating single-step or block-step * * This will be called if %TIF_SYSCALL_TRACE has been set, when the * current task has just finished an attempted system call. Full * user register state is available here. It is safe to block here, * preventing signals from being processed. * * If @step is nonzero, this report is also in lieu of the normal * trap that would follow the system call instruction because * user_enable_block_step() or user_enable_single_step() was used. * In this case, %TIF_SYSCALL_TRACE might not be set. * * Called without locks, just before checking for pending signals. */ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) { if (step) user_single_step_report(regs); else ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_EXIT); } /** * tracehook_signal_handler - signal handler setup is complete * @stepping: nonzero if debugger single-step or block-step in use * * Called by the arch code after a signal handler has been set up. * Register and stack state reflects the user handler about to run. * Signal mask changes have already been made. * * Called without locks, shortly before returning to user mode * (or handling more signals). */ static inline void tracehook_signal_handler(int stepping) { if (stepping) ptrace_notify(SIGTRAP); } /** * set_notify_resume - cause tracehook_notify_resume() to be called * @task: task that will call tracehook_notify_resume() * * Calling this arranges that @task will call tracehook_notify_resume() * before returning to user mode. If it's already running in user mode, * it will enter the kernel and call tracehook_notify_resume() soon. * If it's blocked, it will not be woken. */ static inline void set_notify_resume(struct task_struct *task) { #ifdef TIF_NOTIFY_RESUME if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); #endif } /** * tracehook_notify_resume - report when about to return to user mode * @regs: user-mode registers of @current task * * This is called when %TIF_NOTIFY_RESUME has been set. Now we are * about to return to user mode, and the user state in @regs can be * inspected or adjusted. The caller in arch code has cleared * %TIF_NOTIFY_RESUME before the call. If the flag gets set again * asynchronously, this will be called again before we return to * user mode. * * Called without locks. */ static inline void tracehook_notify_resume(struct pt_regs *regs) { clear_thread_flag(TIF_NOTIFY_RESUME); /* * This barrier pairs with task_work_add()->set_notify_resume() after * hlist_add_head(task->task_works); */ smp_mb__after_atomic(); if (unlikely(current->task_works)) task_work_run(); #ifdef CONFIG_KEYS_REQUEST_CACHE if (unlikely(current->cached_requested_key)) { key_put(current->cached_requested_key); current->cached_requested_key = NULL; } #endif mem_cgroup_handle_over_high(); blkcg_maybe_throttle_current(); } /* * called by exit_to_user_mode_loop() if ti_work & _TIF_NOTIFY_SIGNAL. This * is currently used by TWA_SIGNAL based task_work, which requires breaking * wait loops to ensure that task_work is noticed and run. */ static inline void tracehook_notify_signal(void) { clear_thread_flag(TIF_NOTIFY_SIGNAL); smp_mb__after_atomic(); if (current->task_works) task_work_run(); } /* * Called when we have work to process from exit_to_user_mode_loop() */ static inline void set_notify_signal(struct task_struct *task) { if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && !wake_up_state(task, TASK_INTERRUPTIBLE)) kick_process(task); } #endif /* <linux/tracehook.h> */ |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_H #define _LINUX_LIST_H #include <linux/types.h> #include <linux/stddef.h> #include <linux/poison.h> #include <linux/const.h> #include <linux/kernel.h> /* * Simple doubly linked list implementation. * * Some of the internal functions ("__xxx") are useful when * manipulating whole lists rather than single entries, as * sometimes we already know the next/prev entries and we can * generate better code by using them directly rather than * using the generic single-entry routines. */ #define LIST_HEAD_INIT(name) { &(name), &(name) } #define LIST_HEAD(name) \ struct list_head name = LIST_HEAD_INIT(name) /** * INIT_LIST_HEAD - Initialize a list_head structure * @list: list_head structure to be initialized. * * Initializes the list_head to point to itself. If it is a list header, * the result is an empty list. */ static inline void INIT_LIST_HEAD(struct list_head *list) { WRITE_ONCE(list->next, list); list->prev = list; } #ifdef CONFIG_DEBUG_LIST extern bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next); extern bool __list_del_entry_valid(struct list_head *entry); #else static inline bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { return true; } static inline bool __list_del_entry_valid(struct list_head *entry) { return true; } #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; next->prev = new; new->next = next; new->prev = prev; WRITE_ONCE(prev->next, new); } /** * list_add - add a new entry * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void list_add(struct list_head *new, struct list_head *head) { __list_add(new, head, head->next); } /** * list_add_tail - add a new entry * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. */ static inline void list_add_tail(struct list_head *new, struct list_head *head) { __list_add(new, head->prev, head); } /* * Delete a list entry by making the prev/next entries * point to each other. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_del(struct list_head * prev, struct list_head * next) { next->prev = prev; WRITE_ONCE(prev->next, next); } /* * Delete a list entry and clear the 'prev' pointer. * * This is a special-purpose list clearing method used in the networking code * for lists allocated as per-cpu, where we don't want to incur the extra * WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this * needs to check the node 'prev' pointer instead of calling list_empty(). */ static inline void __list_del_clearprev(struct list_head *entry) { __list_del(entry->prev, entry->next); entry->prev = NULL; } static inline void __list_del_entry(struct list_head *entry) { if (!__list_del_entry_valid(entry)) return; __list_del(entry->prev, entry->next); } /** * list_del - deletes entry from list. * @entry: the element to delete from the list. * Note: list_empty() on entry does not return true after this, the entry is * in an undefined state. */ static inline void list_del(struct list_head *entry) { __list_del_entry(entry); entry->next = LIST_POISON1; entry->prev = LIST_POISON2; } /** * list_replace - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace(struct list_head *old, struct list_head *new) { new->next = old->next; new->next->prev = new; new->prev = old->prev; new->prev->next = new; } /** * list_replace_init - replace old entry by new one and initialize the old one * @old : the element to be replaced * @new : the new element to insert * * If @old was empty, it will be overwritten. */ static inline void list_replace_init(struct list_head *old, struct list_head *new) { list_replace(old, new); INIT_LIST_HEAD(old); } /** * list_swap - replace entry1 with entry2 and re-add entry1 at entry2's position * @entry1: the location to place entry2 * @entry2: the location to place entry1 */ static inline void list_swap(struct list_head *entry1, struct list_head *entry2) { struct list_head *pos = entry2->prev; list_del(entry2); list_replace(entry1, entry2); if (pos == entry1) pos = entry2; list_add(entry1, pos); } /** * list_del_init - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. */ static inline void list_del_init(struct list_head *entry) { __list_del_entry(entry); INIT_LIST_HEAD(entry); } /** * list_move - delete from one list and add as another's head * @list: the entry to move * @head: the head that will precede our entry */ static inline void list_move(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add(list, head); } /** * list_move_tail - delete from one list and add as another's tail * @list: the entry to move * @head: the head that will follow our entry */ static inline void list_move_tail(struct list_head *list, struct list_head *head) { __list_del_entry(list); list_add_tail(list, head); } /** * list_bulk_move_tail - move a subsection of a list to its tail * @head: the head that will follow our entry * @first: first entry to move * @last: last entry to move, can be the same as first * * Move all entries between @first and including @last before @head. * All three entries must belong to the same linked list. */ static inline void list_bulk_move_tail(struct list_head *head, struct list_head *first, struct list_head *last) { first->prev->next = last->next; last->next->prev = first->prev; head->prev->next = first; first->prev = head->prev; last->next = head; head->prev = last; } /** * list_is_first -- tests whether @list is the first entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test * @head: the head of the list */ static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } /** * list_empty - tests whether a list is empty * @head: the list to test. */ static inline int list_empty(const struct list_head *head) { return READ_ONCE(head->next) == head; } /** * list_del_init_careful - deletes entry from list and reinitialize it. * @entry: the element to delete from the list. * * This is the same as list_del_init(), except designed to be used * together with list_empty_careful() in a way to guarantee ordering * of other memory operations. * * Any memory operations done before a list_del_init_careful() are * guaranteed to be visible after a list_empty_careful() test. */ static inline void list_del_init_careful(struct list_head *entry) { __list_del_entry(entry); entry->prev = entry; smp_store_release(&entry->next, entry); } /** * list_empty_careful - tests whether a list is empty and not being modified * @head: the list to test * * Description: * tests whether a list is empty _and_ checks that no other CPU might be * in the process of modifying either member (next or prev) * * NOTE: using list_empty_careful() without synchronization * can only be safe if the only activity that can happen * to the list entry is list_del_init(). Eg. it cannot be used * if another CPU could re-list_add() it. */ static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); return (next == head) && (next == head->prev); } /** * list_rotate_left - rotate the list to the left * @head: the head of the list */ static inline void list_rotate_left(struct list_head *head) { struct list_head *first; if (!list_empty(head)) { first = head->next; list_move_tail(first, head); } } /** * list_rotate_to_front() - Rotate list to specific item. * @list: The desired new front of the list. * @head: The head of the list. * * Rotates list so that @list becomes the new front of the list. */ static inline void list_rotate_to_front(struct list_head *list, struct list_head *head) { /* * Deletes the list head from the list denoted by @head and * places it as the tail of @list, this effectively rotates the * list so that @list is at the front. */ list_move_tail(head, list); } /** * list_is_singular - tests whether a list has just one entry. * @head: the list to test. */ static inline int list_is_singular(const struct list_head *head) { return !list_empty(head) && (head->next == head->prev); } static inline void __list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { struct list_head *new_first = entry->next; list->next = head->next; list->next->prev = list; list->prev = entry; entry->next = list; head->next = new_first; new_first->prev = head; } /** * list_cut_position - cut a list into two * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * and if so we won't cut the list * * This helper moves the initial part of @head, up to and * including @entry, from @head to @list. You should * pass on @entry an element you know is on @head. @list * should be an empty list or a list you do not care about * losing its data. * */ static inline void list_cut_position(struct list_head *list, struct list_head *head, struct list_head *entry) { if (list_empty(head)) return; if (list_is_singular(head) && (head->next != entry && head != entry)) return; if (entry == head) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); } /** * list_cut_before - cut a list into two, before given entry * @list: a new list to add all removed entries * @head: a list with entries * @entry: an entry within head, could be the head itself * * This helper moves the initial part of @head, up to but * excluding @entry, from @head to @list. You should pass * in @entry an element you know is on @head. @list should * be an empty list or a list you do not care about losing * its data. * If @entry == @head, all entries on @head are moved to * @list. */ static inline void list_cut_before(struct list_head *list, struct list_head *head, struct list_head *entry) { if (head->next == entry) { INIT_LIST_HEAD(list); return; } list->next = head->next; list->next->prev = list; list->prev = entry->prev; list->prev->next = list; head->next = entry; entry->prev = head; } static inline void __list_splice(const struct list_head *list, struct list_head *prev, struct list_head *next) { struct list_head *first = list->next; struct list_head *last = list->prev; first->prev = prev; prev->next = first; last->next = next; next->prev = last; } /** * list_splice - join two lists, this is designed for stacks * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice(const struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head, head->next); } /** * list_splice_tail - join two lists, each list being a queue * @list: the new list to add. * @head: the place to add it in the first list. */ static inline void list_splice_tail(struct list_head *list, struct list_head *head) { if (!list_empty(list)) __list_splice(list, head->prev, head); } /** * list_splice_init - join two lists and reinitialise the emptied list. * @list: the new list to add. * @head: the place to add it in the first list. * * The list at @list is reinitialised */ static inline void list_splice_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head, head->next); INIT_LIST_HEAD(list); } } /** * list_splice_tail_init - join two lists and reinitialise the emptied list * @list: the new list to add. * @head: the place to add it in the first list. * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void list_splice_tail_init(struct list_head *list, struct list_head *head) { if (!list_empty(list)) { __list_splice(list, head->prev, head); INIT_LIST_HEAD(list); } } /** * list_entry - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. */ #define list_entry(ptr, type, member) \ container_of(ptr, type, member) /** * list_first_entry - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_first_entry(ptr, type, member) \ list_entry((ptr)->next, type, member) /** * list_last_entry - get the last element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note, that list is expected to be not empty. */ #define list_last_entry(ptr, type, member) \ list_entry((ptr)->prev, type, member) /** * list_first_entry_or_null - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. */ #define list_first_entry_or_null(ptr, type, member) ({ \ struct list_head *head__ = (ptr); \ struct list_head *pos__ = READ_ONCE(head__->next); \ pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) /** * list_next_entry - get the next element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_next_entry(pos, member) \ list_entry((pos)->member.next, typeof(*(pos)), member) /** * list_prev_entry - get the prev element in list * @pos: the type * to cursor * @member: the name of the list_head within the struct. */ #define list_prev_entry(pos, member) \ list_entry((pos)->member.prev, typeof(*(pos)), member) /** * list_for_each - iterate over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each(pos, head) \ for (pos = (head)->next; pos != (head); pos = pos->next) /** * list_for_each_continue - continue iteration over a list * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. * * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ for (pos = pos->next; pos != (head); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards * @pos: the &struct list_head to use as a loop cursor. * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ for (pos = (head)->prev; pos != (head); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ for (pos = (head)->next, n = pos->next; pos != (head); \ pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry * @pos: the &struct list_head to use as a loop cursor. * @n: another &struct list_head to use as temporary storage * @head: the head for your list. */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ pos != (head); \ pos = n, n = pos->prev) /** * list_entry_is_head - test if the entry points to the head of the list * @pos: the type * to cursor * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_entry_is_head(pos, head, member) \ (&pos->member == (head)) /** * list_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry(pos, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_reverse - iterate backwards over list of given type. * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_reverse(pos, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_prepare_entry - prepare a pos entry for use in list_for_each_entry_continue() * @pos: the type * to use as a start point * @head: the head of the list * @member: the name of the list_head within the struct. * * Prepares a pos entry for use as a start point in list_for_each_entry_continue(). */ #define list_prepare_entry(pos, head, member) \ ((pos) ? : list_entry(head, typeof(*pos), member)) /** * list_for_each_entry_continue - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position. */ #define list_for_each_entry_continue(pos, head, member) \ for (pos = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_continue_reverse - iterate backwards from the given point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Start to iterate over list of given type backwards, continuing after * the current position. */ #define list_for_each_entry_continue_reverse(pos, head, member) \ for (pos = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_from - iterate over list of given type from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing from current position. */ #define list_for_each_entry_from(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_next_entry(pos, member)) /** * list_for_each_entry_from_reverse - iterate backwards over list of given type * from the current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, continuing from current position. */ #define list_for_each_entry_from_reverse(pos, head, member) \ for (; !list_entry_is_head(pos, head, member); \ pos = list_prev_entry(pos, member)) /** * list_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. */ #define list_for_each_entry_safe(pos, n, head, member) \ for (pos = list_first_entry(head, typeof(*pos), member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_continue - continue list iteration safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type, continuing after current point, * safe against removal of list entry. */ #define list_for_each_entry_safe_continue(pos, n, head, member) \ for (pos = list_next_entry(pos, member), \ n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_from - iterate over list from current point safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate over list of given type from current point, safe against * removal of list entry. */ #define list_for_each_entry_safe_from(pos, n, head, member) \ for (n = list_next_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_next_entry(n, member)) /** * list_for_each_entry_safe_reverse - iterate backwards over list safe against removal * @pos: the type * to use as a loop cursor. * @n: another type * to use as temporary storage * @head: the head for your list. * @member: the name of the list_head within the struct. * * Iterate backwards over list of given type, safe against removal * of list entry. */ #define list_for_each_entry_safe_reverse(pos, n, head, member) \ for (pos = list_last_entry(head, typeof(*pos), member), \ n = list_prev_entry(pos, member); \ !list_entry_is_head(pos, head, member); \ pos = n, n = list_prev_entry(n, member)) /** * list_safe_reset_next - reset a stale list_for_each_entry_safe loop * @pos: the loop cursor used in the list_for_each_entry_safe loop * @n: temporary storage used in list_for_each_entry_safe * @member: the name of the list_head within the struct. * * list_safe_reset_next is not safe to use in general if the list may be * modified concurrently (eg. the lock is dropped in the loop body). An * exception to this is if the cursor element (pos) is pinned in the list, * and list_safe_reset_next is called after re-taking the lock and before * completing the current iteration of the loop body. */ #define list_safe_reset_next(pos, n, member) \ n = list_next_entry(pos, member) /* * Double linked lists with a single pointer list head. * Mostly useful for hash tables where the two pointer list head is * too wasteful. * You lose the ability to access the tail in O(1). */ #define HLIST_HEAD_INIT { .first = NULL } #define HLIST_HEAD(name) struct hlist_head name = { .first = NULL } #define INIT_HLIST_HEAD(ptr) ((ptr)->first = NULL) static inline void INIT_HLIST_NODE(struct hlist_node *h) { h->next = NULL; h->pprev = NULL; } /** * hlist_unhashed - Has node been removed from list and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed * state. For example, hlist_nulls_del_init_rcu() does leave the * node in unhashed state, but hlist_nulls_del() does not. */ static inline int hlist_unhashed(const struct hlist_node *h) { return !h->pprev; } /** * hlist_unhashed_lockless - Version of hlist_unhashed for lockless use * @h: Node to be checked * * This variant of hlist_unhashed() must be used in lockless contexts * to avoid potential load-tearing. The READ_ONCE() is paired with the * various WRITE_ONCE() in hlist helpers that are defined below. */ static inline int hlist_unhashed_lockless(const struct hlist_node *h) { return !READ_ONCE(h->pprev); } /** * hlist_empty - Is the specified hlist_head structure an empty hlist? * @h: Structure to check. */ static inline int hlist_empty(const struct hlist_head *h) { return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) { struct hlist_node *next = n->next; struct hlist_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (next) WRITE_ONCE(next->pprev, pprev); } /** * hlist_del - Delete the specified hlist_node from its list * @n: Node to delete. * * Note that this function leaves the node in hashed state. Use * hlist_del_init() or similar instead to unhash @n. */ static inline void hlist_del(struct hlist_node *n) { __hlist_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } /** * hlist_del_init - Delete the specified hlist_node from its list and initialize * @n: Node to delete. * * Note that this function leaves the node in unhashed state. */ static inline void hlist_del_init(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); INIT_HLIST_NODE(n); } } /** * hlist_add_head - add a new entry at the beginning of the hlist * @n: new entry to be added * @h: hlist head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. */ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; WRITE_ONCE(n->next, first); if (first) WRITE_ONCE(first->pprev, &n->next); WRITE_ONCE(h->first, n); WRITE_ONCE(n->pprev, &h->first); } /** * hlist_add_before - add a new entry before the one specified * @n: new entry to be added * @next: hlist node to add it before, which must be non-NULL */ static inline void hlist_add_before(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); WRITE_ONCE(n->next, next); WRITE_ONCE(next->pprev, &n->next); WRITE_ONCE(*(n->pprev), n); } /** * hlist_add_behing - add a new entry after the one specified * @n: new entry to be added * @prev: hlist node to add it after, which must be non-NULL */ static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { WRITE_ONCE(n->next, prev->next); WRITE_ONCE(prev->next, n); WRITE_ONCE(n->pprev, &prev->next); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } /** * hlist_add_fake - create a fake hlist consisting of a single headless node * @n: Node to make a fake list out of * * This makes @n appear to be its own predecessor on a headless hlist. * The point of this is to allow things like hlist_del() to work correctly * in cases where there is no list. */ static inline void hlist_add_fake(struct hlist_node *n) { n->pprev = &n->next; } /** * hlist_fake: Is this node a fake hlist? * @h: Node to check for being a self-referential fake hlist. */ static inline bool hlist_fake(struct hlist_node *h) { return h->pprev == &h->next; } /** * hlist_is_singular_node - is node the only element of the specified hlist? * @n: Node to check for singularity. * @h: Header for potentially singular list. * * Check whether the node is the only node of the head without * accessing head, thus avoiding unnecessary cache misses. */ static inline bool hlist_is_singular_node(struct hlist_node *n, struct hlist_head *h) { return !n->next && n->pprev == &h->first; } /** * hlist_move_list - Move an hlist * @old: hlist_head for old list. * @new: hlist_head for new list. * * Move a list from one list head to another. Fixup the pprev * reference of the first entry if it exists. */ static inline void hlist_move_list(struct hlist_head *old, struct hlist_head *new) { new->first = old->first; if (new->first) new->first->pprev = &new->first; old->first = NULL; } #define hlist_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_for_each(pos, head) \ for (pos = (head)->first; pos ; pos = pos->next) #define hlist_for_each_safe(pos, n, head) \ for (pos = (head)->first; pos && ({ n = pos->next; 1; }); \ pos = n) #define hlist_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? hlist_entry(____ptr, type, member) : NULL; \ }) /** * hlist_for_each_entry - iterate over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry(pos, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_continue - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue(pos, member) \ for (pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member);\ pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_from - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from(pos, member) \ for (; pos; \ pos = hlist_entry_safe((pos)->member.next, typeof(*(pos)), member)) /** * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @pos: the type * to use as a loop cursor. * @n: a &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_safe(pos, n, head, member) \ for (pos = hlist_entry_safe((head)->first, typeof(*pos), member);\ pos && ({ n = pos->member.next; 1; }); \ pos = hlist_entry_safe(n, typeof(*pos), member)) #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Supervisor Mode Access Prevention support * * Copyright (C) 2012 Intel Corporation * Author: H. Peter Anvin <hpa@linux.intel.com> */ #ifndef _ASM_X86_SMAP_H #define _ASM_X86_SMAP_H #include <asm/nops.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> /* "Raw" instruction opcodes */ #define __ASM_CLAC ".byte 0x0f,0x01,0xca" #define __ASM_STAC ".byte 0x0f,0x01,0xcb" #ifdef __ASSEMBLY__ #ifdef CONFIG_X86_SMAP #define ASM_CLAC \ ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP #define ASM_STAC \ ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP #else /* CONFIG_X86_SMAP */ #define ASM_CLAC #define ASM_STAC #endif /* CONFIG_X86_SMAP */ #else /* __ASSEMBLY__ */ #ifdef CONFIG_X86_SMAP static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ alternative("", __ASM_CLAC, X86_FEATURE_SMAP); } static __always_inline void stac(void) { /* Note: a barrier is implicit in alternative() */ alternative("", __ASM_STAC, X86_FEATURE_SMAP); } static __always_inline unsigned long smap_save(void) { unsigned long flags; asm volatile ("# smap_save\n\t" ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) "pushf; pop %0; " __ASM_CLAC "\n\t" "1:" : "=rm" (flags) : : "memory", "cc"); return flags; } static __always_inline void smap_restore(unsigned long flags) { asm volatile ("# smap_restore\n\t" ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP) "push %0; popf\n\t" "1:" : : "g" (flags) : "memory", "cc"); } /* These macros can be used in asm() statements */ #define ASM_CLAC \ ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP) #define ASM_STAC \ ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP) #else /* CONFIG_X86_SMAP */ static inline void clac(void) { } static inline void stac(void) { } static inline unsigned long smap_save(void) { return 0; } static inline void smap_restore(unsigned long flags) { } #define ASM_CLAC #define ASM_STAC #endif /* CONFIG_X86_SMAP */ #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_SMAP_H */ |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_H #define _ASM_X86_PGTABLE_H #include <linux/mem_encrypt.h> #include <asm/page.h> #include <asm/pgtable_types.h> /* * Macro to mark a page protection value as UC- */ #define pgprot_noncached(prot) \ ((boot_cpu_data.x86 > 3) \ ? (__pgprot(pgprot_val(prot) | \ cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))) \ : (prot)) /* * Macros to add or remove encryption attribute */ #define pgprot_encrypted(prot) __pgprot(__sme_set(pgprot_val(prot))) #define pgprot_decrypted(prot) __pgprot(__sme_clr(pgprot_val(prot))) #ifndef __ASSEMBLY__ #include <asm/x86_init.h> #include <asm/fpu/xstate.h> #include <asm/fpu/api.h> #include <asm-generic/pgtable_uffd.h> extern pgd_t early_top_pgt[PTRS_PER_PGD]; bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd); void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, bool user); void ptdump_walk_pgd_level_checkwx(void); void ptdump_walk_user_pgd_level_checkwx(void); #ifdef CONFIG_DEBUG_WX #define debug_checkwx() ptdump_walk_pgd_level_checkwx() #define debug_checkwx_user() ptdump_walk_user_pgd_level_checkwx() #else #define debug_checkwx() do { } while (0) #define debug_checkwx_user() do { } while (0) #endif /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __visible; #define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page)) extern spinlock_t pgd_lock; extern struct list_head pgd_list; extern struct mm_struct *pgd_page_get_mm(struct page *page); extern pmdval_t early_pmd_flags; #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else /* !CONFIG_PARAVIRT_XXL */ #define set_pte(ptep, pte) native_set_pte(ptep, pte) #define set_pte_atomic(ptep, pte) \ native_set_pte_atomic(ptep, pte) #define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd) #ifndef __PAGETABLE_P4D_FOLDED #define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd) #define pgd_clear(pgd) (pgtable_l5_enabled() ? native_pgd_clear(pgd) : 0) #endif #ifndef set_p4d # define set_p4d(p4dp, p4d) native_set_p4d(p4dp, p4d) #endif #ifndef __PAGETABLE_PUD_FOLDED #define p4d_clear(p4d) native_p4d_clear(p4d) #endif #ifndef set_pud # define set_pud(pudp, pud) native_set_pud(pudp, pud) #endif #ifndef __PAGETABLE_PUD_FOLDED #define pud_clear(pud) native_pud_clear(pud) #endif #define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep) #define pmd_clear(pmd) native_pmd_clear(pmd) #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) #ifndef __PAGETABLE_P4D_FOLDED #define p4d_val(x) native_p4d_val(x) #define __p4d(x) native_make_p4d(x) #endif #ifndef __PAGETABLE_PUD_FOLDED #define pud_val(x) native_pud_val(x) #define __pud(x) native_make_pud(x) #endif #ifndef __PAGETABLE_PMD_FOLDED #define pmd_val(x) native_pmd_val(x) #define __pmd(x) native_make_pmd(x) #endif #define pte_val(x) native_pte_val(x) #define __pte(x) native_make_pte(x) #define arch_end_context_switch(prev) do {} while(0) #endif /* CONFIG_PARAVIRT_XXL */ /* * The following only work if pte_present() is true. * Undefined behaviour if not.. */ static inline int pte_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_DIRTY; } static inline u32 read_pkru(void) { if (boot_cpu_has(X86_FEATURE_OSPKE)) return rdpkru(); return 0; } static inline void write_pkru(u32 pkru) { struct pkru_state *pk; if (!boot_cpu_has(X86_FEATURE_OSPKE)) return; pk = get_xsave_addr(¤t->thread.fpu.state.xsave, XFEATURE_PKRU); /* * The PKRU value in xstate needs to be in sync with the value that is * written to the CPU. The FPU restore on return to userland would * otherwise load the previous value again. */ fpregs_lock(); if (pk) pk->pkru = pkru; __write_pkru(pkru); fpregs_unlock(); } static inline int pte_young(pte_t pte) { return pte_flags(pte) & _PAGE_ACCESSED; } static inline int pmd_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_DIRTY; } static inline int pmd_young(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_ACCESSED; } static inline int pud_dirty(pud_t pud) { return pud_flags(pud) & _PAGE_DIRTY; } static inline int pud_young(pud_t pud) { return pud_flags(pud) & _PAGE_ACCESSED; } static inline int pte_write(pte_t pte) { return pte_flags(pte) & _PAGE_RW; } static inline int pte_huge(pte_t pte) { return pte_flags(pte) & _PAGE_PSE; } static inline int pte_global(pte_t pte) { return pte_flags(pte) & _PAGE_GLOBAL; } static inline int pte_exec(pte_t pte) { return !(pte_flags(pte) & _PAGE_NX); } static inline int pte_special(pte_t pte) { return pte_flags(pte) & _PAGE_SPECIAL; } /* Entries that were set to PROT_NONE are inverted */ static inline u64 protnone_mask(u64 val); static inline unsigned long pte_pfn(pte_t pte) { phys_addr_t pfn = pte_val(pte); pfn ^= protnone_mask(pfn); return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT; } static inline unsigned long pmd_pfn(pmd_t pmd) { phys_addr_t pfn = pmd_val(pmd); pfn ^= protnone_mask(pfn); return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } static inline unsigned long pud_pfn(pud_t pud) { phys_addr_t pfn = pud_val(pud); pfn ^= protnone_mask(pfn); return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT; } static inline unsigned long p4d_pfn(p4d_t p4d) { return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT; } static inline unsigned long pgd_pfn(pgd_t pgd) { return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT; } #define p4d_leaf p4d_large static inline int p4d_large(p4d_t p4d) { /* No 512 GiB pages yet */ return 0; } #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define pmd_leaf pmd_large static inline int pmd_large(pmd_t pte) { return pmd_flags(pte) & _PAGE_PSE; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */ static inline int pmd_trans_huge(pmd_t pmd) { return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline int pud_trans_huge(pud_t pud) { return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; } #endif #define has_transparent_hugepage has_transparent_hugepage static inline int has_transparent_hugepage(void) { return boot_cpu_has(X86_FEATURE_PSE); } #ifdef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pmd_devmap(pmd_t pmd) { return !!(pmd_val(pmd) & _PAGE_DEVMAP); } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static inline int pud_devmap(pud_t pud) { return !!(pud_val(pud) & _PAGE_DEVMAP); } #else static inline int pud_devmap(pud_t pud) { return 0; } #endif static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t pte_set_flags(pte_t pte, pteval_t set) { pteval_t v = native_pte_val(pte); return native_make_pte(v | set); } static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear) { pteval_t v = native_pte_val(pte); return native_make_pte(v & ~clear); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { return pte_flags(pte) & _PAGE_UFFD_WP; } static inline pte_t pte_mkuffd_wp(pte_t pte) { return pte_set_flags(pte, _PAGE_UFFD_WP); } static inline pte_t pte_clear_uffd_wp(pte_t pte) { return pte_clear_flags(pte, _PAGE_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline pte_t pte_mkclean(pte_t pte) { return pte_clear_flags(pte, _PAGE_DIRTY); } static inline pte_t pte_mkold(pte_t pte) { return pte_clear_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_wrprotect(pte_t pte) { return pte_clear_flags(pte, _PAGE_RW); } static inline pte_t pte_mkexec(pte_t pte) { return pte_clear_flags(pte, _PAGE_NX); } static inline pte_t pte_mkdirty(pte_t pte) { return pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } static inline pte_t pte_mkyoung(pte_t pte) { return pte_set_flags(pte, _PAGE_ACCESSED); } static inline pte_t pte_mkwrite(pte_t pte) { return pte_set_flags(pte, _PAGE_RW); } static inline pte_t pte_mkhuge(pte_t pte) { return pte_set_flags(pte, _PAGE_PSE); } static inline pte_t pte_clrhuge(pte_t pte) { return pte_clear_flags(pte, _PAGE_PSE); } static inline pte_t pte_mkglobal(pte_t pte) { return pte_set_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_clrglobal(pte_t pte) { return pte_clear_flags(pte, _PAGE_GLOBAL); } static inline pte_t pte_mkspecial(pte_t pte) { return pte_set_flags(pte, _PAGE_SPECIAL); } static inline pte_t pte_mkdevmap(pte_t pte) { return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP); } static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) { pmdval_t v = native_pmd_val(pmd); return native_make_pmd(v | set); } static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) { pmdval_t v = native_pmd_val(pmd); return native_make_pmd(v & ~clear); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pmd_uffd_wp(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_UFFD_WP; } static inline pmd_t pmd_mkuffd_wp(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_UFFD_WP); } static inline pmd_t pmd_clear_uffd_wp(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline pmd_t pmd_mkold(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_ACCESSED); } static inline pmd_t pmd_mkclean(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_DIRTY); } static inline pmd_t pmd_wrprotect(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_RW); } static inline pmd_t pmd_mkdirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_mkdevmap(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_DEVMAP); } static inline pmd_t pmd_mkhuge(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_PSE); } static inline pmd_t pmd_mkyoung(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_ACCESSED); } static inline pmd_t pmd_mkwrite(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_RW); } static inline pud_t pud_set_flags(pud_t pud, pudval_t set) { pudval_t v = native_pud_val(pud); return native_make_pud(v | set); } static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) { pudval_t v = native_pud_val(pud); return native_make_pud(v & ~clear); } static inline pud_t pud_mkold(pud_t pud) { return pud_clear_flags(pud, _PAGE_ACCESSED); } static inline pud_t pud_mkclean(pud_t pud) { return pud_clear_flags(pud, _PAGE_DIRTY); } static inline pud_t pud_wrprotect(pud_t pud) { return pud_clear_flags(pud, _PAGE_RW); } static inline pud_t pud_mkdirty(pud_t pud) { return pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); } static inline pud_t pud_mkdevmap(pud_t pud) { return pud_set_flags(pud, _PAGE_DEVMAP); } static inline pud_t pud_mkhuge(pud_t pud) { return pud_set_flags(pud, _PAGE_PSE); } static inline pud_t pud_mkyoung(pud_t pud) { return pud_set_flags(pud, _PAGE_ACCESSED); } static inline pud_t pud_mkwrite(pud_t pud) { return pud_set_flags(pud, _PAGE_RW); } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SOFT_DIRTY; } static inline int pmd_soft_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SOFT_DIRTY; } static inline int pud_soft_dirty(pud_t pud) { return pud_flags(pud) & _PAGE_SOFT_DIRTY; } static inline pte_t pte_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } static inline pud_t pud_mksoft_dirty(pud_t pud) { return pud_set_flags(pud, _PAGE_SOFT_DIRTY); } static inline pte_t pte_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); } static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); } static inline pud_t pud_clear_soft_dirty(pud_t pud) { return pud_clear_flags(pud, _PAGE_SOFT_DIRTY); } #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ /* * Mask out unsupported bits in a present pgprot. Non-present pgprots * can use those bits for other purposes, so leave them be. */ static inline pgprotval_t massage_pgprot(pgprot_t pgprot) { pgprotval_t protval = pgprot_val(pgprot); if (protval & _PAGE_PRESENT) protval &= __supported_pte_mask; return protval; } static inline pgprotval_t check_pgprot(pgprot_t pgprot) { pgprotval_t massaged_val = massage_pgprot(pgprot); /* mmdebug.h can not be included here because of dependencies */ #ifdef CONFIG_DEBUG_VM WARN_ONCE(pgprot_val(pgprot) != massaged_val, "attempted to set unsupported pgprot: %016llx " "bits: %016llx supported: %016llx\n", (u64)pgprot_val(pgprot), (u64)pgprot_val(pgprot) ^ massaged_val, (u64)__supported_pte_mask); #endif return massaged_val; } static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PTE_PFN_MASK; return __pte(pfn | check_pgprot(pgprot)); } static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PMD_PAGE_MASK; return __pmd(pfn | check_pgprot(pgprot)); } static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) { phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; pfn ^= protnone_mask(pgprot_val(pgprot)); pfn &= PHYSICAL_PUD_PAGE_MASK; return __pud(pfn | check_pgprot(pgprot)); } static inline pmd_t pmd_mkinvalid(pmd_t pmd) { return pfn_pmd(pmd_pfn(pmd), __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); } static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { pteval_t val = pte_val(pte), oldval = val; /* * Chop off the NX bit (if present), and add the NX portion of * the newprot (if present): */ val &= _PAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PTE_PFN_MASK); return __pte(val); } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { pmdval_t val = pmd_val(pmd), oldval = val; val &= _HPAGE_CHG_MASK; val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); return __pmd(val); } /* * mprotect needs to preserve PAT and encryption bits when updating * vm_page_prot */ #define pgprot_modify pgprot_modify static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) { pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK; pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK; return __pgprot(preservebits | addbits); } #define pte_pgprot(x) __pgprot(pte_flags(x)) #define pmd_pgprot(x) __pgprot(pmd_flags(x)) #define pud_pgprot(x) __pgprot(pud_flags(x)) #define p4d_pgprot(x) __pgprot(p4d_flags(x)) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) static inline pgprot_t arch_filter_pgprot(pgprot_t prot) { return canon_pgprot(prot); } static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, enum page_cache_mode pcm, enum page_cache_mode new_pcm) { /* * PAT type is always WB for untracked ranges, so no need to check. */ if (x86_platform.is_untracked_pat_range(paddr, paddr + size)) return 1; /* * Certain new memtypes are not allowed with certain * requested memtype: * - request is uncached, return cannot be write-back * - request is write-combine, return cannot be write-back * - request is write-through, return cannot be write-back * - request is write-through, return cannot be write-combine */ if ((pcm == _PAGE_CACHE_MODE_UC_MINUS && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WC && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WT && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WT && new_pcm == _PAGE_CACHE_MODE_WC)) { return 0; } return 1; } pmd_t *populate_extra_pmd(unsigned long vaddr); pte_t *populate_extra_pte(unsigned long vaddr); #ifdef CONFIG_PAGE_TABLE_ISOLATION pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd); /* * Take a PGD location (pgdp) and a pgd value that needs to be set there. * Populates the user and returns the resulting PGD that must be set in * the kernel copy of the page tables. */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { if (!static_cpu_has(X86_FEATURE_PTI)) return pgd; return __pti_set_user_pgtbl(pgdp, pgd); } #else /* CONFIG_PAGE_TABLE_ISOLATION */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { return pgd; } #endif /* CONFIG_PAGE_TABLE_ISOLATION */ #endif /* __ASSEMBLY__ */ #ifdef CONFIG_X86_32 # include <asm/pgtable_32.h> #else # include <asm/pgtable_64.h> #endif #ifndef __ASSEMBLY__ #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/log2.h> #include <asm/fixmap.h> static inline int pte_none(pte_t pte) { return !(pte.pte & ~(_PAGE_KNL_ERRATUM_MASK)); } #define __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t a, pte_t b) { return a.pte == b.pte; } static inline int pte_present(pte_t a) { return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); } #ifdef CONFIG_ARCH_HAS_PTE_DEVMAP static inline int pte_devmap(pte_t a) { return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP; } #endif #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { if (pte_flags(a) & _PAGE_PRESENT) return true; if ((pte_flags(a) & _PAGE_PROTNONE) && mm_tlb_flush_pending(mm)) return true; return false; } static inline int pmd_present(pmd_t pmd) { /* * Checking for _PAGE_PSE is needed too because * split_huge_page will temporarily clear the present bit (but * the _PAGE_PSE flag will remain set at all times while the * _PAGE_PRESENT bit is clear). */ return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE); } #ifdef CONFIG_NUMA_BALANCING /* * These work without NUMA balancing but the kernel does not care. See the * comment in include/linux/pgtable.h */ static inline int pte_protnone(pte_t pte) { return (pte_flags(pte) & (_PAGE_PROTNONE | _PAGE_PRESENT)) == _PAGE_PROTNONE; } static inline int pmd_protnone(pmd_t pmd) { return (pmd_flags(pmd) & (_PAGE_PROTNONE | _PAGE_PRESENT)) == _PAGE_PROTNONE; } #endif /* CONFIG_NUMA_BALANCING */ static inline int pmd_none(pmd_t pmd) { /* Only check low word on 32-bit platforms, since it might be out of sync with upper half. */ unsigned long val = native_pmd_val(pmd); return (val & ~_PAGE_KNL_ERRATUM_MASK) == 0; } static inline unsigned long pmd_page_vaddr(pmd_t pmd) { return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. * * (Currently stuck as a macro because of indirect forward reference * to linux/mm.h:page_to_nid()) */ #define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) static inline int pmd_bad(pmd_t pmd) { return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE; } static inline unsigned long pages_to_mb(unsigned long npg) { return npg >> (20 - PAGE_SHIFT); } #if CONFIG_PGTABLE_LEVELS > 2 static inline int pud_none(pud_t pud) { return (native_pud_val(pud) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; } static inline int pud_present(pud_t pud) { return pud_flags(pud) & _PAGE_PRESENT; } static inline pmd_t *pud_pgtable(pud_t pud) { return (pmd_t *)__va(pud_val(pud) & pud_pfn_mask(pud)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pud_page(pud) pfn_to_page(pud_pfn(pud)) #define pud_leaf pud_large static inline int pud_large(pud_t pud) { return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) == (_PAGE_PSE | _PAGE_PRESENT); } static inline int pud_bad(pud_t pud) { return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; } #else #define pud_leaf pud_large static inline int pud_large(pud_t pud) { return 0; } #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline int p4d_none(p4d_t p4d) { return (native_p4d_val(p4d) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; } static inline int p4d_present(p4d_t p4d) { return p4d_flags(p4d) & _PAGE_PRESENT; } static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_val(p4d) & p4d_pfn_mask(p4d)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d)) static inline int p4d_bad(p4d_t p4d) { unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER; if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (p4d_flags(p4d) & ~ignore_flags) != 0; } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ static inline unsigned long p4d_index(unsigned long address) { return (address >> P4D_SHIFT) & (PTRS_PER_P4D - 1); } #if CONFIG_PGTABLE_LEVELS > 4 static inline int pgd_present(pgd_t pgd) { if (!pgtable_l5_enabled()) return 1; return pgd_flags(pgd) & _PAGE_PRESENT; } static inline unsigned long pgd_page_vaddr(pgd_t pgd) { return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ #define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd)) /* to find an entry in a page-table-directory. */ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) { if (!pgtable_l5_enabled()) return (p4d_t *)pgd; return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address); } static inline int pgd_bad(pgd_t pgd) { unsigned long ignore_flags = _PAGE_USER; if (!pgtable_l5_enabled()) return 0; if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; } static inline int pgd_none(pgd_t pgd) { if (!pgtable_l5_enabled()) return 0; /* * There is no need to do a workaround for the KNL stray * A/D bit erratum here. PGDs only point to page tables * except on 32-bit non-PAE which is not supported on * KNL. */ return !native_pgd_val(pgd); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #endif /* __ASSEMBLY__ */ #define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET) #define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY) #ifndef __ASSEMBLY__ extern int direct_gbpages; void init_mem_mapping(void); void early_alloc_pgt_buf(void); extern void memblock_find_dma_reserve(void); void __init poking_init(void); unsigned long init_memory_mapping(unsigned long start, unsigned long end, pgprot_t prot); #ifdef CONFIG_X86_64 extern pgd_t trampoline_pgd_entry; #endif /* local pte updates need not use xchg for locking */ static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) { pte_t res = *ptep; /* Pure native function needs no input for mm, addr */ native_pte_clear(NULL, 0, ptep); return res; } static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp) { pmd_t res = *pmdp; native_pmd_clear(pmdp); return res; } static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp) { pud_t res = *pudp; native_pud_clear(pudp); return res; } static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { set_pte(ptep, pte); } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { native_set_pud(pudp, pud); } /* * We only update the dirty/accessed state if we set * the dirty bit by hand in the kernel, since the hardware * will do the accessed bit for us, and we don't want to * race with other CPU's that might be updating the dirty * bit at the same time. */ struct vm_area_struct; #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH extern int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep); #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = native_ptep_get_and_clear(ptep); return pte; } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full) { pte_t pte; if (full) { /* * Full address destruction in progress; paravirt does not * care about updates and native needs no locking */ pte = native_local_ptep_get_and_clear(ptep); } else { pte = ptep_get_and_clear(mm, addr, ptep); } return pte; } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte); } #define flush_tlb_fix_spurious_fault(vma, address) do { } while (0) #define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS extern int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty); extern int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, pud_t entry, int dirty); #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG extern int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp); extern int pudp_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp); #define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH extern int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #define pmd_write pmd_write static inline int pmd_write(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_RW; } #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { return native_pmdp_get_and_clear(pmdp); } #define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pud_t *pudp) { return native_pudp_get_and_clear(pudp); } #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp); } #define pud_write pud_write static inline int pud_write(pud_t pud) { return pud_flags(pud) & _PAGE_RW; } #ifndef pmdp_establish #define pmdp_establish pmdp_establish static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { if (IS_ENABLED(CONFIG_SMP)) { return xchg(pmdp, pmd); } else { pmd_t old = *pmdp; WRITE_ONCE(*pmdp, pmd); return old; } } #endif /* * Page table pages are page-aligned. The lower half of the top * level is used for userspace and the top half for the kernel. * * Returns true for parts of the PGD that map userspace and * false for the parts that map the kernel. */ static inline bool pgdp_maps_userspace(void *__ptr) { unsigned long ptr = (unsigned long)__ptr; return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START); } #define pgd_leaf pgd_large static inline int pgd_large(pgd_t pgd) { return 0; } #ifdef CONFIG_PAGE_TABLE_ISOLATION /* * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and * the user one is in the last 4k. To switch between them, you * just need to flip the 12th bit in their addresses. */ #define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT /* * This generates better code than the inline assembly in * __set_bit(). */ static inline void *ptr_set_bit(void *ptr, int bit) { unsigned long __ptr = (unsigned long)ptr; __ptr |= BIT(bit); return (void *)__ptr; } static inline void *ptr_clear_bit(void *ptr, int bit) { unsigned long __ptr = (unsigned long)ptr; __ptr &= ~BIT(bit); return (void *)__ptr; } static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) { return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); } static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) { return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); } static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) { return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) { return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } #endif /* CONFIG_PAGE_TABLE_ISOLATION */ /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); * * dst - pointer to pgd range anwhere on a pgd page * src - "" * count - the number of pgds to copy. * * dst and src can be on the same page, but the range must not overlap, * and must not cross a page boundary. */ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) { memcpy(dst, src, count * sizeof(pgd_t)); #ifdef CONFIG_PAGE_TABLE_ISOLATION if (!static_cpu_has(X86_FEATURE_PTI)) return; /* Clone the user space pgd as well */ memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src), count * sizeof(pgd_t)); #endif } #define PTE_SHIFT ilog2(PTRS_PER_PTE) static inline int page_level_shift(enum pg_level level) { return (PAGE_SHIFT - PTE_SHIFT) + level * PTE_SHIFT; } static inline unsigned long page_level_size(enum pg_level level) { return 1UL << page_level_shift(level); } static inline unsigned long page_level_mask(enum pg_level level) { return ~(page_level_size(level) - 1); } /* * The x86 doesn't have any external MMU info: the kernel page * tables contain all the necessary information. */ static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { } static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd) { } static inline void update_mmu_cache_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { } #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); } static inline int pte_swp_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SWP_SOFT_DIRTY); } static inline int pmd_swp_soft_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SWP_SOFT_DIRTY; } static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SWP_SOFT_DIRTY); } #endif #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline pte_t pte_swp_mkuffd_wp(pte_t pte) { return pte_set_flags(pte, _PAGE_SWP_UFFD_WP); } static inline int pte_swp_uffd_wp(pte_t pte) { return pte_flags(pte) & _PAGE_SWP_UFFD_WP; } static inline pte_t pte_swp_clear_uffd_wp(pte_t pte) { return pte_clear_flags(pte, _PAGE_SWP_UFFD_WP); } static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd) { return pmd_set_flags(pmd, _PAGE_SWP_UFFD_WP); } static inline int pmd_swp_uffd_wp(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_SWP_UFFD_WP; } static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd) { return pmd_clear_flags(pmd, _PAGE_SWP_UFFD_WP); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #define PKRU_AD_BIT 0x1u #define PKRU_WD_BIT 0x2u #define PKRU_BITS_PER_PKEY 2 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS extern u32 init_pkru_value; #else #define init_pkru_value 0 #endif static inline bool __pkru_allows_read(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits)); } static inline bool __pkru_allows_write(u32 pkru, u16 pkey) { int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; /* * Access-disable disables writes too so we need to check * both bits here. */ return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits)); } static inline u16 pte_flags_pkey(unsigned long pte_flags) { #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS /* ifdef to avoid doing 59-bit shift on 32-bit values */ return (pte_flags & _PAGE_PKEY_MASK) >> _PAGE_BIT_PKEY_BIT0; #else return 0; #endif } static inline bool __pkru_allows_pkey(u16 pkey, bool write) { u32 pkru = read_pkru(); if (!__pkru_allows_read(pkru, pkey)) return false; if (write && !__pkru_allows_write(pkru, pkey)) return false; return true; } /* * 'pteval' can come from a PTE, PMD or PUD. We only check * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the * same value on all 3 types. */ static inline bool __pte_access_permitted(unsigned long pteval, bool write) { unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; if (write) need_pte_bits |= _PAGE_RW; if ((pteval & need_pte_bits) != need_pte_bits) return 0; return __pkru_allows_pkey(pte_flags_pkey(pteval), write); } #define pte_access_permitted pte_access_permitted static inline bool pte_access_permitted(pte_t pte, bool write) { return __pte_access_permitted(pte_val(pte), write); } #define pmd_access_permitted pmd_access_permitted static inline bool pmd_access_permitted(pmd_t pmd, bool write) { return __pte_access_permitted(pmd_val(pmd), write); } #define pud_access_permitted pud_access_permitted static inline bool pud_access_permitted(pud_t pud, bool write) { return __pte_access_permitted(pud_val(pud), write); } #define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1 extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot); static inline bool arch_has_pfn_modify_check(void) { return boot_cpu_has_bug(X86_BUG_L1TF); } #define arch_faults_on_old_pte arch_faults_on_old_pte static inline bool arch_faults_on_old_pte(void) { return false; } #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic hugetlb support. * (C) Nadia Yvette Chambers, April 2004 */ #include <linux/list.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/seq_file.h> #include <linux/sysctl.h> #include <linux/highmem.h> #include <linux/mmu_notifier.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <linux/mempolicy.h> #include <linux/compiler.h> #include <linux/cpuset.h> #include <linux/mutex.h> #include <linux/memblock.h> #include <linux/sysfs.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/mmdebug.h> #include <linux/sched/signal.h> #include <linux/rmap.h> #include <linux/string_helpers.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/jhash.h> #include <linux/numa.h> #include <linux/llist.h> #include <linux/cma.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <linux/io.h> #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #include <linux/node.h> #include <linux/userfaultfd_k.h> #include <linux/page_owner.h> #include "internal.h" int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; #ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; #endif static unsigned long hugetlb_cma_size __initdata; /* * Minimum page order among possible hugepage sizes, set to a proper value * at boot time. */ static unsigned int minimum_order __read_mostly = UINT_MAX; __initdata LIST_HEAD(huge_boot_pages); /* for command line parsing */ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static bool __initdata parsed_valid_hugepagesz = true; static bool __initdata parsed_default_hugepagesz; /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, * free_huge_pages, and surplus_huge_pages. */ DEFINE_SPINLOCK(hugetlb_lock); /* * Serializes faults on the same logical page. This is used to * prevent spurious OOMs when the hugepage pool is fully utilized. */ static int num_fault_mutexes; struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp; static inline bool PageHugeFreed(struct page *head) { return page_private(head + 4) == -1UL; } static inline void SetPageHugeFreed(struct page *head) { set_page_private(head + 4, -1UL); } static inline void ClearPageHugeFreed(struct page *head) { set_page_private(head + 4, 0); } /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool take_locks); static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) { bool free = (spool->count == 0) && (spool->used_hpages == 0); spin_unlock(&spool->lock); /* If no pages are used, and no other handles to the subpool * remain, give up any reservations based on minimum size and * free the subpool */ if (free) { if (spool->min_hpages != -1) hugetlb_acct_memory(spool->hstate, -spool->min_hpages); kfree(spool); } } struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages) { struct hugepage_subpool *spool; spool = kzalloc(sizeof(*spool), GFP_KERNEL); if (!spool) return NULL; spin_lock_init(&spool->lock); spool->count = 1; spool->max_hpages = max_hpages; spool->hstate = h; spool->min_hpages = min_hpages; if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) { kfree(spool); return NULL; } spool->rsv_hpages = min_hpages; return spool; } void hugepage_put_subpool(struct hugepage_subpool *spool) { spin_lock(&spool->lock); BUG_ON(!spool->count); spool->count--; unlock_or_release_subpool(spool); } /* * Subpool accounting for allocating and reserving pages. * Return -ENOMEM if there are not enough resources to satisfy the * request. Otherwise, return the number of pages by which the * global pools must be adjusted (upward). The returned value may * only be different than the passed value (delta) in the case where * a subpool minimum size must be maintained. */ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; if (!spool) return ret; spin_lock(&spool->lock); if (spool->max_hpages != -1) { /* maximum size accounting */ if ((spool->used_hpages + delta) <= spool->max_hpages) spool->used_hpages += delta; else { ret = -ENOMEM; goto unlock_ret; } } /* minimum size accounting */ if (spool->min_hpages != -1 && spool->rsv_hpages) { if (delta > spool->rsv_hpages) { /* * Asking for more reserves than those already taken on * behalf of subpool. Return difference. */ ret = delta - spool->rsv_hpages; spool->rsv_hpages = 0; } else { ret = 0; /* reserves already accounted for */ spool->rsv_hpages -= delta; } } unlock_ret: spin_unlock(&spool->lock); return ret; } /* * Subpool accounting for freeing and unreserving pages. * Return the number of global page reservations that must be dropped. * The return value may only be different than the passed value (delta) * in the case where a subpool minimum size must be maintained. */ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; if (!spool) return delta; spin_lock(&spool->lock); if (spool->max_hpages != -1) /* maximum size accounting */ spool->used_hpages -= delta; /* minimum size accounting */ if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) { if (spool->rsv_hpages + delta <= spool->min_hpages) ret = 0; else ret = spool->rsv_hpages + delta - spool->min_hpages; spool->rsv_hpages += delta; if (spool->rsv_hpages > spool->min_hpages) spool->rsv_hpages = spool->min_hpages; } /* * If hugetlbfs_put_super couldn't free spool due to an outstanding * quota reference, free it now. */ unlock_or_release_subpool(spool); return ret; } static inline struct hugepage_subpool *subpool_inode(struct inode *inode) { return HUGETLBFS_SB(inode->i_sb)->spool; } static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) { return subpool_inode(file_inode(vma->vm_file)); } /* Helper that removes a struct file_region from the resv_map cache and returns * it for use. */ static struct file_region * get_file_region_entry_from_cache(struct resv_map *resv, long from, long to) { struct file_region *nrg = NULL; VM_BUG_ON(resv->region_cache_count <= 0); resv->region_cache_count--; nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); nrg->from = from; nrg->to = to; return nrg; } static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg, struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB nrg->reservation_counter = rg->reservation_counter; nrg->css = rg->css; if (rg->css) css_get(rg->css); #endif } /* Helper that records hugetlb_cgroup uncharge info. */ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, struct hstate *h, struct resv_map *resv, struct file_region *nrg) { #ifdef CONFIG_CGROUP_HUGETLB if (h_cg) { nrg->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; /* * The caller will hold exactly one h_cg->css reference for the * whole contiguous reservation region. But this area might be * scattered when there are already some file_regions reside in * it. As a result, many file_regions may share only one css * reference. In order to ensure that one file_region must hold * exactly one h_cg->css reference, we should do css_get for * each file_region and leave the reference held by caller * untouched. */ css_get(&h_cg->css); if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h); /* pages_per_hpage should be the same for all entries in * a resv_map. */ VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h)); } else { nrg->reservation_counter = NULL; nrg->css = NULL; } #endif } static void put_uncharge_info(struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB if (rg->css) css_put(rg->css); #endif } static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { #ifdef CONFIG_CGROUP_HUGETLB return rg && org && rg->reservation_counter == org->reservation_counter && rg->css == org->css; #else return true; #endif } static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) { struct file_region *nrg = NULL, *prg = NULL; prg = list_prev_entry(rg, link); if (&prg->link != &resv->regions && prg->to == rg->from && has_same_uncharge_info(prg, rg)) { prg->to = rg->to; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); rg = prg; } nrg = list_next_entry(rg, link); if (&nrg->link != &resv->regions && nrg->from == rg->to && has_same_uncharge_info(nrg, rg)) { nrg->from = rg->from; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); } } /* * Must be called with resv->lock held. * * Calling this with regions_needed != NULL will count the number of pages * to be added but will not modify the linked list. And regions_needed will * indicate the number of file_regions needed in the cache to carry out to add * the regions for this range. */ static long add_reservation_in_range(struct resv_map *resv, long f, long t, struct hugetlb_cgroup *h_cg, struct hstate *h, long *regions_needed) { long add = 0; struct list_head *head = &resv->regions; long last_accounted_offset = f; struct file_region *rg = NULL, *trg = NULL, *nrg = NULL; if (regions_needed) *regions_needed = 0; /* In this loop, we essentially handle an entry for the range * [last_accounted_offset, rg->from), at every iteration, with some * bounds checking. */ list_for_each_entry_safe(rg, trg, head, link) { /* Skip irrelevant regions that start before our range. */ if (rg->from < f) { /* If this region ends after the last accounted offset, * then we need to update last_accounted_offset. */ if (rg->to > last_accounted_offset) last_accounted_offset = rg->to; continue; } /* When we find a region that starts beyond our range, we've * finished. */ if (rg->from > t) break; /* Add an entry for last_accounted_offset -> rg->from, and * update last_accounted_offset. */ if (rg->from > last_accounted_offset) { add += rg->from - last_accounted_offset; if (!regions_needed) { nrg = get_file_region_entry_from_cache( resv, last_accounted_offset, rg->from); record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg); list_add(&nrg->link, rg->link.prev); coalesce_file_region(resv, nrg); } else *regions_needed += 1; } last_accounted_offset = rg->to; } /* Handle the case where our range extends beyond * last_accounted_offset. */ if (last_accounted_offset < t) { add += t - last_accounted_offset; if (!regions_needed) { nrg = get_file_region_entry_from_cache( resv, last_accounted_offset, t); record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg); list_add(&nrg->link, rg->link.prev); coalesce_file_region(resv, nrg); } else *regions_needed += 1; } VM_BUG_ON(add < 0); return add; } /* Must be called with resv->lock acquired. Will drop lock to allocate entries. */ static int allocate_file_region_entries(struct resv_map *resv, int regions_needed) __must_hold(&resv->lock) { struct list_head allocated_regions; int to_allocate = 0, i = 0; struct file_region *trg = NULL, *rg = NULL; VM_BUG_ON(regions_needed < 0); INIT_LIST_HEAD(&allocated_regions); /* * Check for sufficient descriptors in the cache to accommodate * the number of in progress add operations plus regions_needed. * * This is a while loop because when we drop the lock, some other call * to region_add or region_del may have consumed some region_entries, * so we keep looping here until we finally have enough entries for * (adds_in_progress + regions_needed). */ while (resv->region_cache_count < (resv->adds_in_progress + regions_needed)) { to_allocate = resv->adds_in_progress + regions_needed - resv->region_cache_count; /* At this point, we should have enough entries in the cache * for all the existings adds_in_progress. We should only be * needing to allocate for regions_needed. */ VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress); spin_unlock(&resv->lock); for (i = 0; i < to_allocate; i++) { trg = kmalloc(sizeof(*trg), GFP_KERNEL); if (!trg) goto out_of_memory; list_add(&trg->link, &allocated_regions); } spin_lock(&resv->lock); list_splice(&allocated_regions, &resv->region_cache); resv->region_cache_count += to_allocate; } return 0; out_of_memory: list_for_each_entry_safe(rg, trg, &allocated_regions, link) { list_del(&rg->link); kfree(rg); } return -ENOMEM; } /* * Add the huge page range represented by [f, t) to the reserve * map. Regions will be taken from the cache to fill in this range. * Sufficient regions should exist in the cache due to the previous * call to region_chg with the same range, but in some cases the cache will not * have sufficient entries due to races with other code doing region_add or * region_del. The extra needed entries will be allocated. * * regions_needed is the out value provided by a previous call to region_chg. * * Return the number of new huge pages added to the map. This number is greater * than or equal to zero. If file_region entries needed to be allocated for * this operation and we were not able to allocate, it returns -ENOMEM. * region_add of regions of length 1 never allocate file_regions and cannot * fail; region_chg will always allocate at least 1 entry and a region_add for * 1 page will only require at most 1 entry. */ static long region_add(struct resv_map *resv, long f, long t, long in_regions_needed, struct hstate *h, struct hugetlb_cgroup *h_cg) { long add = 0, actual_regions_needed = 0; spin_lock(&resv->lock); retry: /* Count how many regions are actually needed to execute this add. */ add_reservation_in_range(resv, f, t, NULL, NULL, &actual_regions_needed); /* * Check for sufficient descriptors in the cache to accommodate * this add operation. Note that actual_regions_needed may be greater * than in_regions_needed, as the resv_map may have been modified since * the region_chg call. In this case, we need to make sure that we * allocate extra entries, such that we have enough for all the * existing adds_in_progress, plus the excess needed for this * operation. */ if (actual_regions_needed > in_regions_needed && resv->region_cache_count < resv->adds_in_progress + (actual_regions_needed - in_regions_needed)) { /* region_add operation of range 1 should never need to * allocate file_region entries. */ VM_BUG_ON(t - f <= 1); if (allocate_file_region_entries( resv, actual_regions_needed - in_regions_needed)) { return -ENOMEM; } goto retry; } add = add_reservation_in_range(resv, f, t, h_cg, h, NULL); resv->adds_in_progress -= in_regions_needed; spin_unlock(&resv->lock); VM_BUG_ON(add < 0); return add; } /* * Examine the existing reserve map and determine how many * huge pages in the specified range [f, t) are NOT currently * represented. This routine is called before a subsequent * call to region_add that will actually modify the reserve * map to add the specified range [f, t). region_chg does * not change the number of huge pages represented by the * map. A number of new file_region structures is added to the cache as a * placeholder, for the subsequent region_add call to use. At least 1 * file_region structure is added. * * out_regions_needed is the number of regions added to the * resv->adds_in_progress. This value needs to be provided to a follow up call * to region_add or region_abort for proper accounting. * * Returns the number of huge pages that need to be added to the existing * reservation map for the range [f, t). This number is greater or equal to * zero. -ENOMEM is returned if a new file_region structure or cache entry * is needed and can not be allocated. */ static long region_chg(struct resv_map *resv, long f, long t, long *out_regions_needed) { long chg = 0; spin_lock(&resv->lock); /* Count how many hugepages in this range are NOT represented. */ chg = add_reservation_in_range(resv, f, t, NULL, NULL, out_regions_needed); if (*out_regions_needed == 0) *out_regions_needed = 1; if (allocate_file_region_entries(resv, *out_regions_needed)) return -ENOMEM; resv->adds_in_progress += *out_regions_needed; spin_unlock(&resv->lock); return chg; } /* * Abort the in progress add operation. The adds_in_progress field * of the resv_map keeps track of the operations in progress between * calls to region_chg and region_add. Operations are sometimes * aborted after the call to region_chg. In such cases, region_abort * is called to decrement the adds_in_progress counter. regions_needed * is the value returned by the region_chg call, it is used to decrement * the adds_in_progress counter. * * NOTE: The range arguments [f, t) are not needed or used in this * routine. They are kept to make reading the calling code easier as * arguments will match the associated region_chg call. */ static void region_abort(struct resv_map *resv, long f, long t, long regions_needed) { spin_lock(&resv->lock); VM_BUG_ON(!resv->region_cache_count); resv->adds_in_progress -= regions_needed; spin_unlock(&resv->lock); } /* * Delete the specified range [f, t) from the reserve map. If the * t parameter is LONG_MAX, this indicates that ALL regions after f * should be deleted. Locate the regions which intersect [f, t) * and either trim, delete or split the existing regions. * * Returns the number of huge pages deleted from the reserve map. * In the normal case, the return value is zero or more. In the * case where a region must be split, a new region descriptor must * be allocated. If the allocation fails, -ENOMEM will be returned. * NOTE: If the parameter t == LONG_MAX, then we will never split * a region and possibly return -ENOMEM. Callers specifying * t == LONG_MAX do not need to check for -ENOMEM error. */ static long region_del(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg, *trg; struct file_region *nrg = NULL; long del = 0; retry: spin_lock(&resv->lock); list_for_each_entry_safe(rg, trg, head, link) { /* * Skip regions before the range to be deleted. file_region * ranges are normally of the form [from, to). However, there * may be a "placeholder" entry in the map which is of the form * (from, to) with from == to. Check for placeholder entries * at the beginning of the range to be deleted. */ if (rg->to <= f && (rg->to != rg->from || rg->to != f)) continue; if (rg->from >= t) break; if (f > rg->from && t < rg->to) { /* Must split region */ /* * Check for an entry in the cache before dropping * lock and attempting allocation. */ if (!nrg && resv->region_cache_count > resv->adds_in_progress) { nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); resv->region_cache_count--; } if (!nrg) { spin_unlock(&resv->lock); nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); if (!nrg) return -ENOMEM; goto retry; } del += t - f; hugetlb_cgroup_uncharge_file_region( resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; nrg->to = rg->to; copy_hugetlb_cgroup_uncharge_info(nrg, rg); INIT_LIST_HEAD(&nrg->link); /* Original entry is trimmed */ rg->to = f; list_add(&nrg->link, &rg->link); nrg = NULL; break; } if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; } if (f <= rg->from) { /* Trim beginning of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, t - rg->from, false); del += t - rg->from; rg->from = t; } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - f, false); del += rg->to - f; rg->to = f; } } spin_unlock(&resv->lock); kfree(nrg); return del; } /* * A rare out of memory error was encountered which prevented removal of * the reserve map region for a page. The huge page itself was free'ed * and removed from the page cache. This routine will adjust the subpool * usage count, and the global reserve count if needed. By incrementing * these counts, the reserve map entry which could not be deleted will * appear as a "reserved" entry instead of simply dangling with incorrect * counts. */ void hugetlb_fix_reserve_counts(struct inode *inode) { struct hugepage_subpool *spool = subpool_inode(inode); long rsv_adjust; bool reserved = false; rsv_adjust = hugepage_subpool_get_pages(spool, 1); if (rsv_adjust > 0) { struct hstate *h = hstate_inode(inode); if (!hugetlb_acct_memory(h, 1)) reserved = true; } else if (!rsv_adjust) { reserved = true; } if (!reserved) pr_warn("hugetlb: Huge Page Reserved count may go negative.\n"); } /* * Count and return the number of huge pages in the reserve map * that intersect with the range [f, t). */ static long region_count(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg; long chg = 0; spin_lock(&resv->lock); /* Locate each segment we overlap with, and count that overlap. */ list_for_each_entry(rg, head, link) { long seg_from; long seg_to; if (rg->to <= f) continue; if (rg->from >= t) break; seg_from = max(rg->from, f); seg_to = min(rg->to, t); chg += seg_to - seg_from; } spin_unlock(&resv->lock); return chg; } /* * Convert the address within this vma to the page offset within * the mapping, in pagecache page units; huge pages here. */ static pgoff_t vma_hugecache_offset(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return ((address - vma->vm_start) >> huge_page_shift(h)) + (vma->vm_pgoff >> huge_page_order(h)); } pgoff_t linear_hugepage_index(struct vm_area_struct *vma, unsigned long address) { return vma_hugecache_offset(hstate_vma(vma), vma, address); } EXPORT_SYMBOL_GPL(linear_hugepage_index); /* * Return the size of the pages allocated when backing a VMA. In the majority * cases this will be same size as used by the page table entries. */ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { if (vma->vm_ops && vma->vm_ops->pagesize) return vma->vm_ops->pagesize(vma); return PAGE_SIZE; } EXPORT_SYMBOL_GPL(vma_kernel_pagesize); /* * Return the page size being used by the MMU to back a VMA. In the majority * of cases, the page size used by the kernel matches the MMU size. On * architectures where it differs, an architecture-specific 'strong' * version of this symbol is required. */ __weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return vma_kernel_pagesize(vma); } /* * Flags for MAP_PRIVATE reservations. These are stored in the bottom * bits of the reservation map pointer, which are always clear due to * alignment. */ #define HPAGE_RESV_OWNER (1UL << 0) #define HPAGE_RESV_UNMAPPED (1UL << 1) #define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED) /* * These helpers are used to track how many pages are reserved for * faults in a MAP_PRIVATE mapping. Only the process that called mmap() * is guaranteed to have their future faults succeed. * * With the exception of reset_vma_resv_huge_pages() which is called at fork(), * the reserve counters are updated with the hugetlb_lock held. It is safe * to reset the VMA at fork() time as it is not in use yet and there is no * chance of the global counters getting corrupted as a result of the values. * * The private mapping reservation is represented in a subtly different * manner to a shared mapping. A shared mapping has a region map associated * with the underlying file, this region map represents the backing file * pages which have ever had a reservation assigned which this persists even * after the page is instantiated. A private mapping has a region map * associated with the original mmap which is attached to all VMAs which * reference it, this region map represents those offsets which have consumed * reservation ie. where pages have been instantiated. */ static unsigned long get_vma_private_data(struct vm_area_struct *vma) { return (unsigned long)vma->vm_private_data; } static void set_vma_private_data(struct vm_area_struct *vma, unsigned long value) { vma->vm_private_data = (void *)value; } static void resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map, struct hugetlb_cgroup *h_cg, struct hstate *h) { #ifdef CONFIG_CGROUP_HUGETLB if (!h_cg || !h) { resv_map->reservation_counter = NULL; resv_map->pages_per_hpage = 0; resv_map->css = NULL; } else { resv_map->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; resv_map->pages_per_hpage = pages_per_huge_page(h); resv_map->css = &h_cg->css; } #endif } struct resv_map *resv_map_alloc(void) { struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); struct file_region *rg = kmalloc(sizeof(*rg), GFP_KERNEL); if (!resv_map || !rg) { kfree(resv_map); kfree(rg); return NULL; } kref_init(&resv_map->refs); spin_lock_init(&resv_map->lock); INIT_LIST_HEAD(&resv_map->regions); resv_map->adds_in_progress = 0; /* * Initialize these to 0. On shared mappings, 0's here indicate these * fields don't do cgroup accounting. On private mappings, these will be * re-initialized to the proper values, to indicate that hugetlb cgroup * reservations are to be un-charged from here. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL); INIT_LIST_HEAD(&resv_map->region_cache); list_add(&rg->link, &resv_map->region_cache); resv_map->region_cache_count = 1; return resv_map; } void resv_map_release(struct kref *ref) { struct resv_map *resv_map = container_of(ref, struct resv_map, refs); struct list_head *head = &resv_map->region_cache; struct file_region *rg, *trg; /* Clear out any active regions before we release the map. */ region_del(resv_map, 0, LONG_MAX); /* ... and any entries left in the cache */ list_for_each_entry_safe(rg, trg, head, link) { list_del(&rg->link); kfree(rg); } VM_BUG_ON(resv_map->adds_in_progress); kfree(resv_map); } static inline struct resv_map *inode_resv_map(struct inode *inode) { /* * At inode evict time, i_mapping may not point to the original * address space within the inode. This original address space * contains the pointer to the resv_map. So, always use the * address space embedded within the inode. * The VERY common case is inode->mapping == &inode->i_data but, * this may not be true for device special inodes. */ return (struct resv_map *)(&inode->i_data)->private_data; } static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); if (vma->vm_flags & VM_MAYSHARE) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; return inode_resv_map(inode); } else { return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); } } static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, (get_vma_private_data(vma) & HPAGE_RESV_MASK) | (unsigned long)map); } static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, get_vma_private_data(vma) | flags); } static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); return (get_vma_private_data(vma) & flag) != 0; } /* Reset counters to 0 and clear all HPAGE_RESV_* flags */ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); if (!(vma->vm_flags & VM_MAYSHARE)) vma->vm_private_data = (void *)0; } /* Returns true if the VMA has associated reserve pages */ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) { if (vma->vm_flags & VM_NORESERVE) { /* * This address is already reserved by other process(chg == 0), * so, we should decrement reserved count. Without decrementing, * reserve count remains after releasing inode, because this * allocated page will go into page cache and is regarded as * coming from reserved pool in releasing step. Currently, we * don't have any other solution to deal with this situation * properly, so add work-around here. */ if (vma->vm_flags & VM_MAYSHARE && chg == 0) return true; else return false; } /* Shared mappings always use reserves */ if (vma->vm_flags & VM_MAYSHARE) { /* * We know VM_NORESERVE is not set. Therefore, there SHOULD * be a region map for all pages. The only situation where * there is no region map is if a hole was punched via * fallocate. In this case, there really are no reserves to * use. This situation is indicated if chg != 0. */ if (chg) return false; else return true; } /* * Only the process that called mmap() has reserves for * private mappings. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { /* * Like the shared case above, a hole punch or truncate * could have been performed on the private mapping. * Examine the value of chg to determine if reserves * actually exist or were previously consumed. * Very Subtle - The value of chg comes from a previous * call to vma_needs_reserves(). The reserve map for * private mappings has different (opposite) semantics * than that of shared mappings. vma_needs_reserves() * has already taken this difference in semantics into * account. Therefore, the meaning of chg is the same * as in the shared case above. Code could easily be * combined, but keeping it separate draws attention to * subtle differences. */ if (chg) return false; else return true; } return false; } static void enqueue_huge_page(struct hstate *h, struct page *page) { int nid = page_to_nid(page); list_move(&page->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; SetPageHugeFreed(page); } static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) { struct page *page; bool nocma = !!(current->flags & PF_MEMALLOC_NOCMA); list_for_each_entry(page, &h->hugepage_freelists[nid], lru) { if (nocma && is_migrate_cma_page(page)) continue; if (PageHWPoison(page)) continue; list_move(&page->lru, &h->hugepage_activelist); set_page_refcounted(page); ClearPageHugeFreed(page); h->free_huge_pages--; h->free_huge_pages_node[nid]--; return page; } return NULL; } static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { unsigned int cpuset_mems_cookie; struct zonelist *zonelist; struct zone *zone; struct zoneref *z; int node = NUMA_NO_NODE; zonelist = node_zonelist(nid, gfp_mask); retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) { struct page *page; if (!cpuset_zone_allowed(zone, gfp_mask)) continue; /* * no need to ask again on the same node. Pool is node rather than * zone aware */ if (zone_to_nid(zone) == node) continue; node = zone_to_nid(zone); page = dequeue_huge_page_node_exact(h, node); if (page) return page; } if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return NULL; } static struct page *dequeue_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve, long chg) { struct page *page; struct mempolicy *mpol; gfp_t gfp_mask; nodemask_t *nodemask; int nid; /* * A child process with MAP_PRIVATE mappings created by their parent * have no page reserves. This check ensures that reservations are * not "stolen". The child may still get SIGKILLed */ if (!vma_has_reserves(vma, chg) && h->free_huge_pages - h->resv_huge_pages == 0) goto err; /* If reserves cannot be used, ensure enough pages are in the pool */ if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0) goto err; gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask); if (page && !avoid_reserve && vma_has_reserves(vma, chg)) { SetPagePrivate(page); h->resv_huge_pages--; } mpol_cond_put(mpol); return page; err: return NULL; } /* * common helper functions for hstate_next_node_to_{alloc|free}. * We may have allocated or freed a huge page based on a different * nodes_allowed previously, so h->next_node_to_{alloc|free} might * be outside of *nodes_allowed. Ensure that we use an allowed * node for alloc or free. */ static int next_node_allowed(int nid, nodemask_t *nodes_allowed) { nid = next_node_in(nid, *nodes_allowed); VM_BUG_ON(nid >= MAX_NUMNODES); return nid; } static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) { if (!node_isset(nid, *nodes_allowed)) nid = next_node_allowed(nid, nodes_allowed); return nid; } /* * returns the previously saved node ["this node"] from which to * allocate a persistent huge page for the pool and advance the * next node from which to allocate, handling wrap at end of node * mask. */ static int hstate_next_node_to_alloc(struct hstate *h, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed); h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed); return nid; } /* * helper for free_pool_huge_page() - return the previously saved * node ["this node"] from which to free a huge page. Advance the * next node id whether or not we find a free huge page to free so * that the next attempt to free addresses the next node. */ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); return nid; } #define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_alloc(hs, mask)) || 1); \ nr_nodes--) #define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE static void destroy_compound_gigantic_page(struct page *page, unsigned int order) { int i; int nr_pages = 1 << order; struct page *p = page + 1; atomic_set(compound_mapcount_ptr(page), 0); atomic_set(compound_pincount_ptr(page), 0); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { clear_compound_head(p); set_page_refcounted(p); } set_compound_order(page, 0); page[1].compound_nr = 0; __ClearPageHead(page); } static void free_gigantic_page(struct page *page, unsigned int order) { /* * If the page isn't allocated using the cma allocator, * cma_release() returns false. */ #ifdef CONFIG_CMA if (cma_release(hugetlb_cma[page_to_nid(page)], page, 1 << order)) return; #endif free_contig_range(page_to_pfn(page), 1 << order); } #ifdef CONFIG_CONTIG_ALLOC static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { unsigned long nr_pages = 1UL << huge_page_order(h); if (nid == NUMA_NO_NODE) nid = numa_mem_id(); #ifdef CONFIG_CMA { struct page *page; int node; if (hugetlb_cma[nid]) { page = cma_alloc(hugetlb_cma[nid], nr_pages, huge_page_order(h), true); if (page) return page; } if (!(gfp_mask & __GFP_THISNODE)) { for_each_node_mask(node, *nodemask) { if (node == nid || !hugetlb_cma[node]) continue; page = cma_alloc(hugetlb_cma[node], nr_pages, huge_page_order(h), true); if (page) return page; } } } #endif return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); } #else /* !CONFIG_CONTIG_ALLOC */ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } #endif /* CONFIG_CONTIG_ALLOC */ #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } static inline void free_gigantic_page(struct page *page, unsigned int order) { } static inline void destroy_compound_gigantic_page(struct page *page, unsigned int order) { } #endif static void update_and_free_page(struct hstate *h, struct page *page) { int i; struct page *subpage = page; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; h->nr_huge_pages--; h->nr_huge_pages_node[page_to_nid(page)]--; for (i = 0; i < pages_per_huge_page(h); i++, subpage = mem_map_next(subpage, page, i)) { subpage->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | 1 << PG_dirty | 1 << PG_active | 1 << PG_private | 1 << PG_writeback); } VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page); VM_BUG_ON_PAGE(hugetlb_cgroup_from_page_rsvd(page), page); set_compound_page_dtor(page, NULL_COMPOUND_DTOR); set_page_refcounted(page); if (hstate_is_gigantic(h)) { /* * Temporarily drop the hugetlb_lock, because * we might block in free_gigantic_page(). */ spin_unlock(&hugetlb_lock); destroy_compound_gigantic_page(page, huge_page_order(h)); free_gigantic_page(page, huge_page_order(h)); spin_lock(&hugetlb_lock); } else { __free_pages(page, huge_page_order(h)); } } struct hstate *size_to_hstate(unsigned long size) { struct hstate *h; for_each_hstate(h) { if (huge_page_size(h) == size) return h; } return NULL; } /* * Test to determine whether the hugepage is "active/in-use" (i.e. being linked * to hstate->hugepage_activelist.) * * This function can be called for tail pages, but never returns true for them. */ bool page_huge_active(struct page *page) { return PageHeadHuge(page) && PagePrivate(&page[1]); } /* never called for tail page */ void set_page_huge_active(struct page *page) { VM_BUG_ON_PAGE(!PageHeadHuge(page), page); SetPagePrivate(&page[1]); } static void clear_page_huge_active(struct page *page) { VM_BUG_ON_PAGE(!PageHeadHuge(page), page); ClearPagePrivate(&page[1]); } /* * Internal hugetlb specific page flag. Do not use outside of the hugetlb * code */ static inline bool PageHugeTemporary(struct page *page) { if (!PageHuge(page)) return false; return (unsigned long)page[2].mapping == -1U; } static inline void SetPageHugeTemporary(struct page *page) { page[2].mapping = (void *)-1U; } static inline void ClearPageHugeTemporary(struct page *page) { page[2].mapping = NULL; } static void __free_huge_page(struct page *page) { /* * Can't pass hstate in here because it is called from the * compound page destructor. */ struct hstate *h = page_hstate(page); int nid = page_to_nid(page); struct hugepage_subpool *spool = (struct hugepage_subpool *)page_private(page); bool restore_reserve; VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(page_mapcount(page), page); set_page_private(page, 0); page->mapping = NULL; restore_reserve = PagePrivate(page); ClearPagePrivate(page); /* * If PagePrivate() was set on page, page allocation consumed a * reservation. If the page was associated with a subpool, there * would have been a page reserved in the subpool before allocation * via hugepage_subpool_get_pages(). Since we are 'restoring' the * reservtion, do not call hugepage_subpool_put_pages() as this will * remove the reserved page from the subpool. */ if (!restore_reserve) { /* * A return code of zero implies that the subpool will be * under its minimum size if the reservation is not restored * after page is free. Therefore, force restore_reserve * operation. */ if (hugepage_subpool_put_pages(spool, 1) == 0) restore_reserve = true; } spin_lock(&hugetlb_lock); clear_page_huge_active(page); hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h), page); hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), pages_per_huge_page(h), page); if (restore_reserve) h->resv_huge_pages++; if (PageHugeTemporary(page)) { list_del(&page->lru); ClearPageHugeTemporary(page); update_and_free_page(h, page); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ list_del(&page->lru); update_and_free_page(h, page); h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; } else { arch_clear_hugepage_flags(page); enqueue_huge_page(h, page); } spin_unlock(&hugetlb_lock); } /* * As free_huge_page() can be called from a non-task context, we have * to defer the actual freeing in a workqueue to prevent potential * hugetlb_lock deadlock. * * free_hpage_workfn() locklessly retrieves the linked list of pages to * be freed and frees them one-by-one. As the page->mapping pointer is * going to be cleared in __free_huge_page() anyway, it is reused as the * llist_node structure of a lockless linked list of huge pages to be freed. */ static LLIST_HEAD(hpage_freelist); static void free_hpage_workfn(struct work_struct *work) { struct llist_node *node; struct page *page; node = llist_del_all(&hpage_freelist); while (node) { page = container_of((struct address_space **)node, struct page, mapping); node = node->next; __free_huge_page(page); } } static DECLARE_WORK(free_hpage_work, free_hpage_workfn); void free_huge_page(struct page *page) { /* * Defer freeing if in non-task context to avoid hugetlb_lock deadlock. */ if (!in_task()) { /* * Only call schedule_work() if hpage_freelist is previously * empty. Otherwise, schedule_work() had been called but the * workfn hasn't retrieved the list yet. */ if (llist_add((struct llist_node *)&page->mapping, &hpage_freelist)) schedule_work(&free_hpage_work); return; } __free_huge_page(page); } static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { INIT_LIST_HEAD(&page->lru); set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); set_hugetlb_cgroup(page, NULL); set_hugetlb_cgroup_rsvd(page, NULL); spin_lock(&hugetlb_lock); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; ClearPageHugeFreed(page); spin_unlock(&hugetlb_lock); } static void prep_compound_gigantic_page(struct page *page, unsigned int order) { int i; int nr_pages = 1 << order; struct page *p = page + 1; /* we rely on prep_new_huge_page to set the destructor */ set_compound_order(page, order); __ClearPageReserved(page); __SetPageHead(page); for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { /* * For gigantic hugepages allocated through bootmem at * boot, it's safer to be consistent with the not-gigantic * hugepages and clear the PG_reserved bit from all tail pages * too. Otherwise drivers using get_user_pages() to access tail * pages may get the reference counting wrong if they see * PG_reserved set on a tail page (despite the head page not * having PG_reserved set). Enforcing this consistency between * head and tail pages allows drivers to optimize away a check * on the head page when they need know if put_page() is needed * after get_user_pages(). */ __ClearPageReserved(p); set_page_count(p, 0); set_compound_head(p, page); } atomic_set(compound_mapcount_ptr(page), -1); atomic_set(compound_pincount_ptr(page), 0); } /* * PageHuge() only returns true for hugetlbfs pages, but not for normal or * transparent huge pages. See the PageTransHuge() documentation for more * details. */ int PageHuge(struct page *page) { if (!PageCompound(page)) return 0; page = compound_head(page); return page[1].compound_dtor == HUGETLB_PAGE_DTOR; } EXPORT_SYMBOL_GPL(PageHuge); /* * PageHeadHuge() only returns true for hugetlbfs head page, but not for * normal or transparent huge pages. */ int PageHeadHuge(struct page *page_head) { if (!PageHead(page_head)) return 0; return page_head[1].compound_dtor == HUGETLB_PAGE_DTOR; } /* * Find and lock address space (mapping) in write mode. * * Upon entry, the page is locked which means that page_mapping() is * stable. Due to locking order, we can only trylock_write. If we can * not get the lock, simply return NULL to caller. */ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) { struct address_space *mapping = page_mapping(hpage); if (!mapping) return mapping; if (i_mmap_trylock_write(mapping)) return mapping; return NULL; } pgoff_t hugetlb_basepage_index(struct page *page) { struct page *page_head = compound_head(page); pgoff_t index = page_index(page_head); unsigned long compound_idx; if (compound_order(page_head) >= MAX_ORDER) compound_idx = page_to_pfn(page) - page_to_pfn(page_head); else compound_idx = page - page_head; return (index << compound_order(page_head)) + compound_idx; } static struct page *alloc_buddy_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { int order = huge_page_order(h); struct page *page; bool alloc_try_hard = true; /* * By default we always try hard to allocate the page with * __GFP_RETRY_MAYFAIL flag. However, if we are allocating pages in * a loop (to adjust global huge page counts) and previous allocation * failed, do not continue to try hard on the same node. Use the * node_alloc_noretry bitmap to manage this state information. */ if (node_alloc_noretry && node_isset(nid, *node_alloc_noretry)) alloc_try_hard = false; gfp_mask |= __GFP_COMP|__GFP_NOWARN; if (alloc_try_hard) gfp_mask |= __GFP_RETRY_MAYFAIL; if (nid == NUMA_NO_NODE) nid = numa_mem_id(); page = __alloc_pages_nodemask(gfp_mask, order, nid, nmask); if (page) __count_vm_event(HTLB_BUDDY_PGALLOC); else __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); /* * If we did not specify __GFP_RETRY_MAYFAIL, but still got a page this * indicates an overall state change. Clear bit so that we resume * normal 'try hard' allocations. */ if (node_alloc_noretry && page && !alloc_try_hard) node_clear(nid, *node_alloc_noretry); /* * If we tried hard to get a page but failed, set bit so that * subsequent attempts will not try as hard until there is an * overall state change. */ if (node_alloc_noretry && !page && alloc_try_hard) node_set(nid, *node_alloc_noretry); return page; } /* * Common helper to allocate a fresh hugetlb page. All specific allocators * should use this function to get new hugetlb pages */ static struct page *alloc_fresh_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct page *page; if (hstate_is_gigantic(h)) page = alloc_gigantic_page(h, gfp_mask, nid, nmask); else page = alloc_buddy_huge_page(h, gfp_mask, nid, nmask, node_alloc_noretry); if (!page) return NULL; if (hstate_is_gigantic(h)) prep_compound_gigantic_page(page, huge_page_order(h)); prep_new_huge_page(h, page, page_to_nid(page)); return page; } /* * Allocates a fresh page to the hugetlb allocator pool in the node interleaved * manner. */ static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, nodemask_t *node_alloc_noretry) { struct page *page; int nr_nodes, node; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { page = alloc_fresh_huge_page(h, gfp_mask, node, nodes_allowed, node_alloc_noretry); if (page) break; } if (!page) return 0; put_page(page); /* free it into the hugepage allocator */ return 1; } /* * Free huge page from pool from next node to free. * Attempt to keep persistent huge pages more or less * balanced over allowed nodes. * Called with hugetlb_lock locked. */ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, bool acct_surplus) { int nr_nodes, node; int ret = 0; for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * If we're returning unused surplus pages, only examine * nodes with surplus pages. */ if ((!acct_surplus || h->surplus_huge_pages_node[node]) && !list_empty(&h->hugepage_freelists[node])) { struct page *page = list_entry(h->hugepage_freelists[node].next, struct page, lru); list_del(&page->lru); h->free_huge_pages--; h->free_huge_pages_node[node]--; if (acct_surplus) { h->surplus_huge_pages--; h->surplus_huge_pages_node[node]--; } update_and_free_page(h, page); ret = 1; break; } } return ret; } /* * Dissolve a given free hugepage into free buddy pages. This function does * nothing for in-use hugepages and non-hugepages. * This function returns values like below: * * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use * (allocated or reserved.) * 0: successfully dissolved free hugepages or the page is not a * hugepage (considered as already dissolved) */ int dissolve_free_huge_page(struct page *page) { int rc = -EBUSY; retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (!PageHuge(page)) return 0; spin_lock(&hugetlb_lock); if (!PageHuge(page)) { rc = 0; goto out; } if (!page_count(page)) { struct page *head = compound_head(page); struct hstate *h = page_hstate(head); int nid = page_to_nid(head); if (h->free_huge_pages - h->resv_huge_pages == 0) goto out; /* * We should make sure that the page is already on the free list * when it is dissolved. */ if (unlikely(!PageHugeFreed(head))) { spin_unlock(&hugetlb_lock); cond_resched(); /* * Theoretically, we should return -EBUSY when we * encounter this race. In fact, we have a chance * to successfully dissolve the page if we do a * retry. Because the race window is quite small. * If we seize this opportunity, it is an optimization * for increasing the success rate of dissolving page. */ goto retry; } /* * Move PageHWPoison flag from head page to the raw error page, * which makes any subpages rather than the error page reusable. */ if (PageHWPoison(head) && page != head) { SetPageHWPoison(page); ClearPageHWPoison(head); } list_del(&head->lru); h->free_huge_pages--; h->free_huge_pages_node[nid]--; h->max_huge_pages--; update_and_free_page(h, head); rc = 0; } out: spin_unlock(&hugetlb_lock); return rc; } /* * Dissolve free hugepages in a given pfn range. Used by memory hotplug to * make specified memory blocks removable from the system. * Note that this will dissolve a free gigantic hugepage completely, if any * part of it lies within the given range. * Also note that if dissolve_free_huge_page() returns with an error, all * free hugepages that were dissolved before that error are lost. */ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct page *page; int rc = 0; if (!hugepages_supported()) return rc; for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) { page = pfn_to_page(pfn); rc = dissolve_free_huge_page(page); if (rc) break; } return rc; } /* * Allocates a fresh surplus page from the page allocator. */ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct page *page = NULL; if (hstate_is_gigantic(h)) return NULL; spin_lock(&hugetlb_lock); if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) goto out_unlock; spin_unlock(&hugetlb_lock); page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL); if (!page) return NULL; spin_lock(&hugetlb_lock); /* * We could have raced with the pool size change. * Double check that and simply deallocate the new page * if we would end up overcommiting the surpluses. Abuse * temporary page to workaround the nasty free_huge_page * codeflow */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { SetPageHugeTemporary(page); spin_unlock(&hugetlb_lock); put_page(page); return NULL; } else { h->surplus_huge_pages++; h->surplus_huge_pages_node[page_to_nid(page)]++; } out_unlock: spin_unlock(&hugetlb_lock); return page; } static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct page *page; if (hstate_is_gigantic(h)) return NULL; page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL); if (!page) return NULL; /* * We do not account these pages as surplus because they are only * temporary and will be released properly on the last reference */ SetPageHugeTemporary(page); return page; } /* * Use the VMA's mpolicy to allocate a huge page from the buddy. */ static struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { struct page *page; struct mempolicy *mpol; gfp_t gfp_mask = htlb_alloc_mask(h); int nid; nodemask_t *nodemask; nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask); mpol_cond_put(mpol); return page; } /* page migration callback function */ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { spin_lock(&hugetlb_lock); if (h->free_huge_pages - h->resv_huge_pages > 0) { struct page *page; page = dequeue_huge_page_nodemask(h, gfp_mask, preferred_nid, nmask); if (page) { spin_unlock(&hugetlb_lock); return page; } } spin_unlock(&hugetlb_lock); return alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask); } /* mempolicy aware migration callback */ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct mempolicy *mpol; nodemask_t *nodemask; struct page *page; gfp_t gfp_mask; int node; gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask); mpol_cond_put(mpol); return page; } /* * Increase the hugetlb pool such that it can accommodate a reservation * of size 'delta'. */ static int gather_surplus_pages(struct hstate *h, int delta) __must_hold(&hugetlb_lock) { struct list_head surplus_list; struct page *page, *tmp; int ret, i; int needed, allocated; bool alloc_ok = true; needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { h->resv_huge_pages += delta; return 0; } allocated = 0; INIT_LIST_HEAD(&surplus_list); ret = -ENOMEM; retry: spin_unlock(&hugetlb_lock); for (i = 0; i < needed; i++) { page = alloc_surplus_huge_page(h, htlb_alloc_mask(h), NUMA_NO_NODE, NULL); if (!page) { alloc_ok = false; break; } list_add(&page->lru, &surplus_list); cond_resched(); } allocated += i; /* * After retaking hugetlb_lock, we need to recalculate 'needed' * because either resv_huge_pages or free_huge_pages may have changed. */ spin_lock(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - (h->free_huge_pages + allocated); if (needed > 0) { if (alloc_ok) goto retry; /* * We were not able to allocate enough pages to * satisfy the entire reservation so we free what * we've allocated so far. */ goto free; } /* * The surplus_list now contains _at_least_ the number of extra pages * needed to accommodate the reservation. Add the appropriate number * of pages to the hugetlb pool and free the extras back to the buddy * allocator. Commit the entire reservation here to prevent another * process from stealing the pages as they are added to the pool but * before they are reserved. */ needed += allocated; h->resv_huge_pages += delta; ret = 0; /* Free the needed pages to the hugetlb pool */ list_for_each_entry_safe(page, tmp, &surplus_list, lru) { if ((--needed) < 0) break; /* * This page is now managed by the hugetlb allocator and has * no users -- drop the buddy allocator's reference. */ put_page_testzero(page); VM_BUG_ON_PAGE(page_count(page), page); enqueue_huge_page(h, page); } free: spin_unlock(&hugetlb_lock); /* Free unnecessary surplus pages to the buddy allocator */ list_for_each_entry_safe(page, tmp, &surplus_list, lru) put_page(page); spin_lock(&hugetlb_lock); return ret; } /* * This routine has two main purposes: * 1) Decrement the reservation count (resv_huge_pages) by the value passed * in unused_resv_pages. This corresponds to the prior adjustments made * to the associated reservation map. * 2) Free any unused surplus pages that may have been allocated to satisfy * the reservation. As many as unused_resv_pages may be freed. * * Called with hugetlb_lock held. However, the lock could be dropped (and * reacquired) during calls to cond_resched_lock. Whenever dropping the lock, * we must make sure nobody else can claim pages we are in the process of * freeing. Do this by ensuring resv_huge_page always is greater than the * number of huge pages we plan to free when dropping the lock. */ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; /* Cannot return gigantic pages currently */ if (hstate_is_gigantic(h)) goto out; /* * Part (or even all) of the reservation could have been backed * by pre-allocated pages. Only free surplus pages. */ nr_pages = min(unused_resv_pages, h->surplus_huge_pages); /* * We want to release as many surplus pages as possible, spread * evenly across all nodes with memory. Iterate across these nodes * until we can no longer free unreserved surplus pages. This occurs * when the nodes with surplus pages have no free pages. * free_pool_huge_page() will balance the freed pages across the * on-line nodes with memory and will handle the hstate accounting. * * Note that we decrement resv_huge_pages as we free the pages. If * we drop the lock, resv_huge_pages will still be sufficiently large * to cover subsequent pages we may free. */ while (nr_pages--) { h->resv_huge_pages--; unused_resv_pages--; if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1)) goto out; cond_resched_lock(&hugetlb_lock); } out: /* Fully uncommit the reservation */ h->resv_huge_pages -= unused_resv_pages; } /* * vma_needs_reservation, vma_commit_reservation and vma_end_reservation * are used by the huge page allocation routines to manage reservations. * * vma_needs_reservation is called to determine if the huge page at addr * within the vma has an associated reservation. If a reservation is * needed, the value 1 is returned. The caller is then responsible for * managing the global reservation and subpool usage counts. After * the huge page has been allocated, vma_commit_reservation is called * to add the page to the reservation map. If the page allocation fails, * the reservation must be ended instead of committed. vma_end_reservation * is called in such cases. * * In the normal case, vma_commit_reservation returns the same value * as the preceding vma_needs_reservation call. The only time this * is not the case is if a reserve map was changed between calls. It * is the responsibility of the caller to notice the difference and * take appropriate action. * * vma_add_reservation is used in error paths where a reservation must * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, enum vma_resv_mode mode) { struct resv_map *resv; pgoff_t idx; long ret; long dummy_out_regions_needed; resv = vma_resv_map(vma); if (!resv) return 1; idx = vma_hugecache_offset(h, vma, addr); switch (mode) { case VMA_NEEDS_RESV: ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed); /* We assume that vma_reservation_* routines always operate on * 1 page, and that adding to resv map a 1 page entry can only * ever require 1 region. */ VM_BUG_ON(dummy_out_regions_needed != 1); break; case VMA_COMMIT_RESV: ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); break; case VMA_END_RESV: region_abort(resv, idx, idx + 1, 1); ret = 0; break; case VMA_ADD_RESV: if (vma->vm_flags & VM_MAYSHARE) { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } else { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } break; default: BUG(); } if (vma->vm_flags & VM_MAYSHARE) return ret; else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && ret >= 0) { /* * In most cases, reserves always exist for private mappings. * However, a file associated with mapping could have been * hole punched or truncated after reserves were consumed. * As subsequent fault on such a range will not use reserves. * Subtle - The reserve map for private mappings has the * opposite meaning than that of shared mappings. If NO * entry is in the reserve map, it means a reservation exists. * If an entry exists in the reserve map, it means the * reservation has already been consumed. As a result, the * return value of this routine is the opposite of the * value returned from reserve map manipulation routines above. */ if (ret) return 0; else return 1; } else return ret < 0 ? ret : 0; } static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV); } static long vma_commit_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV); } static void vma_end_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { (void)__vma_reservation_common(h, vma, addr, VMA_END_RESV); } static long vma_add_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } /* * This routine is called to restore a reservation on error paths. In the * specific error paths, a huge page was allocated (via alloc_huge_page) * and is about to be freed. If a reservation for the page existed, * alloc_huge_page would have consumed the reservation and set PagePrivate * in the newly allocated page. When the page is freed via free_huge_page, * the global reservation count will be incremented if PagePrivate is set. * However, free_huge_page can not adjust the reserve map. Adjust the * reserve map here to be consistent with global reserve count adjustments * to be made by free_huge_page. */ static void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct page *page) { if (unlikely(PagePrivate(page))) { long rc = vma_needs_reservation(h, vma, address); if (unlikely(rc < 0)) { /* * Rare out of memory condition in reserve map * manipulation. Clear PagePrivate so that * global reserve count will not be incremented * by free_huge_page. This will make it appear * as though the reservation for this page was * consumed. This may prevent the task from * faulting in the page at a later time. This * is better than inconsistent global huge page * accounting of reserve counts. */ ClearPagePrivate(page); } else if (rc) { rc = vma_add_reservation(h, vma, address); if (unlikely(rc < 0)) /* * See above comment about rare out of * memory condition. */ ClearPagePrivate(page); } else vma_end_reservation(h, vma, address); } } struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct page *page; long map_chg, map_commit; long gbl_chg; int ret, idx; struct hugetlb_cgroup *h_cg; bool deferred_reserve; idx = hstate_index(h); /* * Examine the region/reserve map to determine if the process * has a reservation for the page to be allocated. A return * code of zero indicates a reservation exists (no change). */ map_chg = gbl_chg = vma_needs_reservation(h, vma, addr); if (map_chg < 0) return ERR_PTR(-ENOMEM); /* * Processes that did not create the mapping will have no * reserves as indicated by the region/reserve map. Check * that the allocation will not exceed the subpool limit. * Allocations for MAP_NORESERVE mappings also need to be * checked against any subpool limit. */ if (map_chg || avoid_reserve) { gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) { vma_end_reservation(h, vma, addr); return ERR_PTR(-ENOSPC); } /* * Even though there was no reservation in the region/reserve * map, there could be reservations associated with the * subpool that can be used. This would be indicated if the * return value of hugepage_subpool_get_pages() is zero. * However, if avoid_reserve is specified we still avoid even * the subpool reservations. */ if (avoid_reserve) gbl_chg = 1; } /* If this allocation is not consuming a reservation, charge it now. */ deferred_reserve = map_chg || avoid_reserve || !vma_resv_map(vma); if (deferred_reserve) { ret = hugetlb_cgroup_charge_cgroup_rsvd( idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_subpool_put; } ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_uncharge_cgroup_reservation; spin_lock(&hugetlb_lock); /* * glb_chg is passed to indicate whether or not a page must be taken * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg); if (!page) { spin_unlock(&hugetlb_lock); page = alloc_buddy_huge_page_with_mpol(h, vma, addr); if (!page) goto out_uncharge_cgroup; spin_lock(&hugetlb_lock); if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { SetPagePrivate(page); h->resv_huge_pages--; } list_add(&page->lru, &h->hugepage_activelist); /* Fall through */ } hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page); /* If allocation is not consuming a reservation, also store the * hugetlb_cgroup pointer on the page. */ if (deferred_reserve) { hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h), h_cg, page); } spin_unlock(&hugetlb_lock); set_page_private(page, (unsigned long)spool); map_commit = vma_commit_reservation(h, vma, addr); if (unlikely(map_chg > map_commit)) { /* * The page was added to the reservation map between * vma_needs_reservation and vma_commit_reservation. * This indicates a race with hugetlb_reserve_pages. * Adjust for the subpool count incremented above AND * in hugetlb_reserve_pages for the same page. Also, * the reservation count added in hugetlb_reserve_pages * no longer applies. */ long rsv_adjust; rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); if (deferred_reserve) hugetlb_cgroup_uncharge_page_rsvd(hstate_index(h), pages_per_huge_page(h), page); } return page; out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); out_uncharge_cgroup_reservation: if (deferred_reserve) hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: if (map_chg || avoid_reserve) hugepage_subpool_put_pages(spool, 1); vma_end_reservation(h, vma, addr); return ERR_PTR(-ENOSPC); } int alloc_bootmem_huge_page(struct hstate *h) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); int __alloc_bootmem_huge_page(struct hstate *h) { struct huge_bootmem_page *m; int nr_nodes, node; for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { void *addr; addr = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, node); if (addr) { /* * Use the beginning of the huge page to store the * huge_bootmem_page struct (until gather_bootmem * puts them into the mem_map). */ m = addr; goto found; } } return 0; found: BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h))); /* Put them into a private list first because mem_map is not up yet */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages); m->hstate = h; return 1; } /* * Put bootmem huge pages into the standard lists after mem_map is up. * Note: This only applies to gigantic (order > MAX_ORDER) pages. */ static void __init gather_bootmem_prealloc(void) { struct huge_bootmem_page *m; list_for_each_entry(m, &huge_boot_pages, list) { struct page *page = virt_to_page(m); struct hstate *h = m->hstate; VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(page_count(page) != 1); prep_compound_gigantic_page(page, huge_page_order(h)); WARN_ON(PageReserved(page)); prep_new_huge_page(h, page, page_to_nid(page)); put_page(page); /* free it into the hugepage allocator */ /* * We need to restore the 'stolen' pages to totalram_pages * in order to fix confusing memory reports from free(1) and * other side-effects, like CommitLimit going negative. */ adjust_managed_page_count(page, pages_per_huge_page(h)); cond_resched(); } } static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long i; nodemask_t *node_alloc_noretry; if (!hstate_is_gigantic(h)) { /* * Bit mask controlling how hard we retry per-node allocations. * Ignore errors as lower level routines can deal with * node_alloc_noretry == NULL. If this kmalloc fails at boot * time, we are likely in bigger trouble. */ node_alloc_noretry = kmalloc(sizeof(*node_alloc_noretry), GFP_KERNEL); } else { /* allocations done at boot time */ node_alloc_noretry = NULL; } /* bit mask controlling how hard we retry per-node allocations */ if (node_alloc_noretry) nodes_clear(*node_alloc_noretry); for (i = 0; i < h->max_huge_pages; ++i) { if (hstate_is_gigantic(h)) { if (hugetlb_cma_size) { pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); goto free; } if (!alloc_bootmem_huge_page(h)) break; } else if (!alloc_pool_huge_page(h, &node_states[N_MEMORY], node_alloc_noretry)) break; cond_resched(); } if (i < h->max_huge_pages) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %lu of page size %s failed. Only allocated %lu hugepages.\n", h->max_huge_pages, buf, i); h->max_huge_pages = i; } free: kfree(node_alloc_noretry); } static void __init hugetlb_init_hstates(void) { struct hstate *h; for_each_hstate(h) { if (minimum_order > huge_page_order(h)) minimum_order = huge_page_order(h); /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); } VM_BUG_ON(minimum_order == UINT_MAX); } static void __init report_hugepages(void) { struct hstate *h; for_each_hstate(h) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n", buf, h->free_huge_pages); } } #ifdef CONFIG_HIGHMEM static void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { int i; if (hstate_is_gigantic(h)) return; for_each_node_mask(i, *nodes_allowed) { struct page *page, *next; struct list_head *freel = &h->hugepage_freelists[i]; list_for_each_entry_safe(page, next, freel, lru) { if (count >= h->nr_huge_pages) return; if (PageHighMem(page)) continue; list_del(&page->lru); update_and_free_page(h, page); h->free_huge_pages--; h->free_huge_pages_node[page_to_nid(page)]--; } } } #else static inline void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { } #endif /* * Increment or decrement surplus_huge_pages. Keep node-specific counters * balanced by operating on them in a round-robin fashion. * Returns 1 if an adjustment was made. */ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, int delta) { int nr_nodes, node; VM_BUG_ON(delta != -1 && delta != 1); if (delta < 0) { for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node]) goto found; } } else { for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node] < h->nr_huge_pages_node[node]) goto found; } } return 0; found: h->surplus_huge_pages += delta; h->surplus_huge_pages_node[node] += delta; return 1; } #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { unsigned long min_count, ret; NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); /* * Bit mask controlling how hard we retry per-node allocations. * If we can not allocate the bit mask, do not attempt to allocate * the requested huge pages. */ if (node_alloc_noretry) nodes_clear(*node_alloc_noretry); else return -ENOMEM; spin_lock(&hugetlb_lock); /* * Check for a node specific request. * Changing node specific huge page count may require a corresponding * change to the global count. In any case, the passed node mask * (nodes_allowed) will restrict alloc/free to the specified node. */ if (nid != NUMA_NO_NODE) { unsigned long old_count = count; count += h->nr_huge_pages - h->nr_huge_pages_node[nid]; /* * User may have specified a large count value which caused the * above calculation to overflow. In this case, they wanted * to allocate as many huge pages as possible. Set count to * largest possible value to align with their intention. */ if (count < old_count) count = ULONG_MAX; } /* * Gigantic pages runtime allocation depend on the capability for large * page range allocation. * If the system does not provide this feature, return an error when * the user tries to allocate gigantic pages but let the user free the * boottime allocated gigantic pages. */ if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { if (count > persistent_huge_pages(h)) { spin_unlock(&hugetlb_lock); NODEMASK_FREE(node_alloc_noretry); return -EINVAL; } /* Fall through to decrease pool */ } /* * Increase the pool size * First take pages out of surplus state. Then make up the * remaining difference by allocating fresh huge pages. * * We might race with alloc_surplus_huge_page() here and be unable * to convert a surplus huge page to a normal huge page. That is * not critical, though, it just means the overall size of the * pool might be one hugepage larger than it needs to be, but * within all the constraints specified by the sysctls. */ while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, -1)) break; } while (count > persistent_huge_pages(h)) { /* * If this allocation races such that we no longer need the * page, free_huge_page will handle it by freeing the page * and reducing the surplus. */ spin_unlock(&hugetlb_lock); /* yield cpu to avoid soft lockup */ cond_resched(); ret = alloc_pool_huge_page(h, nodes_allowed, node_alloc_noretry); spin_lock(&hugetlb_lock); if (!ret) goto out; /* Bail for signals. Probably ctrl-c from user */ if (signal_pending(current)) goto out; } /* * Decrease the pool size * First return free pages to the buddy allocator (being careful * to keep enough around to satisfy reservations). Then place * pages into surplus state as needed so the pool will shrink * to the desired size as pages become free. * * By placing pages into the surplus state independent of the * overcommit value, we are allowing the surplus pool size to * exceed overcommit. There are few sane options here. Since * alloc_surplus_huge_page() is checking the global counter, * though, we'll note that we're not allowed to exceed surplus * and won't grow the pool anywhere else. Not until one of the * sysctls are changed, or the surplus pages go out of use. */ min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages; min_count = max(count, min_count); try_to_free_low(h, min_count, nodes_allowed); while (min_count < persistent_huge_pages(h)) { if (!free_pool_huge_page(h, nodes_allowed, 0)) break; cond_resched_lock(&hugetlb_lock); } while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) break; } out: h->max_huge_pages = persistent_huge_pages(h); spin_unlock(&hugetlb_lock); NODEMASK_FREE(node_alloc_noretry); return 0; } #define HSTATE_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) #define HSTATE_ATTR(_name) \ static struct kobj_attribute _name##_attr = \ __ATTR(_name, 0644, _name##_show, _name##_store) static struct kobject *hugepages_kobj; static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp); static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp) { int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (hstate_kobjs[i] == kobj) { if (nidp) *nidp = NUMA_NO_NODE; return &hstates[i]; } return kobj_to_node_hstate(kobj, nidp); } static ssize_t nr_hugepages_show_common(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long nr_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) nr_huge_pages = h->nr_huge_pages; else nr_huge_pages = h->nr_huge_pages_node[nid]; return sprintf(buf, "%lu\n", nr_huge_pages); } static ssize_t __nr_hugepages_store_common(bool obey_mempolicy, struct hstate *h, int nid, unsigned long count, size_t len) { int err; nodemask_t nodes_allowed, *n_mask; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return -EINVAL; if (nid == NUMA_NO_NODE) { /* * global hstate attribute */ if (!(obey_mempolicy && init_nodemask_of_mempolicy(&nodes_allowed))) n_mask = &node_states[N_MEMORY]; else n_mask = &nodes_allowed; } else { /* * Node specific request. count adjustment happens in * set_max_huge_pages() after acquiring hugetlb_lock. */ init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } err = set_max_huge_pages(h, count, nid, n_mask); return err ? err : len; } static ssize_t nr_hugepages_store_common(bool obey_mempolicy, struct kobject *kobj, const char *buf, size_t len) { struct hstate *h; unsigned long count; int nid; int err; err = kstrtoul(buf, 10, &count); if (err) return err; h = kobj_to_hstate(kobj, &nid); return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len); } static ssize_t nr_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(false, kobj, buf, len); } HSTATE_ATTR(nr_hugepages); #ifdef CONFIG_NUMA /* * hstate attribute for optionally mempolicy-based constraint on persistent * huge page alloc/free. */ static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(true, kobj, buf, len); } HSTATE_ATTR(nr_hugepages_mempolicy); #endif static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages); } static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long input; struct hstate *h = kobj_to_hstate(kobj, NULL); if (hstate_is_gigantic(h)) return -EINVAL; err = kstrtoul(buf, 10, &input); if (err) return err; spin_lock(&hugetlb_lock); h->nr_overcommit_huge_pages = input; spin_unlock(&hugetlb_lock); return count; } HSTATE_ATTR(nr_overcommit_hugepages); static ssize_t free_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long free_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) free_huge_pages = h->free_huge_pages; else free_huge_pages = h->free_huge_pages_node[nid]; return sprintf(buf, "%lu\n", free_huge_pages); } HSTATE_ATTR_RO(free_hugepages); static ssize_t resv_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sprintf(buf, "%lu\n", h->resv_huge_pages); } HSTATE_ATTR_RO(resv_hugepages); static ssize_t surplus_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long surplus_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) surplus_huge_pages = h->surplus_huge_pages; else surplus_huge_pages = h->surplus_huge_pages_node[nid]; return sprintf(buf, "%lu\n", surplus_huge_pages); } HSTATE_ATTR_RO(surplus_hugepages); static struct attribute *hstate_attrs[] = { &nr_hugepages_attr.attr, &nr_overcommit_hugepages_attr.attr, &free_hugepages_attr.attr, &resv_hugepages_attr.attr, &surplus_hugepages_attr.attr, #ifdef CONFIG_NUMA &nr_hugepages_mempolicy_attr.attr, #endif NULL, }; static const struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct kobject **hstate_kobjs, const struct attribute_group *hstate_attr_group) { int retval; int hi = hstate_index(h); hstate_kobjs[hi] = kobject_create_and_add(h->name, parent); if (!hstate_kobjs[hi]) return -ENOMEM; retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); if (retval) { kobject_put(hstate_kobjs[hi]); hstate_kobjs[hi] = NULL; } return retval; } static void __init hugetlb_sysfs_init(void) { struct hstate *h; int err; hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); if (!hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, hstate_kobjs, &hstate_attr_group); if (err) pr_err("HugeTLB: Unable to add hstate %s", h->name); } } #ifdef CONFIG_NUMA /* * node_hstate/s - associate per node hstate attributes, via their kobjects, * with node devices in node_devices[] using a parallel array. The array * index of a node device or _hstate == node id. * This is here to avoid any static dependency of the node device driver, in * the base kernel, on the hugetlb module. */ struct node_hstate { struct kobject *hugepages_kobj; struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; }; static struct node_hstate node_hstates[MAX_NUMNODES]; /* * A subset of global hstate attributes for node devices */ static struct attribute *per_node_hstate_attrs[] = { &nr_hugepages_attr.attr, &free_hugepages_attr.attr, &surplus_hugepages_attr.attr, NULL, }; static const struct attribute_group per_node_hstate_attr_group = { .attrs = per_node_hstate_attrs, }; /* * kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj. * Returns node id via non-NULL nidp. */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { int nid; for (nid = 0; nid < nr_node_ids; nid++) { struct node_hstate *nhs = &node_hstates[nid]; int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (nhs->hstate_kobjs[i] == kobj) { if (nidp) *nidp = nid; return &hstates[i]; } } BUG(); return NULL; } /* * Unregister hstate attributes from a single node device. * No-op if no hstate attributes attached. */ static void hugetlb_unregister_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; if (!nhs->hugepages_kobj) return; /* no hstate attributes */ for_each_hstate(h) { int idx = hstate_index(h); if (nhs->hstate_kobjs[idx]) { kobject_put(nhs->hstate_kobjs[idx]); nhs->hstate_kobjs[idx] = NULL; } } kobject_put(nhs->hugepages_kobj); nhs->hugepages_kobj = NULL; } /* * Register hstate attributes for a single node device. * No-op if attributes already registered. */ static void hugetlb_register_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; int err; if (nhs->hugepages_kobj) return; /* already allocated */ nhs->hugepages_kobj = kobject_create_and_add("hugepages", &node->dev.kobj); if (!nhs->hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj, nhs->hstate_kobjs, &per_node_hstate_attr_group); if (err) { pr_err("HugeTLB: Unable to add hstate %s for node %d\n", h->name, node->dev.id); hugetlb_unregister_node(node); break; } } } /* * hugetlb init time: register hstate attributes for all registered node * devices of nodes that have memory. All on-line nodes should have * registered their associated device by this time. */ static void __init hugetlb_register_all_nodes(void) { int nid; for_each_node_state(nid, N_MEMORY) { struct node *node = node_devices[nid]; if (node->dev.id == nid) hugetlb_register_node(node); } /* * Let the node device driver know we're here so it can * [un]register hstate attributes on node hotplug. */ register_hugetlbfs_with_node(hugetlb_register_node, hugetlb_unregister_node); } #else /* !CONFIG_NUMA */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { BUG(); if (nidp) *nidp = -1; return NULL; } static void hugetlb_register_all_nodes(void) { } #endif static int __init hugetlb_init(void) { int i; if (!hugepages_supported()) { if (hugetlb_max_hstate || default_hstate_max_huge_pages) pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n"); return 0; } /* * Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists. Some * architectures depend on setup being done here. */ hugetlb_add_hstate(HUGETLB_PAGE_ORDER); if (!parsed_default_hugepagesz) { /* * If we did not parse a default huge page size, set * default_hstate_idx to HPAGE_SIZE hstate. And, if the * number of huge pages for this default size was implicitly * specified, set that here as well. * Note that the implicit setting will overwrite an explicit * setting. A warning will be printed in this case. */ default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE)); if (default_hstate_max_huge_pages) { if (default_hstate.max_huge_pages) { char buf[32]; string_get_size(huge_page_size(&default_hstate), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n", default_hstate.max_huge_pages, buf); pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n", default_hstate_max_huge_pages); } default_hstate.max_huge_pages = default_hstate_max_huge_pages; } } hugetlb_cma_check(); hugetlb_init_hstates(); gather_bootmem_prealloc(); report_hugepages(); hugetlb_sysfs_init(); hugetlb_register_all_nodes(); hugetlb_cgroup_file_init(); #ifdef CONFIG_SMP num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); #else num_fault_mutexes = 1; #endif hugetlb_fault_mutex_table = kmalloc_array(num_fault_mutexes, sizeof(struct mutex), GFP_KERNEL); BUG_ON(!hugetlb_fault_mutex_table); for (i = 0; i < num_fault_mutexes; i++) mutex_init(&hugetlb_fault_mutex_table[i]); return 0; } subsys_initcall(hugetlb_init); /* Overwritten by architectures with more huge page sizes */ bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size) { return size == HPAGE_SIZE; } void __init hugetlb_add_hstate(unsigned int order) { struct hstate *h; unsigned long i; if (size_to_hstate(PAGE_SIZE << order)) { return; } BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order == 0); h = &hstates[hugetlb_max_hstate++]; h->order = order; h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1); h->nr_huge_pages = 0; h->free_huge_pages = 0; for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); INIT_LIST_HEAD(&h->hugepage_activelist); h->next_nid_to_alloc = first_memory_node; h->next_nid_to_free = first_memory_node; snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/1024); parsed_hstate = h; } /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz * specification. If not, ignore the hugepages value. hugepages can also * be the first huge page command line option in which case it implicitly * specifies the number of huge pages for the default size. */ static int __init hugepages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; return 0; } /* * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter * yet, so this hugepages= parameter goes to the "default hstate". * Otherwise, it goes with the previously parsed hugepagesz or * default_hugepagesz. */ else if (!hugetlb_max_hstate) mhp = &default_hstate_max_huge_pages; else mhp = &parsed_hstate->max_huge_pages; if (mhp == last_mhp) { pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s); return 0; } if (sscanf(s, "%lu", mhp) <= 0) *mhp = 0; /* * Global state is always initialized later in hugetlb_init. * But we need to allocate >= MAX_ORDER hstates here early to still * use the bootmem allocator. */ if (hugetlb_max_hstate && parsed_hstate->order >= MAX_ORDER) hugetlb_hstate_alloc_pages(parsed_hstate); last_mhp = mhp; return 1; } __setup("hugepages=", hugepages_setup); /* * hugepagesz command line processing * A specific huge page size can only be specified once with hugepagesz. * hugepagesz is followed by hugepages on the command line. The global * variable 'parsed_valid_hugepagesz' is used to determine if prior * hugepagesz argument was valid. */ static int __init hugepagesz_setup(char *s) { unsigned long size; struct hstate *h; parsed_valid_hugepagesz = false; size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported hugepagesz=%s\n", s); return 0; } h = size_to_hstate(size); if (h) { /* * hstate for this size already exists. This is normally * an error, but is allowed if the existing hstate is the * default hstate. More specifically, it is only allowed if * the number of huge pages for the default hstate was not * previously specified. */ if (!parsed_default_hugepagesz || h != &default_hstate || default_hstate.max_huge_pages) { pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s); return 0; } /* * No need to call hugetlb_add_hstate() as hstate already * exists. But, do set parsed_hstate so that a following * hugepages= parameter will be applied to this hstate. */ parsed_hstate = h; parsed_valid_hugepagesz = true; return 1; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; return 1; } __setup("hugepagesz=", hugepagesz_setup); /* * default_hugepagesz command line input * Only one instance of default_hugepagesz allowed on command line. */ static int __init default_hugepagesz_setup(char *s) { unsigned long size; parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); return 0; } size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s); return 0; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; parsed_default_hugepagesz = true; default_hstate_idx = hstate_index(size_to_hstate(size)); /* * The number of default huge pages (for this size) could have been * specified as the first hugetlb parameter: hugepages=X. If so, * then default_hstate_max_huge_pages is set. If the default huge * page size is gigantic (>= MAX_ORDER), then the pages must be * allocated here from bootmem allocator. */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; if (hstate_is_gigantic(&default_hstate)) hugetlb_hstate_alloc_pages(&default_hstate); default_hstate_max_huge_pages = 0; } return 1; } __setup("default_hugepagesz=", default_hugepagesz_setup); static unsigned int allowed_mems_nr(struct hstate *h) { int node; unsigned int nr = 0; nodemask_t *mpol_allowed; unsigned int *array = h->free_huge_pages_node; gfp_t gfp_mask = htlb_alloc_mask(h); mpol_allowed = policy_nodemask_current(gfp_mask); for_each_node_mask(node, cpuset_current_mems_allowed) { if (!mpol_allowed || (mpol_allowed && node_isset(node, *mpol_allowed))) nr += array[node]; } return nr; } #ifdef CONFIG_SYSCTL static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos, unsigned long *out) { struct ctl_table dup_table; /* * In order to avoid races with __do_proc_doulongvec_minmax(), we * can duplicate the @table and alter the duplicate of it. */ dup_table = *table; dup_table.data = out; return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos); } static int hugetlb_sysctl_handler_common(bool obey_mempolicy, struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp = h->max_huge_pages; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) ret = __nr_hugepages_store_common(obey_mempolicy, h, NUMA_NO_NODE, tmp, *length); out: return ret; } int hugetlb_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(false, table, write, buffer, length, ppos); } #ifdef CONFIG_NUMA int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(true, table, write, buffer, length, ppos); } #endif /* CONFIG_NUMA */ int hugetlb_overcommit_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; tmp = h->nr_overcommit_huge_pages; if (write && hstate_is_gigantic(h)) return -EINVAL; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) { spin_lock(&hugetlb_lock); h->nr_overcommit_huge_pages = tmp; spin_unlock(&hugetlb_lock); } out: return ret; } #endif /* CONFIG_SYSCTL */ void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h; unsigned long total = 0; if (!hugepages_supported()) return; for_each_hstate(h) { unsigned long count = h->nr_huge_pages; total += (PAGE_SIZE << huge_page_order(h)) * count; if (h == &default_hstate) seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" "HugePages_Rsvd: %5lu\n" "HugePages_Surp: %5lu\n" "Hugepagesize: %8lu kB\n", count, h->free_huge_pages, h->resv_huge_pages, h->surplus_huge_pages, (PAGE_SIZE << huge_page_order(h)) / 1024); } seq_printf(m, "Hugetlb: %8lu kB\n", total / 1024); } int hugetlb_report_node_meminfo(char *buf, int len, int nid) { struct hstate *h = &default_hstate; if (!hugepages_supported()) return 0; return sysfs_emit_at(buf, len, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" "Node %d HugePages_Surp: %5u\n", nid, h->nr_huge_pages_node[nid], nid, h->free_huge_pages_node[nid], nid, h->surplus_huge_pages_node[nid]); } void hugetlb_show_meminfo(void) { struct hstate *h; int nid; if (!hugepages_supported()) return; for_each_node_state(nid, N_MEMORY) for_each_hstate(h) pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", nid, h->nr_huge_pages_node[nid], h->free_huge_pages_node[nid], h->surplus_huge_pages_node[nid], 1UL << (huge_page_order(h) + PAGE_SHIFT - 10)); } void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm) { seq_printf(m, "HugetlbPages:\t%8lu kB\n", atomic_long_read(&mm->hugetlb_usage) << (PAGE_SHIFT - 10)); } /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { struct hstate *h; unsigned long nr_total_pages = 0; for_each_hstate(h) nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h); return nr_total_pages; } static int hugetlb_acct_memory(struct hstate *h, long delta) { int ret = -ENOMEM; spin_lock(&hugetlb_lock); /* * When cpuset is configured, it breaks the strict hugetlb page * reservation as the accounting is done on a global variable. Such * reservation is completely rubbish in the presence of cpuset because * the reservation is not checked against page availability for the * current cpuset. Application can still potentially OOM'ed by kernel * with lack of free htlb page in cpuset that the task is in. * Attempt to enforce strict accounting with cpuset is almost * impossible (or too ugly) because cpuset is too fluid that * task or memory node can be dynamically moved between cpusets. * * The change of semantics for shared hugetlb mapping with cpuset is * undesirable. However, in order to preserve some of the semantics, * we fall back to check against current free page availability as * a best attempt and hopefully to minimize the impact of changing * semantics that cpuset has. * * Apart from cpuset, we also have memory policy mechanism that * also determines from which node the kernel will allocate memory * in a NUMA system. So similar to cpuset, we also should consider * the memory policy of the current task. Similar to the description * above. */ if (delta > 0) { if (gather_surplus_pages(h, delta) < 0) goto out; if (delta > allowed_mems_nr(h)) { return_unused_surplus_pages(h, delta); goto out; } } ret = 0; if (delta < 0) return_unused_surplus_pages(h, (unsigned long) -delta); out: spin_unlock(&hugetlb_lock); return ret; } static void hugetlb_vm_op_open(struct vm_area_struct *vma) { struct resv_map *resv = vma_resv_map(vma); /* * This new VMA should share its siblings reservation map if present. * The VMA will only ever have a valid reservation map pointer where * it is being copied for another still existing VMA. As that VMA * has a reference to the reservation map it cannot disappear until * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_dup_hugetlb_cgroup_uncharge_info(resv); kref_get(&resv->refs); } } static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); struct resv_map *resv = vma_resv_map(vma); struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve, start, end; long gbl_reserve; if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return; start = vma_hugecache_offset(h, vma, vma->vm_start); end = vma_hugecache_offset(h, vma, vma->vm_end); reserve = (end - start) - region_count(resv, start, end); hugetlb_cgroup_uncharge_counter(resv, start, end); if (reserve) { /* * Decrement reserve counts. The global reserve count may be * adjusted if the subpool has a minimum size. */ gbl_reserve = hugepage_subpool_put_pages(spool, reserve); hugetlb_acct_memory(h, -gbl_reserve); } kref_put(&resv->refs, resv_map_release); } static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; return 0; } void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) { /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. * This function is called in the middle of a VMA split operation, with * MM, VMA and rmap all write-locked to prevent concurrent page table * walks (except hardware and gup_fast()). */ mmap_assert_write_locked(vma->vm_mm); i_mmap_assert_write_locked(vma->vm_file->f_mapping); if (addr & ~PUD_MASK) { unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; if (floor >= vma->vm_start && ceil <= vma->vm_end) { /* * Locking: * Use take_locks=false here. * The file rmap lock is already held. * The hugetlb VMA lock can't be taken when we already * hold the file rmap lock, and we don't need it because * its purpose is to synchronize against concurrent page * table walks, which are not possible thanks to the * locks held by our caller. */ hugetlb_unshare_pmds(vma, floor, ceil, /* take_locks = */ false); } } } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) { struct hstate *hstate = hstate_vma(vma); return 1UL << huge_page_shift(hstate); } /* * We cannot handle pagefaults against hugetlb pages at all. They cause * handle_mm_fault() to try to instantiate regular-sized pages in the * hugegpage VMA. do_page_fault() is supposed to trap this, so BUG is we get * this far. */ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) { BUG(); return 0; } /* * When a new function is introduced to vm_operations_struct and added * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops. * This is because under System V memory model, mappings created via * shmget/shmat with "huge page" specified are backed by hugetlbfs files, * their original vm_ops are overwritten with shm_vm_ops. */ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, .split = hugetlb_vm_op_split, .pagesize = hugetlb_vm_op_pagesize, }; static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, int writable) { pte_t entry; if (writable) { entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, vma->vm_page_prot))); } else { entry = huge_pte_wrprotect(mk_huge_pte(page, vma->vm_page_prot)); } entry = pte_mkyoung(entry); entry = pte_mkhuge(entry); entry = arch_make_huge_pte(entry, vma, page, writable); return entry; } static void set_huge_ptep_writable(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t entry; entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(ptep))); if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) update_mmu_cache(vma, address, ptep); } bool is_hugetlb_entry_migration(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_migration_entry(swp)) return true; else return false; } static bool is_hugetlb_entry_hwpoisoned(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_hwpoison_entry(swp)) return true; else return false; } int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma) { pte_t *src_pte, *dst_pte, entry, dst_entry; struct page *ptepage; unsigned long addr; int cow; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct address_space *mapping = vma->vm_file->f_mapping; struct mmu_notifier_range range; int ret = 0; cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; if (cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src, vma->vm_start, vma->vm_end); mmu_notifier_invalidate_range_start(&range); } else { /* * For shared mappings i_mmap_rwsem must be held to call * huge_pte_alloc, otherwise the returned ptep could go * away if part of a shared pmd and another thread calls * huge_pmd_unshare. */ i_mmap_lock_read(mapping); } for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = huge_pte_offset(src, addr, sz); if (!src_pte) continue; dst_pte = huge_pte_alloc(dst, addr, sz); if (!dst_pte) { ret = -ENOMEM; break; } /* * If the pagetables are shared don't copy or take references. * dst_pte == src_pte is the common case of src/dest sharing. * * However, src could have 'unshared' and dst shares with * another vma. If dst_pte !none, this implies sharing. * Check here before taking page table lock, and once again * after taking the lock below. */ dst_entry = huge_ptep_get(dst_pte); if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) continue; dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); dst_entry = huge_ptep_get(dst_pte); if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) { /* * Skip if src entry none. Also, skip in the * unlikely case dst entry !none as this implies * sharing with another vma. */ ; } else if (unlikely(is_hugetlb_entry_migration(entry) || is_hugetlb_entry_hwpoisoned(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); if (is_write_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. */ make_migration_entry_read(&swp_entry); entry = swp_entry_to_pte(swp_entry); set_huge_swap_pte_at(src, addr, src_pte, entry, sz); } set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz); } else { if (cow) { /* * No need to notify as we are downgrading page * table protection not changing it to point * to a new page. * * See Documentation/vm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); } entry = huge_ptep_get(src_pte); ptepage = pte_page(entry); get_page(ptepage); page_dup_rmap(ptepage, true); set_huge_pte_at(dst, addr, dst_pte, entry); hugetlb_count_add(pages_per_huge_page(h), dst); } spin_unlock(src_ptl); spin_unlock(dst_ptl); } if (cow) mmu_notifier_invalidate_range_end(&range); else i_mmap_unlock_read(mapping); return ret; } void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) { struct mm_struct *mm = vma->vm_mm; unsigned long address; pte_t *ptep; pte_t pte; spinlock_t *ptl; struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mmu_notifier_range range; bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); /* * This is a hugetlb vma, all the pte entries should point * to huge page. */ tlb_change_page_size(tlb, sz); tlb_start_vma(tlb, vma); /* * If sharing possible, alert mmu notifiers of worst case. */ mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); mmu_notifier_invalidate_range_start(&range); address = start; for (; address < end; address += sz) { ptep = huge_pte_offset(mm, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, &address, ptep)) { spin_unlock(ptl); tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); force_flush = true; continue; } pte = huge_ptep_get(ptep); if (huge_pte_none(pte)) { spin_unlock(ptl); continue; } /* * Migrating hugepage or HWPoisoned hugepage is already * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; } page = pte_page(pte); /* * If a reference page is supplied, it is because a specific * page is being unmapped, not a range. Ensure the page we * are about to unmap is the actual page of interest. */ if (ref_page) { if (page != ref_page) { spin_unlock(ptl); continue; } /* * Mark the VMA as having unmapped its page so that * future faults in this VMA will fail rather than * looking like data was lost */ set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED); } pte = huge_ptep_get_and_clear(mm, address, ptep); tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) set_page_dirty(page); hugetlb_count_sub(pages_per_huge_page(h), mm); page_remove_rmap(page, true); spin_unlock(ptl); tlb_remove_page_size(tlb, page, huge_page_size(h)); /* * Bail out after unmapping reference page if supplied */ if (ref_page) break; } mmu_notifier_invalidate_range_end(&range); tlb_end_vma(tlb, vma); /* * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We * could defer the flush until now, since by holding i_mmap_rwsem we * guaranteed that the last refernece would not be dropped. But we must * do the flushing before we return, as otherwise i_mmap_rwsem will be * dropped and the last reference to the shared PMDs page might be * dropped as well. * * In theory we could defer the freeing of the PMD pages as well, but * huge_pmd_unshare() relies on the exact page_count for the PMD page to * detect sharing, so we cannot defer the release of the page either. * Instead, do flush now. */ if (force_flush) tlb_flush_mmu_tlbonly(tlb); } void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) { __unmap_hugepage_range(tlb, vma, start, end, ref_page); /* * Clear this flag so that x86's huge_pmd_share page_table_shareable * test will fail on a vma being torn down, and not grab a page table * on its way out. We're lucky that the flag has such an appropriate * name, and can in fact be safely cleared here. We could clear it * before the __unmap_hugepage_range above, but all that's necessary * is to clear it before releasing the i_mmap_rwsem. This works * because in the context this is called, the VMA is about to be * destroyed and the i_mmap_rwsem is held. */ vma->vm_flags &= ~VM_MAYSHARE; } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) { struct mm_struct *mm; struct mmu_gather tlb; unsigned long tlb_start = start; unsigned long tlb_end = end; /* * If shared PMDs were possibly used within this vma range, adjust * start/end for worst case tlb flushing. * Note that we can not be sure if PMDs are shared until we try to * unmap pages. However, we want to make sure TLB flushing covers * the largest possible range. */ adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end); mm = vma->vm_mm; tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end); __unmap_hugepage_range(&tlb, vma, start, end, ref_page); tlb_finish_mmu(&tlb, tlb_start, tlb_end); } /* * This is called when the original mapper is failing to COW a MAP_PRIVATE * mappping it owns the reserve page for. The intention is to unmap the page * from other VMAs and let the children be SIGKILLed if they are faulting the * same region. */ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page, unsigned long address) { struct hstate *h = hstate_vma(vma); struct vm_area_struct *iter_vma; struct address_space *mapping; pgoff_t pgoff; /* * vm_pgoff is in PAGE_SIZE units, hence the different calculation * from page cache lookup which is in HPAGE_SIZE units. */ address = address & huge_page_mask(h); pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; mapping = vma->vm_file->f_mapping; /* * Take the mapping lock for the duration of the table walk. As * this mapping should be shared between all the VMAs, * __unmap_hugepage_range() is called as the lock is already held */ i_mmap_lock_write(mapping); vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) continue; /* * Shared VMAs have their own reserves and do not affect * MAP_PRIVATE accounting but it is possible that a shared * VMA is using the same page so check and skip such VMAs. */ if (iter_vma->vm_flags & VM_MAYSHARE) continue; /* * Unmap the page from other VMAs without their own reserves. * They get marked to be SIGKILLed if they fault in these * areas. This is because a future no-page fault on this VMA * could insert a zeroed page instead of the data existing * from the time of fork. This would look like data corruption */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) unmap_hugepage_range(iter_vma, address, address + huge_page_size(h), page); } i_mmap_unlock_write(mapping); } /* * Hugetlb_cow() should be called with page lock of the original hugepage held. * Called with hugetlb_instantiation_mutex held and pte_page locked so we * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, struct page *pagecache_page, spinlock_t *ptl) { pte_t pte; struct hstate *h = hstate_vma(vma); struct page *old_page, *new_page; int outside_reserve = 0; vm_fault_t ret = 0; unsigned long haddr = address & huge_page_mask(h); struct mmu_notifier_range range; pte = huge_ptep_get(ptep); old_page = pte_page(pte); retry_avoidcopy: /* If no-one else is actually using this page, avoid the copy * and just make the page writable */ if (page_mapcount(old_page) == 1 && PageAnon(old_page)) { page_move_anon_rmap(old_page, vma); set_huge_ptep_writable(vma, haddr, ptep); return 0; } /* * If the process that created a MAP_PRIVATE mapping is about to * perform a COW due to a shared page count, attempt to satisfy * the allocation without using the existing reserves. The pagecache * page is used to determine if the reserve at this address was * consumed or not. If reserves were used, a partial faulted mapping * at the time of fork() could consume its reserves on COW instead * of the full address range. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && old_page != pagecache_page) outside_reserve = 1; get_page(old_page); /* * Drop page table lock as buddy allocator may be called. It will * be acquired again before returning to the caller, as expected. */ spin_unlock(ptl); new_page = alloc_huge_page(vma, haddr, outside_reserve); if (IS_ERR(new_page)) { /* * If a process owning a MAP_PRIVATE mapping fails to COW, * it is due to references held by a child and an insufficient * huge page pool. To guarantee the original mappers * reliability, unmap the page from child processes. The child * may get SIGKILLed if it later faults. */ if (outside_reserve) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx; u32 hash; put_page(old_page); BUG_ON(huge_pte_none(pte)); /* * Drop hugetlb_fault_mutex and i_mmap_rwsem before * unmapping. unmapping needs to hold i_mmap_rwsem * in write mode. Dropping i_mmap_rwsem in read mode * here is OK as COW mappings do not interact with * PMD sharing. * * Reacquire both after unmap operation. */ idx = vma_hugecache_offset(h, vma, haddr); hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); unmap_ref_private(mm, vma, old_page, haddr); i_mmap_lock_read(mapping); mutex_lock(&hugetlb_fault_mutex_table[hash]); spin_lock(ptl); ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) goto retry_avoidcopy; /* * race occurs while re-acquiring page table * lock, and our job is done. */ return 0; } ret = vmf_error(PTR_ERR(new_page)); goto out_release_old; } /* * When the original hugepage is shared one, it does not have * anon_vma prepared. */ if (unlikely(anon_vma_prepare(vma))) { ret = VM_FAULT_OOM; goto out_release_all; } copy_user_huge_page(new_page, old_page, address, vma, pages_per_huge_page(h)); __SetPageUptodate(new_page); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, haddr, haddr + huge_page_size(h)); mmu_notifier_invalidate_range_start(&range); /* * Retake the page table lock to check for racing updates * before the page tables are altered */ spin_lock(ptl); ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { ClearPagePrivate(new_page); /* Break COW */ huge_ptep_clear_flush(vma, haddr, ptep); mmu_notifier_invalidate_range(mm, range.start, range.end); set_huge_pte_at(mm, haddr, ptep, make_huge_pte(vma, new_page, 1)); page_remove_rmap(old_page, true); hugepage_add_new_anon_rmap(new_page, vma, haddr); set_page_huge_active(new_page); /* Make the old page be freed below */ new_page = old_page; } spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: restore_reserve_on_error(h, vma, haddr, new_page); put_page(new_page); out_release_old: put_page(old_page); spin_lock(ptl); /* Caller expects lock to be held */ return ret; } /* Return the pagecache page at a given address within a VMA */ static struct page *hugetlbfs_pagecache_page(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping; pgoff_t idx; mapping = vma->vm_file->f_mapping; idx = vma_hugecache_offset(h, vma, address); return find_lock_page(mapping, idx); } /* * Return whether there is a pagecache page to back given address within VMA. * Caller follow_hugetlb_page() holds page_table_lock so we cannot lock_page. */ static bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping; pgoff_t idx; struct page *page; mapping = vma->vm_file->f_mapping; idx = vma_hugecache_offset(h, vma, address); page = find_get_page(mapping, idx); if (page) put_page(page); return page != NULL; } int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx) { struct inode *inode = mapping->host; struct hstate *h = hstate_inode(inode); int err = add_to_page_cache(page, mapping, idx, GFP_KERNEL); if (err) return err; ClearPagePrivate(page); /* * set page dirty so that it will not be removed from cache/file * by non-hugetlbfs specific code paths. */ set_page_dirty(page); spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); return 0; } static vm_fault_t hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping, pgoff_t idx, unsigned long address, pte_t *ptep, unsigned int flags) { struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; int anon_rmap = 0; unsigned long size; struct page *page; pte_t new_pte; spinlock_t *ptl; unsigned long haddr = address & huge_page_mask(h); bool new_page = false; u32 hash = hugetlb_fault_mutex_hash(mapping, idx); /* * Currently, we are forced to kill the process in the event the * original mapper has unmapped pages from the child due to a failed * COW. Warn that such a situation has occurred as it may not be obvious */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", current->pid); goto out; } /* * We can not race with truncation due to holding i_mmap_rwsem. * i_size is modified when holding i_mmap_rwsem, so check here * once for faults beyond end of file. */ size = i_size_read(mapping->host) >> huge_page_shift(h); if (idx >= size) goto out; retry: page = find_lock_page(mapping, idx); if (!page) { /* * Check for page in userfault range */ if (userfaultfd_missing(vma)) { struct vm_fault vmf = { .vma = vma, .address = haddr, .flags = flags, /* * Hard to debug if it ends up being * used by a callee that assumes * something about the other * uninitialized fields... same as in * memory.c */ }; /* * vma_lock and hugetlb_fault_mutex must be dropped * before handling userfault. Also mmap_lock will * be dropped during handling userfault, any vma * operation should be careful from here. */ mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); return handle_userfault(&vmf, VM_UFFD_MISSING); } page = alloc_huge_page(vma, haddr, 0); if (IS_ERR(page)) { /* * Returning error will result in faulting task being * sent SIGBUS. The hugetlb fault mutex prevents two * tasks from racing to fault in the same page which * could result in false unable to allocate errors. * Page migration does not take the fault mutex, but * does a clear then write of pte's under page table * lock. Page fault code could race with migration, * notice the clear pte and try to allocate a page * here. Before returning error, get ptl and make * sure there really is no pte entry. */ ptl = huge_pte_lock(h, mm, ptep); if (!huge_pte_none(huge_ptep_get(ptep))) { ret = 0; spin_unlock(ptl); goto out; } spin_unlock(ptl); ret = vmf_error(PTR_ERR(page)); goto out; } clear_huge_page(page, address, pages_per_huge_page(h)); __SetPageUptodate(page); new_page = true; if (vma->vm_flags & VM_MAYSHARE) { int err = huge_add_to_page_cache(page, mapping, idx); if (err) { put_page(page); if (err == -EEXIST) goto retry; goto out; } } else { lock_page(page); if (unlikely(anon_vma_prepare(vma))) { ret = VM_FAULT_OOM; goto backout_unlocked; } anon_rmap = 1; } } else { /* * If memory error occurs between mmap() and fault, some process * don't have hwpoisoned swap entry for errored virtual address. * So we need to block hugepage fault by PG_hwpoison bit check. */ if (unlikely(PageHWPoison(page))) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } } /* * If we are going to COW a private mapping later, we examine the * pending reservations for this page now. This will ensure that * any allocations necessary to record that reservation occur outside * the spinlock. */ if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { if (vma_needs_reservation(h, vma, haddr) < 0) { ret = VM_FAULT_OOM; goto backout_unlocked; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, haddr); } ptl = huge_pte_lock(h, mm, ptep); ret = 0; if (!huge_pte_none(huge_ptep_get(ptep))) goto backout; if (anon_rmap) { ClearPagePrivate(page); hugepage_add_new_anon_rmap(page, vma, haddr); } else page_dup_rmap(page, true); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); set_huge_pte_at(mm, haddr, ptep, new_pte); hugetlb_count_add(pages_per_huge_page(h), mm); if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ ret = hugetlb_cow(mm, vma, address, ptep, page, ptl); } spin_unlock(ptl); /* * Only make newly allocated pages active. Existing pages found * in the pagecache could be !page_huge_active() if they have been * isolated for migration. */ if (new_page) set_page_huge_active(page); unlock_page(page); out: mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); return ret; backout: spin_unlock(ptl); backout_unlocked: unlock_page(page); restore_reserve_on_error(h, vma, haddr, page); put_page(page); goto out; } #ifdef CONFIG_SMP u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { unsigned long key[2]; u32 hash; key[0] = (unsigned long) mapping; key[1] = idx; hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0); return hash & (num_fault_mutexes - 1); } #else /* * For uniprocesor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { return 0; } #endif vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { pte_t *ptep, entry; spinlock_t *ptl; vm_fault_t ret; u32 hash; pgoff_t idx; struct page *page = NULL; struct page *pagecache_page = NULL; struct hstate *h = hstate_vma(vma); struct address_space *mapping; int need_wait_lock = 0; unsigned long haddr = address & huge_page_mask(h); ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (ptep) { /* * Since we hold no locks, ptep could be stale. That is * OK as we are only making decisions based on content and * not actually modifying content here. */ entry = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_migration(entry))) { migration_entry_wait_huge(vma, mm, ptep); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); } /* * Acquire i_mmap_rwsem before calling huge_pte_alloc and hold * until finished with ptep. This serves two purposes: * 1) It prevents huge_pmd_unshare from being called elsewhere * and making the ptep no longer valid. * 2) It synchronizes us with i_size modifications during truncation. * * ptep could have already be assigned via huge_pte_offset. That * is OK, as huge_pte_alloc will return the same value unless * something has changed. */ mapping = vma->vm_file->f_mapping; i_mmap_lock_read(mapping); ptep = huge_pte_alloc(mm, haddr, huge_page_size(h)); if (!ptep) { i_mmap_unlock_read(mapping); return VM_FAULT_OOM; } /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ idx = vma_hugecache_offset(h, vma, haddr); hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); entry = huge_ptep_get(ptep); if (huge_pte_none(entry)) /* * hugetlb_no_page will drop vma lock and hugetlb fault * mutex internally, which make us return immediately. */ return hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); ret = 0; /* * entry could be a migration/hwpoison entry at this point, so this * check prevents the kernel from going below assuming that we have * an active hugepage in pagecache. This goto expects the 2nd page * fault, and is_hugetlb_entry_(migration|hwpoisoned) check will * properly handle it. */ if (!pte_present(entry)) goto out_mutex; /* * If we are going to COW the mapping later, we examine the pending * reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the * spinlock. For private mappings, we also lookup the pagecache * page now as it is used to determine if a reservation has been * consumed. */ if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { if (vma_needs_reservation(h, vma, haddr) < 0) { ret = VM_FAULT_OOM; goto out_mutex; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, haddr); if (!(vma->vm_flags & VM_MAYSHARE)) pagecache_page = hugetlbfs_pagecache_page(h, vma, haddr); } ptl = huge_pte_lock(h, mm, ptep); /* Check for a racing update before calling hugetlb_cow */ if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) goto out_ptl; /* * hugetlb_cow() requires page locks of pte_page(entry) and * pagecache_page, so here we need take the former one * when page != pagecache_page or !pagecache_page. */ page = pte_page(entry); if (page != pagecache_page) if (!trylock_page(page)) { need_wait_lock = 1; goto out_ptl; } get_page(page); if (flags & FAULT_FLAG_WRITE) { if (!huge_pte_write(entry)) { ret = hugetlb_cow(mm, vma, address, ptep, pagecache_page, ptl); goto out_put_page; } entry = huge_pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (huge_ptep_set_access_flags(vma, haddr, ptep, entry, flags & FAULT_FLAG_WRITE)) update_mmu_cache(vma, haddr, ptep); out_put_page: if (page != pagecache_page) unlock_page(page); put_page(page); out_ptl: spin_unlock(ptl); if (pagecache_page) { unlock_page(pagecache_page); put_page(pagecache_page); } out_mutex: mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); /* * Generally it's safe to hold refcount during waiting page lock. But * here we just wait to defer the next page fault to avoid busy loop and * the page is not used after unlocked before returning from the current * page fault. So we are safe from accessing freed page, even if we wait * here without taking refcount. */ if (need_wait_lock) wait_on_page_locked(page); return ret; } /* * Used by userfaultfd UFFDIO_COPY. Based on mcopy_atomic_pte with * modifications for huge pages. */ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, struct page **pagep) { struct address_space *mapping; pgoff_t idx; unsigned long size; int vm_shared = dst_vma->vm_flags & VM_SHARED; struct hstate *h = hstate_vma(dst_vma); pte_t _dst_pte; spinlock_t *ptl; int ret; struct page *page; if (!*pagep) { /* If a page already exists, then it's UFFDIO_COPY for * a non-missing case. Return -EEXIST. */ if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { ret = -EEXIST; goto out; } page = alloc_huge_page(dst_vma, dst_addr, 0); if (IS_ERR(page)) { ret = -ENOMEM; goto out; } ret = copy_huge_page_from_user(page, (const void __user *) src_addr, pages_per_huge_page(h), false); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; *pagep = page; /* don't free the page */ goto out; } } else { page = *pagep; *pagep = NULL; } /* * The memory barrier inside __SetPageUptodate makes sure that * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); mapping = dst_vma->vm_file->f_mapping; idx = vma_hugecache_offset(h, dst_vma, dst_addr); /* * If shared, add to page cache */ if (vm_shared) { size = i_size_read(mapping->host) >> huge_page_shift(h); ret = -EFAULT; if (idx >= size) goto out_release_nounlock; /* * Serialization between remove_inode_hugepages() and * huge_add_to_page_cache() below happens through the * hugetlb_fault_mutex_table that here must be hold by * the caller. */ ret = huge_add_to_page_cache(page, mapping, idx); if (ret) goto out_release_nounlock; } ptl = huge_pte_lockptr(h, dst_mm, dst_pte); spin_lock(ptl); /* * Recheck the i_size after holding PT lock to make sure not * to leave any page mapped (as page_mapped()) beyond the end * of the i_size (remove_inode_hugepages() is strict about * enforcing that). If we bail out here, we'll also leave a * page in the radix tree in the vm_shared case beyond the end * of the i_size, but remove_inode_hugepages() will take care * of it as soon as we drop the hugetlb_fault_mutex_table. */ size = i_size_read(mapping->host) >> huge_page_shift(h); ret = -EFAULT; if (idx >= size) goto out_release_unlock; ret = -EEXIST; if (!huge_pte_none(huge_ptep_get(dst_pte))) goto out_release_unlock; if (vm_shared) { page_dup_rmap(page, true); } else { ClearPagePrivate(page); hugepage_add_new_anon_rmap(page, dst_vma, dst_addr); } _dst_pte = make_huge_pte(dst_vma, page, dst_vma->vm_flags & VM_WRITE); if (dst_vma->vm_flags & VM_WRITE) _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); (void)huge_ptep_set_access_flags(dst_vma, dst_addr, dst_pte, _dst_pte, dst_vma->vm_flags & VM_WRITE); hugetlb_count_add(pages_per_huge_page(h), dst_mm); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); set_page_huge_active(page); if (vm_shared) unlock_page(page); ret = 0; out: return ret; out_release_unlock: spin_unlock(ptl); if (vm_shared) unlock_page(page); out_release_nounlock: put_page(page); goto out; } long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, unsigned long *nr_pages, long i, unsigned int flags, int *locked) { unsigned long pfn_offset; unsigned long vaddr = *position; unsigned long remainder = *nr_pages; struct hstate *h = hstate_vma(vma); int err = -EFAULT; while (vaddr < vma->vm_end && remainder) { pte_t *pte; spinlock_t *ptl = NULL; int absent; struct page *page; /* * If we have a pending SIGKILL, don't keep faulting pages and * potentially allocating memory. */ if (fatal_signal_pending(current)) { remainder = 0; break; } /* * Some archs (sparc64, sh*) have multiple pte_ts to * each hugepage. We have to make sure we get the * first, for the page indexing below to work. * * Note that page table lock is not held when pte is null. */ pte = huge_pte_offset(mm, vaddr & huge_page_mask(h), huge_page_size(h)); if (pte) ptl = huge_pte_lock(h, mm, pte); absent = !pte || huge_pte_none(huge_ptep_get(pte)); /* * When coredumping, it suits get_dump_page if we just return * an error where there's an empty slot with no huge pagecache * to back it. This way, we avoid allocating a hugepage, and * the sparse dumpfile avoids allocating disk blocks, but its * huge holes still show up with zeroes where they need to be. */ if (absent && (flags & FOLL_DUMP) && !hugetlbfs_pagecache_present(h, vma, vaddr)) { if (pte) spin_unlock(ptl); remainder = 0; break; } /* * We need call hugetlb_fault for both hugepages under migration * (in which case hugetlb_fault waits for the migration,) and * hwpoisoned hugepages (in which case we need to prevent the * caller from accessing to them.) In order to do this, we use * here is_swap_pte instead of is_hugetlb_entry_migration and * is_hugetlb_entry_hwpoisoned. This is because it simply covers * both cases, and because we can't follow correct pages * directly from any kind of swap entries. */ if (absent || is_swap_pte(huge_ptep_get(pte)) || ((flags & FOLL_WRITE) && !huge_pte_write(huge_ptep_get(pte)))) { vm_fault_t ret; unsigned int fault_flags = 0; if (pte) spin_unlock(ptl); if (flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (locked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; if (flags & FOLL_NOWAIT) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; if (flags & FOLL_TRIED) { /* * Note: FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_TRIED can co-exist */ fault_flags |= FAULT_FLAG_TRIED; } ret = hugetlb_fault(mm, vma, vaddr, fault_flags); if (ret & VM_FAULT_ERROR) { err = vm_fault_to_errno(ret, flags); remainder = 0; break; } if (ret & VM_FAULT_RETRY) { if (locked && !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *locked = 0; *nr_pages = 0; /* * VM_FAULT_RETRY must not return an * error, it will return zero * instead. * * No need to update "position" as the * caller will not check it after * *nr_pages is set to 0. */ return i; } continue; } pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT; page = pte_page(huge_ptep_get(pte)); /* * If subpage information not requested, update counters * and skip the same_page loop below. */ if (!pages && !vmas && !pfn_offset && (vaddr + huge_page_size(h) < vma->vm_end) && (remainder >= pages_per_huge_page(h))) { vaddr += huge_page_size(h); remainder -= pages_per_huge_page(h); i += pages_per_huge_page(h); spin_unlock(ptl); continue; } same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); /* * try_grab_page() should always succeed here, because: * a) we hold the ptl lock, and b) we've just checked * that the huge page is present in the page tables. If * the huge page is present, then the tail pages must * also be present. The ptl prevents the head page and * tail pages from being rearranged in any way. So this * page must be available at this point, unless the page * refcount overflowed: */ if (WARN_ON_ONCE(!try_grab_page(pages[i], flags))) { spin_unlock(ptl); remainder = 0; err = -ENOMEM; break; } } if (vmas) vmas[i] = vma; vaddr += PAGE_SIZE; ++pfn_offset; --remainder; ++i; if (vaddr < vma->vm_end && remainder && pfn_offset < pages_per_huge_page(h)) { /* * We use pfn_offset to avoid touching the pageframes * of this compound page. */ goto same_page; } spin_unlock(ptl); } *nr_pages = remainder; /* * setting position is actually required only if remainder is * not zero but it's faster not to add a "if (remainder)" * branch. */ *position = vaddr; return i ? i : err; } #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE /* * ARCHes with special requirements for evicting HUGETLB backing TLB entries can * implement this. */ #define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #endif unsigned long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot) { struct mm_struct *mm = vma->vm_mm; unsigned long start = address; pte_t *ptep; pte_t pte; struct hstate *h = hstate_vma(vma); unsigned long pages = 0; bool shared_pmd = false; struct mmu_notifier_range range; /* * In the case of shared PMDs, the area to flush could be beyond * start/end. Set range.start/range.end to cover the maximum possible * range if PMD sharing is possible. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, vma, mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); i_mmap_lock_write(vma->vm_file->f_mapping); for (; address < end; address += huge_page_size(h)) { spinlock_t *ptl; ptep = huge_pte_offset(mm, address, huge_page_size(h)); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, &address, ptep)) { pages++; spin_unlock(ptl); shared_pmd = true; continue; } pte = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { spin_unlock(ptl); continue; } if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); if (is_write_migration_entry(entry)) { pte_t newpte; make_migration_entry_read(&entry); newpte = swp_entry_to_pte(entry); set_huge_swap_pte_at(mm, address, ptep, newpte, huge_page_size(h)); pages++; } spin_unlock(ptl); continue; } if (!huge_pte_none(pte)) { pte_t old_pte; old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = pte_mkhuge(huge_pte_modify(old_pte, newprot)); pte = arch_make_huge_pte(pte, vma, NULL, 0); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; } spin_unlock(ptl); } /* * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: * once we release i_mmap_rwsem, another task can do the final put_page * and that page table be reused and filled with junk. If we actually * did unshare a page of pmds, flush the range corresponding to the pud. */ if (shared_pmd) flush_hugetlb_tlb_range(vma, range.start, range.end); else flush_hugetlb_tlb_range(vma, start, end); /* * No need to call mmu_notifier_invalidate_range() we are downgrading * page table protection not changing it to point to a new page. * * See Documentation/vm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); mmu_notifier_invalidate_range_end(&range); return pages << h->order; } /* Return true if reservation was successful, false otherwise. */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags) { long chg, add = -1; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; struct hugetlb_cgroup *h_cg = NULL; long gbl_reserve, regions_needed = 0; /* This should never happen */ if (from > to) { VM_WARN(1, "%s called with a negative range\n", __func__); return false; } /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page * without using reserves */ if (vm_flags & VM_NORESERVE) return true; /* * Shared mappings base their reservation on the number of pages that * are already allocated on behalf of the file. Private mappings need * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !vma is a shm mapping */ if (!vma || vma->vm_flags & VM_MAYSHARE) { /* * resv_map can not be NULL as hugetlb_reserve_pages is only * called for inodes for which resv_maps were created (see * hugetlbfs_get_inode). */ resv_map = inode_resv_map(inode); chg = region_chg(resv_map, from, to, ®ions_needed); } else { /* Private mapping. */ resv_map = resv_map_alloc(); if (!resv_map) return false; chg = to - from; set_vma_resv_map(vma, resv_map); set_vma_resv_flags(vma, HPAGE_RESV_OWNER); } if (chg < 0) goto out_err; if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), &h_cg) < 0) goto out_err; if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) { /* For private mappings, the hugetlb_cgroup uncharge info hangs * of the resv_map. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h); } /* * There must be enough pages in the subpool for the mapping. If * the subpool has a minimum size, there may be some global * reservations already in place (gbl_reserve). */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); if (gbl_reserve < 0) goto out_uncharge_cgroup; /* * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; /* * Account for the reservations made. Shared mappings record regions * that have reservations as they are shared by multiple VMAs. * When the last VMA disappears, the region map says how much * the reservation was and the page cache tells how much of * the reservation was consumed. Private mappings are per-VMA and * only the consumed reservations are tracked. When the VMA * disappears, the original reservation is the VMA size and the * consumed reservations are stored in the map. Hence, nothing * else has to be done for private mappings here */ if (!vma || vma->vm_flags & VM_MAYSHARE) { add = region_add(resv_map, from, to, regions_needed, h, h_cg); if (unlikely(add < 0)) { hugetlb_acct_memory(h, -gbl_reserve); goto out_put_pages; } else if (unlikely(chg > add)) { /* * pages in this range were added to the reserve * map between region_chg and region_add. This * indicates a race with alloc_huge_page. Adjust * the subpool and reserve counts modified above * based on the difference. */ long rsv_adjust; /* * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the * reference to h_cg->css. See comment below for detail. */ hugetlb_cgroup_uncharge_cgroup_rsvd( hstate_index(h), (chg - add) * pages_per_huge_page(h), h_cg); rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); } else if (h_cg) { /* * The file_regions will hold their own reference to * h_cg->css. So we should release the reference held * via hugetlb_cgroup_charge_cgroup_rsvd() when we are * done. */ hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } return true; out_put_pages: /* put back original number of pages, chg */ (void)hugepage_subpool_put_pages(spool, chg); out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg); out_err: if (!vma || vma->vm_flags & VM_MAYSHARE) /* Only call region_abort if the region_chg succeeded but the * region_add failed or didn't run. */ if (chg >= 0 && add < 0) region_abort(resv_map, from, to, regions_needed); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) kref_put(&resv_map->refs, resv_map_release); return false; } long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed) { struct hstate *h = hstate_inode(inode); struct resv_map *resv_map = inode_resv_map(inode); long chg = 0; struct hugepage_subpool *spool = subpool_inode(inode); long gbl_reserve; /* * Since this routine can be called in the evict inode path for all * hugetlbfs inodes, resv_map could be NULL. */ if (resv_map) { chg = region_del(resv_map, start, end); /* * region_del() can fail in the rare case where a region * must be split and another region descriptor can not be * allocated. If end == LONG_MAX, it will not fail. */ if (chg < 0) return chg; } spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); /* * If the subpool has a minimum size, the number of global * reservations to be released may be adjusted. */ gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); hugetlb_acct_memory(h, -gbl_reserve); return 0; } #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE static unsigned long page_table_shareable(struct vm_area_struct *svma, struct vm_area_struct *vma, unsigned long addr, pgoff_t idx) { unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + svma->vm_start; unsigned long sbase = saddr & PUD_MASK; unsigned long s_end = sbase + PUD_SIZE; /* Allow segments to share if only one is marked locked */ unsigned long vm_flags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; unsigned long svm_flags = svma->vm_flags & VM_LOCKED_CLEAR_MASK; /* * match the virtual addresses, permission and the alignment of the * page table page. */ if (pmd_index(addr) != pmd_index(saddr) || vm_flags != svm_flags || sbase < svma->vm_start || svma->vm_end < s_end) return 0; return saddr; } static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) { unsigned long base = addr & PUD_MASK; unsigned long end = base + PUD_SIZE; /* * check on proper vm_flags and page table alignment */ if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end)) return true; return false; } /* * Determine if start,end range within vma could be mapped by shared pmd. * If yes, adjust start and end to cover range associated with possible * shared pmd mappings. */ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE), v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); /* * vma need span at least one aligned PUD size and the start,end range * must at least partialy within it. */ if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || (*end <= v_start) || (*start >= v_end)) return; /* Extend the range to be PUD aligned for a worst case scenario */ if (*start > v_start) *start = ALIGN_DOWN(*start, PUD_SIZE); if (*end < v_end) *end = ALIGN(*end, PUD_SIZE); } /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the * code much cleaner. * * This routine must be called with i_mmap_rwsem held in at least read mode if * sharing is possible. For hugetlbfs, this prevents removal of any page * table entries associated with the address space. This is important as we * are setting up sharing based on existing page table entries (mappings). * * NOTE: This routine is only called from huge_pte_alloc. Some callers of * huge_pte_alloc know that sharing is not possible and do not take * i_mmap_rwsem as a performance optimization. This is handled by the * if !vma_shareable check at the beginning of the routine. i_mmap_rwsem is * only required for subsequent processing. */ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) { struct vm_area_struct *vma = find_vma(mm, addr); struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; struct vm_area_struct *svma; unsigned long saddr; pte_t *spte = NULL; pte_t *pte; spinlock_t *ptl; if (!vma_shareable(vma, addr)) return (pte_t *)pmd_alloc(mm, pud, addr); i_mmap_assert_locked(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; saddr = page_table_shareable(svma, vma, addr, idx); if (saddr) { spte = huge_pte_offset(svma->vm_mm, saddr, vma_mmu_pagesize(svma)); if (spte) { atomic_inc(&virt_to_page(spte)->pt_share_count); break; } } } if (!spte) goto out; ptl = huge_pte_lock(hstate_vma(vma), mm, spte); if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { atomic_dec(&virt_to_page(spte)->pt_share_count); } spin_unlock(ptl); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); return pte; } /* * unmap huge page backed by shared pte. * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user */ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long *addr, pte_t *ptep) { unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, *addr); p4d_t *p4d = p4d_offset(pgd, *addr); pud_t *pud = pud_offset(p4d, *addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); if (sz != PMD_SIZE) return 0; if (!atomic_read(&virt_to_page(ptep)->pt_share_count)) return 0; pud_clear(pud); /* * Once our caller drops the rmap lock, some other process might be * using this page table as a normal, non-hugetlb page table. * Wait for pending gup_fast() in other threads to finish before letting * that happen. */ tlb_remove_table_sync_one(); atomic_dec(&virt_to_page(ptep)->pt_share_count); mm_dec_nr_pmds(mm); /* * This update of passed address optimizes loops sequentially * processing addresses in increments of huge page size (PMD_SIZE * in this case). By clearing the pud, a PUD_SIZE area is unmapped. * Update address to the 'last page' in the cleared area so that * calling loop can move to first page past this area. */ *addr |= PUD_SIZE - PMD_SIZE; return 1; } #define want_pmd_share() (1) #else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) { return NULL; } int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long *addr, pte_t *ptep) { return 0; } void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } #define want_pmd_share() (0) #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { pte = (pte_t *)pud; } else { BUG_ON(sz != PMD_SIZE); if (want_pmd_share() && pud_none(*pud)) pte = huge_pmd_share(mm, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); } } BUG_ON(pte && pte_present(*pte) && !pte_huge(*pte)); return pte; } /* * huge_pte_offset() - Walk the page table to resolve the hugepage * entry at address @addr * * Return: Pointer to page table entry (PUD or PMD) for * address @addr, or NULL if a !p*d_present() entry is encountered and the * size @sz doesn't match the hugepage size at this level of the page * table. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) return NULL; p4d = p4d_offset(pgd, addr); if (!p4d_present(*p4d)) return NULL; pud = pud_offset(p4d, addr); if (sz == PUD_SIZE) /* must be pud huge, non-present or none */ return (pte_t *)pud; if (!pud_present(*pud)) return NULL; /* must have a valid entry and size to go further */ pmd = pmd_offset(pud, addr); /* must be pmd huge, non-present or none */ return (pte_t *)pmd; } #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ /* * These functions are overwritable if your architecture needs its own * behavior. */ struct page * __weak follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) { return ERR_PTR(-EINVAL); } struct page * __weak follow_huge_pd(struct vm_area_struct *vma, unsigned long address, hugepd_t hpd, int flags, int pdshift) { WARN(1, "hugepd follow called with no support for hugepage directory format\n"); return NULL; } struct page * __weak follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, int flags) { struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; struct page *page = NULL; spinlock_t *ptl; pte_t *ptep, pte; /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return NULL; retry: ptep = huge_pte_offset(mm, address, huge_page_size(h)); if (!ptep) return NULL; ptl = huge_pte_lock(h, mm, ptep); pte = huge_ptep_get(ptep); if (pte_present(pte)) { page = pte_page(pte) + ((address & ~huge_page_mask(h)) >> PAGE_SHIFT); /* * try_grab_page() should always succeed here, because: a) we * hold the pmd (ptl) lock, and b) we've just checked that the * huge pmd (head) page is present in the page tables. The ptl * prevents the head page and tail pages from being rearranged * in any way. So this page must be available at this point, * unless the page refcount overflowed: */ if (WARN_ON_ONCE(!try_grab_page(page, flags))) { page = NULL; goto out; } } else { if (is_hugetlb_entry_migration(pte)) { spin_unlock(ptl); __migration_entry_wait(mm, ptep, ptl); goto retry; } /* * hwpoisoned entry is treated as no_page_table in * follow_page_mask(). */ } out: spin_unlock(ptl); return page; } struct page * __weak follow_huge_pud(struct mm_struct *mm, unsigned long address, pud_t *pud, int flags) { if (flags & (FOLL_GET | FOLL_PIN)) return NULL; return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); } struct page * __weak follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags) { if (flags & (FOLL_GET | FOLL_PIN)) return NULL; return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT); } int isolate_hugetlb(struct page *page, struct list_head *list) { int ret = 0; spin_lock(&hugetlb_lock); if (!PageHeadHuge(page) || !page_huge_active(page) || !get_page_unless_zero(page)) { ret = -EBUSY; goto unlock; } clear_page_huge_active(page); list_move_tail(&page->lru, list); unlock: spin_unlock(&hugetlb_lock); return ret; } void putback_active_hugepage(struct page *page) { VM_BUG_ON_PAGE(!PageHead(page), page); spin_lock(&hugetlb_lock); set_page_huge_active(page); list_move_tail(&page->lru, &(page_hstate(page))->hugepage_activelist); spin_unlock(&hugetlb_lock); put_page(page); } void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) { struct hstate *h = page_hstate(oldpage); hugetlb_cgroup_migrate(oldpage, newpage); set_page_owner_migrate_reason(newpage, reason); /* * transfer temporary state of the new huge page. This is * reverse to other transitions because the newpage is going to * be final while the old one will be freed so it takes over * the temporary status. * * Also note that we have to transfer the per-node surplus state * here as well otherwise the global surplus count will not match * the per-node's. */ if (PageHugeTemporary(newpage)) { int old_nid = page_to_nid(oldpage); int new_nid = page_to_nid(newpage); SetPageHugeTemporary(oldpage); ClearPageHugeTemporary(newpage); spin_lock(&hugetlb_lock); if (h->surplus_huge_pages_node[old_nid]) { h->surplus_huge_pages_node[old_nid]--; h->surplus_huge_pages_node[new_nid]++; } spin_unlock(&hugetlb_lock); } } /* * If @take_locks is false, the caller must ensure that no concurrent page table * access can happen (except for gup_fast() and hardware page walks). * If @take_locks is true, we take the hugetlb VMA lock (to lock out things like * concurrent page fault handling) and the file rmap lock. */ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool take_locks) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; unsigned long address; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & VM_MAYSHARE)) return; if (start >= end) return; flush_cache_range(vma, start, end); /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, start, end); mmu_notifier_invalidate_range_start(&range); if (take_locks) { i_mmap_lock_write(vma->vm_file->f_mapping); } else { i_mmap_assert_write_locked(vma->vm_file->f_mapping); } for (address = start; address < end; address += PUD_SIZE) { ptep = huge_pte_offset(mm, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); huge_pmd_unshare(mm, vma, &address, ptep); spin_unlock(ptl); } flush_hugetlb_tlb_range(vma, start, end); if (take_locks) { i_mmap_unlock_write(vma->vm_file->f_mapping); } /* * No need to call mmu_notifier_invalidate_range(), see * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); } #ifdef CONFIG_CMA static bool cma_reserve_called __initdata; static int __init cmdline_parse_hugetlb_cma(char *p) { hugetlb_cma_size = memparse(p, &p); return 0; } early_param("hugetlb_cma", cmdline_parse_hugetlb_cma); void __init hugetlb_cma_reserve(int order) { unsigned long size, reserved, per_node; int nid; cma_reserve_called = true; if (!hugetlb_cma_size) return; if (hugetlb_cma_size < (PAGE_SIZE << order)) { pr_warn("hugetlb_cma: cma area should be at least %lu MiB\n", (PAGE_SIZE << order) / SZ_1M); return; } /* * If 3 GB area is requested on a machine with 4 numa nodes, * let's allocate 1 GB on first three nodes and ignore the last one. */ per_node = DIV_ROUND_UP(hugetlb_cma_size, nr_online_nodes); pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n", hugetlb_cma_size / SZ_1M, per_node / SZ_1M); reserved = 0; for_each_node_state(nid, N_ONLINE) { int res; char name[CMA_MAX_NAME]; size = min(per_node, hugetlb_cma_size - reserved); size = round_up(size, PAGE_SIZE << order); snprintf(name, sizeof(name), "hugetlb%d", nid); res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order, 0, false, name, &hugetlb_cma[nid], nid); if (res) { pr_warn("hugetlb_cma: reservation failed: err %d, node %d", res, nid); continue; } reserved += size; pr_info("hugetlb_cma: reserved %lu MiB on node %d\n", size / SZ_1M, nid); if (reserved >= hugetlb_cma_size) break; } } void __init hugetlb_cma_check(void) { if (!hugetlb_cma_size || cma_reserve_called) return; pr_warn("hugetlb_cma: the option isn't supported by current arch\n"); } #endif /* CONFIG_CMA */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Events for filesystem locks * * Copyright 2013 Jeff Layton <jlayton@poochiereds.net> */ #undef TRACE_SYSTEM #define TRACE_SYSTEM filelock #if !defined(_TRACE_FILELOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FILELOCK_H #include <linux/tracepoint.h> #include <linux/fs.h> #include <linux/device.h> #include <linux/kdev_t.h> #define show_fl_flags(val) \ __print_flags(val, "|", \ { FL_POSIX, "FL_POSIX" }, \ { FL_FLOCK, "FL_FLOCK" }, \ { FL_DELEG, "FL_DELEG" }, \ { FL_ACCESS, "FL_ACCESS" }, \ { FL_EXISTS, "FL_EXISTS" }, \ { FL_LEASE, "FL_LEASE" }, \ { FL_CLOSE, "FL_CLOSE" }, \ { FL_SLEEP, "FL_SLEEP" }, \ { FL_DOWNGRADE_PENDING, "FL_DOWNGRADE_PENDING" }, \ { FL_UNLOCK_PENDING, "FL_UNLOCK_PENDING" }, \ { FL_OFDLCK, "FL_OFDLCK" }) #define show_fl_type(val) \ __print_symbolic(val, \ { F_RDLCK, "F_RDLCK" }, \ { F_WRLCK, "F_WRLCK" }, \ { F_UNLCK, "F_UNLCK" }) TRACE_EVENT(locks_get_lock_context, TP_PROTO(struct inode *inode, int type, struct file_lock_context *ctx), TP_ARGS(inode, type, ctx), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(unsigned char, type) __field(struct file_lock_context *, ctx) ), TP_fast_assign( __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->type = type; __entry->ctx = ctx; ), TP_printk("dev=0x%x:0x%x ino=0x%lx type=%s ctx=%p", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, show_fl_type(__entry->type), __entry->ctx) ); DECLARE_EVENT_CLASS(filelock_lock, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret), TP_STRUCT__entry( __field(struct file_lock *, fl) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(struct file_lock *, fl_blocker) __field(fl_owner_t, fl_owner) __field(unsigned int, fl_pid) __field(unsigned int, fl_flags) __field(unsigned char, fl_type) __field(loff_t, fl_start) __field(loff_t, fl_end) __field(int, ret) ), TP_fast_assign( __entry->fl = fl ? fl : NULL; __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->fl_blocker = fl ? fl->fl_blocker : NULL; __entry->fl_owner = fl ? fl->fl_owner : NULL; __entry->fl_pid = fl ? fl->fl_pid : 0; __entry->fl_flags = fl ? fl->fl_flags : 0; __entry->fl_type = fl ? fl->fl_type : 0; __entry->fl_start = fl ? fl->fl_start : 0; __entry->fl_end = fl ? fl->fl_end : 0; __entry->ret = ret; ), TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d", __entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->fl_blocker, __entry->fl_owner, __entry->fl_pid, show_fl_flags(__entry->fl_flags), show_fl_type(__entry->fl_type), __entry->fl_start, __entry->fl_end, __entry->ret) ); DEFINE_EVENT(filelock_lock, posix_lock_inode, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DEFINE_EVENT(filelock_lock, fcntl_setlk, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DEFINE_EVENT(filelock_lock, locks_remove_posix, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DEFINE_EVENT(filelock_lock, flock_lock_inode, TP_PROTO(struct inode *inode, struct file_lock *fl, int ret), TP_ARGS(inode, fl, ret)); DECLARE_EVENT_CLASS(filelock_lease, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl), TP_STRUCT__entry( __field(struct file_lock *, fl) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(struct file_lock *, fl_blocker) __field(fl_owner_t, fl_owner) __field(unsigned int, fl_flags) __field(unsigned char, fl_type) __field(unsigned long, fl_break_time) __field(unsigned long, fl_downgrade_time) ), TP_fast_assign( __entry->fl = fl ? fl : NULL; __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->fl_blocker = fl ? fl->fl_blocker : NULL; __entry->fl_owner = fl ? fl->fl_owner : NULL; __entry->fl_flags = fl ? fl->fl_flags : 0; __entry->fl_type = fl ? fl->fl_type : 0; __entry->fl_break_time = fl ? fl->fl_break_time : 0; __entry->fl_downgrade_time = fl ? fl->fl_downgrade_time : 0; ), TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu", __entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->fl_blocker, __entry->fl_owner, show_fl_flags(__entry->fl_flags), show_fl_type(__entry->fl_type), __entry->fl_break_time, __entry->fl_downgrade_time) ); DEFINE_EVENT(filelock_lease, break_lease_noblock, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, break_lease_block, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, break_lease_unblock, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, generic_delete_lease, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl)); DEFINE_EVENT(filelock_lease, time_out_leases, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl)); TRACE_EVENT(generic_add_lease, TP_PROTO(struct inode *inode, struct file_lock *fl), TP_ARGS(inode, fl), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(int, wcount) __field(int, rcount) __field(int, icount) __field(dev_t, s_dev) __field(fl_owner_t, fl_owner) __field(unsigned int, fl_flags) __field(unsigned char, fl_type) ), TP_fast_assign( __entry->s_dev = inode->i_sb->s_dev; __entry->i_ino = inode->i_ino; __entry->wcount = atomic_read(&inode->i_writecount); __entry->rcount = atomic_read(&inode->i_readcount); __entry->icount = atomic_read(&inode->i_count); __entry->fl_owner = fl->fl_owner; __entry->fl_flags = fl->fl_flags; __entry->fl_type = fl->fl_type; ), TP_printk("dev=0x%x:0x%x ino=0x%lx wcount=%d rcount=%d icount=%d fl_owner=%p fl_flags=%s fl_type=%s", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->wcount, __entry->rcount, __entry->icount, __entry->fl_owner, show_fl_flags(__entry->fl_flags), show_fl_type(__entry->fl_type)) ); TRACE_EVENT(leases_conflict, TP_PROTO(bool conflict, struct file_lock *lease, struct file_lock *breaker), TP_ARGS(conflict, lease, breaker), TP_STRUCT__entry( __field(void *, lease) __field(void *, breaker) __field(unsigned int, l_fl_flags) __field(unsigned int, b_fl_flags) __field(unsigned char, l_fl_type) __field(unsigned char, b_fl_type) __field(bool, conflict) ), TP_fast_assign( __entry->lease = lease; __entry->l_fl_flags = lease->fl_flags; __entry->l_fl_type = lease->fl_type; __entry->breaker = breaker; __entry->b_fl_flags = breaker->fl_flags; __entry->b_fl_type = breaker->fl_type; __entry->conflict = conflict; ), TP_printk("conflict %d: lease=%p fl_flags=%s fl_type=%s; breaker=%p fl_flags=%s fl_type=%s", __entry->conflict, __entry->lease, show_fl_flags(__entry->l_fl_flags), show_fl_type(__entry->l_fl_type), __entry->breaker, show_fl_flags(__entry->b_fl_flags), show_fl_type(__entry->b_fl_type)) ); #endif /* _TRACE_FILELOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 | /* This file is automatically generated. Do not edit. */ #ifndef _SELINUX_FLASK_H_ #define _SELINUX_FLASK_H_ #define SECCLASS_SECURITY 1 #define SECCLASS_PROCESS 2 #define SECCLASS_PROCESS2 3 #define SECCLASS_SYSTEM 4 #define SECCLASS_CAPABILITY 5 #define SECCLASS_FILESYSTEM 6 #define SECCLASS_FILE 7 #define SECCLASS_DIR 8 #define SECCLASS_FD 9 #define SECCLASS_LNK_FILE 10 #define SECCLASS_CHR_FILE 11 #define SECCLASS_BLK_FILE 12 #define SECCLASS_SOCK_FILE 13 #define SECCLASS_FIFO_FILE 14 #define SECCLASS_SOCKET 15 #define SECCLASS_TCP_SOCKET 16 #define SECCLASS_UDP_SOCKET 17 #define SECCLASS_RAWIP_SOCKET 18 #define SECCLASS_NODE 19 #define SECCLASS_NETIF 20 #define SECCLASS_NETLINK_SOCKET 21 #define SECCLASS_PACKET_SOCKET 22 #define SECCLASS_KEY_SOCKET 23 #define SECCLASS_UNIX_STREAM_SOCKET 24 #define SECCLASS_UNIX_DGRAM_SOCKET 25 #define SECCLASS_SEM 26 #define SECCLASS_MSG 27 #define SECCLASS_MSGQ 28 #define SECCLASS_SHM 29 #define SECCLASS_IPC 30 #define SECCLASS_NETLINK_ROUTE_SOCKET 31 #define SECCLASS_NETLINK_TCPDIAG_SOCKET 32 #define SECCLASS_NETLINK_NFLOG_SOCKET 33 #define SECCLASS_NETLINK_XFRM_SOCKET 34 #define SECCLASS_NETLINK_SELINUX_SOCKET 35 #define SECCLASS_NETLINK_ISCSI_SOCKET 36 #define SECCLASS_NETLINK_AUDIT_SOCKET 37 #define SECCLASS_NETLINK_FIB_LOOKUP_SOCKET 38 #define SECCLASS_NETLINK_CONNECTOR_SOCKET 39 #define SECCLASS_NETLINK_NETFILTER_SOCKET 40 #define SECCLASS_NETLINK_DNRT_SOCKET 41 #define SECCLASS_ASSOCIATION 42 #define SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET 43 #define SECCLASS_NETLINK_GENERIC_SOCKET 44 #define SECCLASS_NETLINK_SCSITRANSPORT_SOCKET 45 #define SECCLASS_NETLINK_RDMA_SOCKET 46 #define SECCLASS_NETLINK_CRYPTO_SOCKET 47 #define SECCLASS_APPLETALK_SOCKET 48 #define SECCLASS_PACKET 49 #define SECCLASS_KEY 50 #define SECCLASS_DCCP_SOCKET 51 #define SECCLASS_MEMPROTECT 52 #define SECCLASS_PEER 53 #define SECCLASS_CAPABILITY2 54 #define SECCLASS_KERNEL_SERVICE 55 #define SECCLASS_TUN_SOCKET 56 #define SECCLASS_BINDER 57 #define SECCLASS_CAP_USERNS 58 #define SECCLASS_CAP2_USERNS 59 #define SECCLASS_SCTP_SOCKET 60 #define SECCLASS_ICMP_SOCKET 61 #define SECCLASS_AX25_SOCKET 62 #define SECCLASS_IPX_SOCKET 63 #define SECCLASS_NETROM_SOCKET 64 #define SECCLASS_ATMPVC_SOCKET 65 #define SECCLASS_X25_SOCKET 66 #define SECCLASS_ROSE_SOCKET 67 #define SECCLASS_DECNET_SOCKET 68 #define SECCLASS_ATMSVC_SOCKET 69 #define SECCLASS_RDS_SOCKET 70 #define SECCLASS_IRDA_SOCKET 71 #define SECCLASS_PPPOX_SOCKET 72 #define SECCLASS_LLC_SOCKET 73 #define SECCLASS_CAN_SOCKET 74 #define SECCLASS_TIPC_SOCKET 75 #define SECCLASS_BLUETOOTH_SOCKET 76 #define SECCLASS_IUCV_SOCKET 77 #define SECCLASS_RXRPC_SOCKET 78 #define SECCLASS_ISDN_SOCKET 79 #define SECCLASS_PHONET_SOCKET 80 #define SECCLASS_IEEE802154_SOCKET 81 #define SECCLASS_CAIF_SOCKET 82 #define SECCLASS_ALG_SOCKET 83 #define SECCLASS_NFC_SOCKET 84 #define SECCLASS_VSOCK_SOCKET 85 #define SECCLASS_KCM_SOCKET 86 #define SECCLASS_QIPCRTR_SOCKET 87 #define SECCLASS_SMC_SOCKET 88 #define SECCLASS_INFINIBAND_PKEY 89 #define SECCLASS_INFINIBAND_ENDPORT 90 #define SECCLASS_BPF 91 #define SECCLASS_XDP_SOCKET 92 #define SECCLASS_PERF_EVENT 93 #define SECCLASS_LOCKDOWN 94 #define SECINITSID_KERNEL 1 #define SECINITSID_SECURITY 2 #define SECINITSID_UNLABELED 3 #define SECINITSID_FILE 5 #define SECINITSID_ANY_SOCKET 8 #define SECINITSID_PORT 9 #define SECINITSID_NETIF 10 #define SECINITSID_NETMSG 11 #define SECINITSID_NODE 12 #define SECINITSID_DEVNULL 27 #define SECINITSID_NUM 27 static inline bool security_is_socket_class(u16 kern_tclass) { bool sock = false; switch (kern_tclass) { case SECCLASS_SOCKET: case SECCLASS_TCP_SOCKET: case SECCLASS_UDP_SOCKET: case SECCLASS_RAWIP_SOCKET: case SECCLASS_NETLINK_SOCKET: case SECCLASS_PACKET_SOCKET: case SECCLASS_KEY_SOCKET: case SECCLASS_UNIX_STREAM_SOCKET: case SECCLASS_UNIX_DGRAM_SOCKET: case SECCLASS_NETLINK_ROUTE_SOCKET: case SECCLASS_NETLINK_TCPDIAG_SOCKET: case SECCLASS_NETLINK_NFLOG_SOCKET: case SECCLASS_NETLINK_XFRM_SOCKET: case SECCLASS_NETLINK_SELINUX_SOCKET: case SECCLASS_NETLINK_ISCSI_SOCKET: case SECCLASS_NETLINK_AUDIT_SOCKET: case SECCLASS_NETLINK_FIB_LOOKUP_SOCKET: case SECCLASS_NETLINK_CONNECTOR_SOCKET: case SECCLASS_NETLINK_NETFILTER_SOCKET: case SECCLASS_NETLINK_DNRT_SOCKET: case SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET: case SECCLASS_NETLINK_GENERIC_SOCKET: case SECCLASS_NETLINK_SCSITRANSPORT_SOCKET: case SECCLASS_NETLINK_RDMA_SOCKET: case SECCLASS_NETLINK_CRYPTO_SOCKET: case SECCLASS_APPLETALK_SOCKET: case SECCLASS_DCCP_SOCKET: case SECCLASS_TUN_SOCKET: case SECCLASS_SCTP_SOCKET: case SECCLASS_ICMP_SOCKET: case SECCLASS_AX25_SOCKET: case SECCLASS_IPX_SOCKET: case SECCLASS_NETROM_SOCKET: case SECCLASS_ATMPVC_SOCKET: case SECCLASS_X25_SOCKET: case SECCLASS_ROSE_SOCKET: case SECCLASS_DECNET_SOCKET: case SECCLASS_ATMSVC_SOCKET: case SECCLASS_RDS_SOCKET: case SECCLASS_IRDA_SOCKET: case SECCLASS_PPPOX_SOCKET: case SECCLASS_LLC_SOCKET: case SECCLASS_CAN_SOCKET: case SECCLASS_TIPC_SOCKET: case SECCLASS_BLUETOOTH_SOCKET: case SECCLASS_IUCV_SOCKET: case SECCLASS_RXRPC_SOCKET: case SECCLASS_ISDN_SOCKET: case SECCLASS_PHONET_SOCKET: case SECCLASS_IEEE802154_SOCKET: case SECCLASS_CAIF_SOCKET: case SECCLASS_ALG_SOCKET: case SECCLASS_NFC_SOCKET: case SECCLASS_VSOCK_SOCKET: case SECCLASS_KCM_SOCKET: case SECCLASS_QIPCRTR_SOCKET: case SECCLASS_SMC_SOCKET: case SECCLASS_XDP_SOCKET: sock = true; break; default: break; } return sock; } #endif |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM writeback #if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_WRITEBACK_H #include <linux/tracepoint.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #define show_inode_state(state) \ __print_flags(state, "|", \ {I_DIRTY_SYNC, "I_DIRTY_SYNC"}, \ {I_DIRTY_DATASYNC, "I_DIRTY_DATASYNC"}, \ {I_DIRTY_PAGES, "I_DIRTY_PAGES"}, \ {I_NEW, "I_NEW"}, \ {I_WILL_FREE, "I_WILL_FREE"}, \ {I_FREEING, "I_FREEING"}, \ {I_CLEAR, "I_CLEAR"}, \ {I_SYNC, "I_SYNC"}, \ {I_DIRTY_TIME, "I_DIRTY_TIME"}, \ {I_REFERENCED, "I_REFERENCED"} \ ) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a,b) TRACE_DEFINE_ENUM(a); #define EMe(a,b) TRACE_DEFINE_ENUM(a); #define WB_WORK_REASON \ EM( WB_REASON_BACKGROUND, "background") \ EM( WB_REASON_VMSCAN, "vmscan") \ EM( WB_REASON_SYNC, "sync") \ EM( WB_REASON_PERIODIC, "periodic") \ EM( WB_REASON_LAPTOP_TIMER, "laptop_timer") \ EM( WB_REASON_FS_FREE_SPACE, "fs_free_space") \ EMe(WB_REASON_FORKER_THREAD, "forker_thread") WB_WORK_REASON /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a,b) { a, b }, #define EMe(a,b) { a, b } struct wb_writeback_work; DECLARE_EVENT_CLASS(writeback_page_template, TP_PROTO(struct page *page, struct address_space *mapping), TP_ARGS(page, mapping), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(pgoff_t, index) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); __entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0; __entry->index = page->index; ), TP_printk("bdi %s: ino=%lu index=%lu", __entry->name, (unsigned long)__entry->ino, __entry->index ) ); DEFINE_EVENT(writeback_page_template, writeback_dirty_page, TP_PROTO(struct page *page, struct address_space *mapping), TP_ARGS(page, mapping) ); DEFINE_EVENT(writeback_page_template, wait_on_page_writeback, TP_PROTO(struct page *page, struct address_space *mapping), TP_ARGS(page, mapping) ); DECLARE_EVENT_CLASS(writeback_dirty_inode_template, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, flags) ), TP_fast_assign( struct backing_dev_info *bdi = inode_to_bdi(inode); /* may be called for files on pseudo FSes w/ unregistered bdi */ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->flags = flags; ), TP_printk("bdi %s: ino=%lu state=%s flags=%s", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), show_inode_state(__entry->flags) ) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_mark_inode_dirty, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode_start, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode, TP_PROTO(struct inode *inode, int flags), TP_ARGS(inode, flags) ); #ifdef CREATE_TRACE_POINTS #ifdef CONFIG_CGROUP_WRITEBACK static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return cgroup_ino(wb->memcg_css->cgroup); } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { if (wbc->wb) return __trace_wb_assign_cgroup(wbc->wb); else return 1; } #else /* CONFIG_CGROUP_WRITEBACK */ static inline ino_t __trace_wb_assign_cgroup(struct bdi_writeback *wb) { return 1; } static inline ino_t __trace_wbc_assign_cgroup(struct writeback_control *wbc) { return 1; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* CREATE_TRACE_POINTS */ #ifdef CONFIG_CGROUP_WRITEBACK TRACE_EVENT(inode_foreign_history, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned int history), TP_ARGS(inode, wbc, history), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, cgroup_ino) __field(unsigned int, history) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); __entry->history = history; ), TP_printk("bdi %s: ino=%lu cgroup_ino=%lu history=0x%x", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->cgroup_ino, __entry->history ) ); TRACE_EVENT(inode_switch_wbs, TP_PROTO(struct inode *inode, struct bdi_writeback *old_wb, struct bdi_writeback *new_wb), TP_ARGS(inode, old_wb, new_wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(ino_t, old_cgroup_ino) __field(ino_t, new_cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(old_wb->bdi), 32); __entry->ino = inode->i_ino; __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); ), TP_printk("bdi %s: ino=%lu old_cgroup_ino=%lu new_cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, (unsigned long)__entry->old_cgroup_ino, (unsigned long)__entry->new_cgroup_ino ) ); TRACE_EVENT(track_foreign_dirty, TP_PROTO(struct page *page, struct bdi_writeback *wb), TP_ARGS(page, wb), TP_STRUCT__entry( __array(char, name, 32) __field(u64, bdi_id) __field(ino_t, ino) __field(unsigned int, memcg_id) __field(ino_t, cgroup_ino) __field(ino_t, page_cgroup_ino) ), TP_fast_assign( struct address_space *mapping = page_mapping(page); struct inode *inode = mapping ? mapping->host : NULL; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->bdi_id = wb->bdi->id; __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->page_cgroup_ino = cgroup_ino(page->mem_cgroup->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", __entry->name, __entry->bdi_id, (unsigned long)__entry->ino, __entry->memcg_id, (unsigned long)__entry->cgroup_ino, (unsigned long)__entry->page_cgroup_ino ) ); TRACE_EVENT(flush_foreign, TP_PROTO(struct bdi_writeback *wb, unsigned int frn_bdi_id, unsigned int frn_memcg_id), TP_ARGS(wb, frn_bdi_id, frn_memcg_id), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) __field(unsigned int, frn_bdi_id) __field(unsigned int, frn_memcg_id) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->frn_bdi_id = frn_bdi_id; __entry->frn_memcg_id = frn_memcg_id; ), TP_printk("bdi %s: cgroup_ino=%lu frn_bdi_id=%u frn_memcg_id=%u", __entry->name, (unsigned long)__entry->cgroup_ino, __entry->frn_bdi_id, __entry->frn_memcg_id ) ); #endif DECLARE_EVENT_CLASS(writeback_write_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), TP_STRUCT__entry ( __array(char, name, 32) __field(ino_t, ino) __field(int, sync_mode) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, __entry->sync_mode, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DEFINE_EVENT(writeback_write_inode_template, writeback_write_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc) ); DECLARE_EVENT_CLASS(writeback_work_class, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), TP_ARGS(wb, work), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_pages) __field(dev_t, sb_dev) __field(int, sync_mode) __field(int, for_kupdate) __field(int, range_cyclic) __field(int, for_background) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; __entry->for_kupdate = work->for_kupdate; __entry->range_cyclic = work->range_cyclic; __entry->for_background = work->for_background; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%lu", __entry->name, MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), __entry->nr_pages, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, __entry->for_background, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_WORK_EVENT(name) \ DEFINE_EVENT(writeback_work_class, name, \ TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work), \ TP_ARGS(wb, work)) DEFINE_WRITEBACK_WORK_EVENT(writeback_queue); DEFINE_WRITEBACK_WORK_EVENT(writeback_exec); DEFINE_WRITEBACK_WORK_EVENT(writeback_start); DEFINE_WRITEBACK_WORK_EVENT(writeback_written); DEFINE_WRITEBACK_WORK_EVENT(writeback_wait); TRACE_EVENT(writeback_pages_written, TP_PROTO(long pages_written), TP_ARGS(pages_written), TP_STRUCT__entry( __field(long, pages) ), TP_fast_assign( __entry->pages = pages_written; ), TP_printk("%ld", __entry->pages) ); DECLARE_EVENT_CLASS(writeback_class, TP_PROTO(struct bdi_writeback *wb), TP_ARGS(wb), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: cgroup_ino=%lu", __entry->name, (unsigned long)__entry->cgroup_ino ) ); #define DEFINE_WRITEBACK_EVENT(name) \ DEFINE_EVENT(writeback_class, name, \ TP_PROTO(struct bdi_writeback *wb), \ TP_ARGS(wb)) DEFINE_WRITEBACK_EVENT(writeback_wake_background); TRACE_EVENT(writeback_bdi_register, TP_PROTO(struct backing_dev_info *bdi), TP_ARGS(bdi), TP_STRUCT__entry( __array(char, name, 32) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); ), TP_printk("bdi %s", __entry->name ) ); DECLARE_EVENT_CLASS(wbc_class, TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), TP_ARGS(wbc, bdi), TP_STRUCT__entry( __array(char, name, 32) __field(long, nr_to_write) __field(long, pages_skipped) __field(int, sync_mode) __field(int, for_kupdate) __field(int, for_background) __field(int, for_reclaim) __field(int, range_cyclic) __field(long, range_start) __field(long, range_end) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->sync_mode = wbc->sync_mode; __entry->for_kupdate = wbc->for_kupdate; __entry->for_background = wbc->for_background; __entry->for_reclaim = wbc->for_reclaim; __entry->range_cyclic = wbc->range_cyclic; __entry->range_start = (long)wbc->range_start; __entry->range_end = (long)wbc->range_end; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d " "bgrd=%d reclm=%d cyclic=%d " "start=0x%lx end=0x%lx cgroup_ino=%lu", __entry->name, __entry->nr_to_write, __entry->pages_skipped, __entry->sync_mode, __entry->for_kupdate, __entry->for_background, __entry->for_reclaim, __entry->range_cyclic, __entry->range_start, __entry->range_end, (unsigned long)__entry->cgroup_ino ) ) #define DEFINE_WBC_EVENT(name) \ DEFINE_EVENT(wbc_class, name, \ TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \ TP_ARGS(wbc, bdi)) DEFINE_WBC_EVENT(wbc_writepage); TRACE_EVENT(writeback_queue_io, TP_PROTO(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before, int moved), TP_ARGS(wb, work, dirtied_before, moved), TP_STRUCT__entry( __array(char, name, 32) __field(unsigned long, older) __field(long, age) __field(int, moved) __field(int, reason) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->older = dirtied_before; __entry->age = (jiffies - dirtied_before) * 1000 / HZ; __entry->moved = moved; __entry->reason = work->reason; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%lu", __entry->name, __entry->older, /* dirtied_before in jiffies */ __entry->age, /* dirtied_before in relative milliseconds */ __entry->moved, __print_symbolic(__entry->reason, WB_WORK_REASON), (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(global_dirty_state, TP_PROTO(unsigned long background_thresh, unsigned long dirty_thresh ), TP_ARGS(background_thresh, dirty_thresh ), TP_STRUCT__entry( __field(unsigned long, nr_dirty) __field(unsigned long, nr_writeback) __field(unsigned long, background_thresh) __field(unsigned long, dirty_thresh) __field(unsigned long, dirty_limit) __field(unsigned long, nr_dirtied) __field(unsigned long, nr_written) ), TP_fast_assign( __entry->nr_dirty = global_node_page_state(NR_FILE_DIRTY); __entry->nr_writeback = global_node_page_state(NR_WRITEBACK); __entry->nr_dirtied = global_node_page_state(NR_DIRTIED); __entry->nr_written = global_node_page_state(NR_WRITTEN); __entry->background_thresh = background_thresh; __entry->dirty_thresh = dirty_thresh; __entry->dirty_limit = global_wb_domain.dirty_limit; ), TP_printk("dirty=%lu writeback=%lu " "bg_thresh=%lu thresh=%lu limit=%lu " "dirtied=%lu written=%lu", __entry->nr_dirty, __entry->nr_writeback, __entry->background_thresh, __entry->dirty_thresh, __entry->dirty_limit, __entry->nr_dirtied, __entry->nr_written ) ); #define KBps(x) ((x) << (PAGE_SHIFT - 10)) TRACE_EVENT(bdi_dirty_ratelimit, TP_PROTO(struct bdi_writeback *wb, unsigned long dirty_rate, unsigned long task_ratelimit), TP_ARGS(wb, dirty_rate, task_ratelimit), TP_STRUCT__entry( __array(char, bdi, 32) __field(unsigned long, write_bw) __field(unsigned long, avg_write_bw) __field(unsigned long, dirty_rate) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned long, balanced_dirty_ratelimit) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->write_bw = KBps(wb->write_bandwidth); __entry->avg_write_bw = KBps(wb->avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); __entry->dirty_ratelimit = KBps(wb->dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->balanced_dirty_ratelimit = KBps(wb->balanced_dirty_ratelimit); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "write_bw=%lu awrite_bw=%lu dirty_rate=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "balanced_dirty_ratelimit=%lu cgroup_ino=%lu", __entry->bdi, __entry->write_bw, /* write bandwidth */ __entry->avg_write_bw, /* avg write bandwidth */ __entry->dirty_rate, /* bdi dirty rate */ __entry->dirty_ratelimit, /* base ratelimit */ __entry->task_ratelimit, /* ratelimit with position control */ __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(balance_dirty_pages, TP_PROTO(struct bdi_writeback *wb, unsigned long thresh, unsigned long bg_thresh, unsigned long dirty, unsigned long bdi_thresh, unsigned long bdi_dirty, unsigned long dirty_ratelimit, unsigned long task_ratelimit, unsigned long dirtied, unsigned long period, long pause, unsigned long start_time), TP_ARGS(wb, thresh, bg_thresh, dirty, bdi_thresh, bdi_dirty, dirty_ratelimit, task_ratelimit, dirtied, period, pause, start_time), TP_STRUCT__entry( __array( char, bdi, 32) __field(unsigned long, limit) __field(unsigned long, setpoint) __field(unsigned long, dirty) __field(unsigned long, bdi_setpoint) __field(unsigned long, bdi_dirty) __field(unsigned long, dirty_ratelimit) __field(unsigned long, task_ratelimit) __field(unsigned int, dirtied) __field(unsigned int, dirtied_pause) __field(unsigned long, paused) __field( long, pause) __field(unsigned long, period) __field( long, think) __field(ino_t, cgroup_ino) ), TP_fast_assign( unsigned long freerun = (thresh + bg_thresh) / 2; strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->limit = global_wb_domain.dirty_limit; __entry->setpoint = (global_wb_domain.dirty_limit + freerun) / 2; __entry->dirty = dirty; __entry->bdi_setpoint = __entry->setpoint * bdi_thresh / (thresh + 1); __entry->bdi_dirty = bdi_dirty; __entry->dirty_ratelimit = KBps(dirty_ratelimit); __entry->task_ratelimit = KBps(task_ratelimit); __entry->dirtied = dirtied; __entry->dirtied_pause = current->nr_dirtied_pause; __entry->think = current->dirty_paused_when == 0 ? 0 : (long)(jiffies - current->dirty_paused_when) * 1000/HZ; __entry->period = period * 1000 / HZ; __entry->pause = pause * 1000 / HZ; __entry->paused = (jiffies - start_time) * 1000 / HZ; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: " "limit=%lu setpoint=%lu dirty=%lu " "bdi_setpoint=%lu bdi_dirty=%lu " "dirty_ratelimit=%lu task_ratelimit=%lu " "dirtied=%u dirtied_pause=%u " "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%lu", __entry->bdi, __entry->limit, __entry->setpoint, __entry->dirty, __entry->bdi_setpoint, __entry->bdi_dirty, __entry->dirty_ratelimit, __entry->task_ratelimit, __entry->dirtied, __entry->dirtied_pause, __entry->paused, /* ms */ __entry->pause, /* ms */ __entry->period, /* ms */ __entry->think, /* ms */ (unsigned long)__entry->cgroup_ino ) ); TRACE_EVENT(writeback_sb_inodes_requeue, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode)); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, (unsigned long)__entry->cgroup_ino ) ); DECLARE_EVENT_CLASS(writeback_congest_waited_template, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), TP_ARGS(usec_timeout, usec_delayed), TP_STRUCT__entry( __field( unsigned int, usec_timeout ) __field( unsigned int, usec_delayed ) ), TP_fast_assign( __entry->usec_timeout = usec_timeout; __entry->usec_delayed = usec_delayed; ), TP_printk("usec_timeout=%u usec_delayed=%u", __entry->usec_timeout, __entry->usec_delayed) ); DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), TP_ARGS(usec_timeout, usec_delayed) ); DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested, TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), TP_ARGS(usec_timeout, usec_delayed) ); DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write ), TP_ARGS(inode, wbc, nr_to_write), TP_STRUCT__entry( __array(char, name, 32) __field(ino_t, ino) __field(unsigned long, state) __field(unsigned long, dirtied_when) __field(unsigned long, writeback_index) __field(long, nr_to_write) __field(unsigned long, wrote) __field(ino_t, cgroup_ino) ), TP_fast_assign( strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->nr_to_write = nr_to_write; __entry->wrote = nr_to_write - wbc->nr_to_write; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); ), TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu " "index=%lu to_write=%ld wrote=%lu cgroup_ino=%lu", __entry->name, (unsigned long)__entry->ino, show_inode_state(__entry->state), __entry->dirtied_when, (jiffies - __entry->dirtied_when) / HZ, __entry->writeback_index, __entry->nr_to_write, __entry->wrote, (unsigned long)__entry->cgroup_ino ) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode_start, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DEFINE_EVENT(writeback_single_inode_template, writeback_single_inode, TP_PROTO(struct inode *inode, struct writeback_control *wbc, unsigned long nr_to_write), TP_ARGS(inode, wbc, nr_to_write) ); DECLARE_EVENT_CLASS(writeback_inode_template, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field(unsigned long, state ) __field( __u16, mode ) __field(unsigned long, dirtied_when ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->mode = inode->i_mode; __entry->dirtied_when = inode->dirtied_when; ), TP_printk("dev %d,%d ino %lu dirtied %lu state %s mode 0%o", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long)__entry->ino, __entry->dirtied_when, show_inode_state(__entry->state), __entry->mode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_lazytime_iput, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, writeback_dirty_inode_enqueue, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); /* * Inode writeback list tracking. */ DEFINE_EVENT(writeback_inode_template, sb_mark_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); DEFINE_EVENT(writeback_inode_template, sb_clear_inode_writeback, TP_PROTO(struct inode *inode), TP_ARGS(inode) ); #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 | // SPDX-License-Identifier: GPL-2.0-or-later /* Common capabilities, needed by capability.o. */ #include <linux/capability.h> #include <linux/audit.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/lsm_hooks.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/ptrace.h> #include <linux/xattr.h> #include <linux/hugetlb.h> #include <linux/mount.h> #include <linux/sched.h> #include <linux/prctl.h> #include <linux/securebits.h> #include <linux/user_namespace.h> #include <linux/binfmts.h> #include <linux/personality.h> /* * If a non-root user executes a setuid-root binary in * !secure(SECURE_NOROOT) mode, then we raise capabilities. * However if fE is also set, then the intent is for only * the file capabilities to be applied, and the setuid-root * bit is left on either to change the uid (plausible) or * to get full privilege on a kernel without file capabilities * support. So in that case we do not raise capabilities. * * Warn if that happens, once per boot. */ static void warn_setuid_and_fcaps_mixed(const char *fname) { static int warned; if (!warned) { printk(KERN_INFO "warning: `%s' has both setuid-root and" " effective capabilities. Therefore not raising all" " capabilities.\n", fname); warned = 1; } } /** * cap_capable - Determine whether a task has a particular effective capability * @cred: The credentials to use * @ns: The user namespace in which we need the capability * @cap: The capability to check for * @opts: Bitmask of options defined in include/linux/security.h * * Determine whether the nominated task has the specified capability amongst * its effective set, returning 0 if it does, -ve if it does not. * * NOTE WELL: cap_has_capability() cannot be used like the kernel's capable() * and has_capability() functions. That is, it has the reverse semantics: * cap_has_capability() returns 0 when a task has a capability, but the * kernel's capable() and has_capability() returns 1 for this case. */ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, int cap, unsigned int opts) { struct user_namespace *ns = targ_ns; /* See if cred has the capability in the target user namespace * by examining the target user namespace and all of the target * user namespace's parents. */ for (;;) { /* Do we have the necessary capabilities? */ if (ns == cred->user_ns) return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM; /* * If we're already at a lower level than we're looking for, * we're done searching. */ if (ns->level <= cred->user_ns->level) return -EPERM; /* * The owner of the user namespace in the parent of the * user namespace has all caps. */ if ((ns->parent == cred->user_ns) && uid_eq(ns->owner, cred->euid)) return 0; /* * If you have a capability in a parent user ns, then you have * it over all children user namespaces as well. */ ns = ns->parent; } /* We never get here */ } /** * cap_settime - Determine whether the current process may set the system clock * @ts: The time to set * @tz: The timezone to set * * Determine whether the current process may set the system clock and timezone * information, returning 0 if permission granted, -ve if denied. */ int cap_settime(const struct timespec64 *ts, const struct timezone *tz) { if (!capable(CAP_SYS_TIME)) return -EPERM; return 0; } /** * cap_ptrace_access_check - Determine whether the current process may access * another * @child: The process to be accessed * @mode: The mode of attachment. * * If we are in the same or an ancestor user_ns and have all the target * task's capabilities, then ptrace access is allowed. * If we have the ptrace capability to the target user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether a process may access another, returning 0 if permission * granted, -ve if denied. */ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode) { int ret = 0; const struct cred *cred, *child_cred; const kernel_cap_t *caller_caps; rcu_read_lock(); cred = current_cred(); child_cred = __task_cred(child); if (mode & PTRACE_MODE_FSCREDS) caller_caps = &cred->cap_effective; else caller_caps = &cred->cap_permitted; if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, *caller_caps)) goto out; if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_ptrace_traceme - Determine whether another process may trace the current * @parent: The task proposed to be the tracer * * If parent is in the same or an ancestor user_ns and has all current's * capabilities, then ptrace access is allowed. * If parent has the ptrace capability to current's user_ns, then ptrace * access is allowed. * Else denied. * * Determine whether the nominated task is permitted to trace the current * process, returning 0 if permission is granted, -ve if denied. */ int cap_ptrace_traceme(struct task_struct *parent) { int ret = 0; const struct cred *cred, *child_cred; rcu_read_lock(); cred = __task_cred(parent); child_cred = current_cred(); if (cred->user_ns == child_cred->user_ns && cap_issubset(child_cred->cap_permitted, cred->cap_permitted)) goto out; if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE)) goto out; ret = -EPERM; out: rcu_read_unlock(); return ret; } /** * cap_capget - Retrieve a task's capability sets * @target: The task from which to retrieve the capability sets * @effective: The place to record the effective set * @inheritable: The place to record the inheritable set * @permitted: The place to record the permitted set * * This function retrieves the capabilities of the nominated task and returns * them to the caller. */ int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { const struct cred *cred; /* Derived from kernel/capability.c:sys_capget. */ rcu_read_lock(); cred = __task_cred(target); *effective = cred->cap_effective; *inheritable = cred->cap_inheritable; *permitted = cred->cap_permitted; rcu_read_unlock(); return 0; } /* * Determine whether the inheritable capabilities are limited to the old * permitted set. Returns 1 if they are limited, 0 if they are not. */ static inline int cap_inh_is_capped(void) { /* they are so limited unless the current task has the CAP_SETPCAP * capability */ if (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) == 0) return 0; return 1; } /** * cap_capset - Validate and apply proposed changes to current's capabilities * @new: The proposed new credentials; alterations should be made here * @old: The current task's current credentials * @effective: A pointer to the proposed new effective capabilities set * @inheritable: A pointer to the proposed new inheritable capabilities set * @permitted: A pointer to the proposed new permitted capabilities set * * This function validates and applies a proposed mass change to the current * process's capability sets. The changes are made to the proposed new * credentials, and assuming no error, will be committed by the caller of LSM. */ int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { if (cap_inh_is_capped() && !cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_permitted))) /* incapable of using this inheritable set */ return -EPERM; if (!cap_issubset(*inheritable, cap_combine(old->cap_inheritable, old->cap_bset))) /* no new pI capabilities outside bounding set */ return -EPERM; /* verify restrictions on target's new Permitted set */ if (!cap_issubset(*permitted, old->cap_permitted)) return -EPERM; /* verify the _new_Effective_ is a subset of the _new_Permitted_ */ if (!cap_issubset(*effective, *permitted)) return -EPERM; new->cap_effective = *effective; new->cap_inheritable = *inheritable; new->cap_permitted = *permitted; /* * Mask off ambient bits that are no longer both permitted and * inheritable. */ new->cap_ambient = cap_intersect(new->cap_ambient, cap_intersect(*permitted, *inheritable)); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EINVAL; return 0; } /** * cap_inode_need_killpriv - Determine if inode change affects privileges * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV * * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV * affects the security markings on that inode, and if it is, should * inode_killpriv() be invoked or the change rejected. * * Returns 1 if security.capability has a value, meaning inode_killpriv() * is required, 0 otherwise, meaning inode_killpriv() is not required. */ int cap_inode_need_killpriv(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); int error; error = __vfs_getxattr(dentry, inode, XATTR_NAME_CAPS, NULL, 0); return error > 0; } /** * cap_inode_killpriv - Erase the security markings on an inode * @dentry: The inode/dentry to alter * * Erase the privilege-enhancing security markings on an inode. * * Returns 0 if successful, -ve on error. */ int cap_inode_killpriv(struct dentry *dentry) { int error; error = __vfs_removexattr(dentry, XATTR_NAME_CAPS); if (error == -EOPNOTSUPP) error = 0; return error; } static bool rootid_owns_currentns(kuid_t kroot) { struct user_namespace *ns; if (!uid_valid(kroot)) return false; for (ns = current_user_ns(); ; ns = ns->parent) { if (from_kuid(ns, kroot) == 0) return true; if (ns == &init_user_ns) break; } return false; } static __u32 sansflags(__u32 m) { return m & ~VFS_CAP_FLAGS_EFFECTIVE; } static bool is_v2header(size_t size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_2) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_2; } static bool is_v3header(size_t size, const struct vfs_cap_data *cap) { if (size != XATTR_CAPS_SZ_3) return false; return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_3; } /* * getsecurity: We are called for security.* before any attempt to read the * xattr from the inode itself. * * This gives us a chance to read the on-disk value and convert it. If we * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler. * * Note we are not called by vfs_getxattr_alloc(), but that is only called * by the integrity subsystem, which really wants the unconverted values - * so that's good. */ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) { int size, ret; kuid_t kroot; u32 nsmagic, magic; uid_t root, mappedroot; char *tmpbuf = NULL; struct vfs_cap_data *cap; struct vfs_ns_cap_data *nscap = NULL; struct dentry *dentry; struct user_namespace *fs_ns; if (strcmp(name, "capability") != 0) return -EOPNOTSUPP; dentry = d_find_any_alias(inode); if (!dentry) return -EINVAL; size = sizeof(struct vfs_ns_cap_data); ret = (int) vfs_getxattr_alloc(dentry, XATTR_NAME_CAPS, &tmpbuf, size, GFP_NOFS); dput(dentry); if (ret < 0 || !tmpbuf) { size = ret; goto out_free; } fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; if (is_v2header((size_t) ret, cap)) { root = 0; } else if (is_v3header((size_t) ret, cap)) { nscap = (struct vfs_ns_cap_data *) tmpbuf; root = le32_to_cpu(nscap->rootid); } else { size = -EINVAL; goto out_free; } kroot = make_kuid(fs_ns, root); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ mappedroot = from_kuid(current_user_ns(), kroot); if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { size = sizeof(struct vfs_ns_cap_data); if (alloc) { if (!nscap) { /* v2 -> v3 conversion */ nscap = kzalloc(size, GFP_ATOMIC); if (!nscap) { size = -ENOMEM; goto out_free; } nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); nscap->magic_etc = cpu_to_le32(nsmagic); } else { /* use allocated v3 buffer */ tmpbuf = NULL; } nscap->rootid = cpu_to_le32(mappedroot); *buffer = nscap; } goto out_free; } if (!rootid_owns_currentns(kroot)) { size = -EOVERFLOW; goto out_free; } /* This comes from a parent namespace. Return as a v2 capability */ size = sizeof(struct vfs_cap_data); if (alloc) { if (nscap) { /* v3 -> v2 conversion */ cap = kzalloc(size, GFP_ATOMIC); if (!cap) { size = -ENOMEM; goto out_free; } magic = VFS_CAP_REVISION_2; nsmagic = le32_to_cpu(nscap->magic_etc); if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) magic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); cap->magic_etc = cpu_to_le32(magic); } else { /* use unconverted v2 */ tmpbuf = NULL; } *buffer = cap; } out_free: kfree(tmpbuf); return size; } static kuid_t rootid_from_xattr(const void *value, size_t size, struct user_namespace *task_ns) { const struct vfs_ns_cap_data *nscap = value; uid_t rootid = 0; if (size == XATTR_CAPS_SZ_3) rootid = le32_to_cpu(nscap->rootid); return make_kuid(task_ns, rootid); } static bool validheader(size_t size, const struct vfs_cap_data *cap) { return is_v2header(size, cap) || is_v3header(size, cap); } /* * User requested a write of security.capability. If needed, update the * xattr to change from v2 to v3, or to fixup the v3 rootid. * * If all is ok, we return the new size, on error return < 0. */ int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size) { struct vfs_ns_cap_data *nscap; uid_t nsrootid; const struct vfs_cap_data *cap = *ivalue; __u32 magic, nsmagic; struct inode *inode = d_backing_inode(dentry); struct user_namespace *task_ns = current_user_ns(), *fs_ns = inode->i_sb->s_user_ns; kuid_t rootid; size_t newsize; if (!*ivalue) return -EINVAL; if (!validheader(size, cap)) return -EINVAL; if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP)) return -EPERM; if (size == XATTR_CAPS_SZ_2) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; rootid = rootid_from_xattr(*ivalue, size, task_ns); if (!uid_valid(rootid)) return -EINVAL; nsrootid = from_kuid(fs_ns, rootid); if (nsrootid == -1) return -EINVAL; newsize = sizeof(struct vfs_ns_cap_data); nscap = kmalloc(newsize, GFP_ATOMIC); if (!nscap) return -ENOMEM; nscap->rootid = cpu_to_le32(nsrootid); nsmagic = VFS_CAP_REVISION_3; magic = le32_to_cpu(cap->magic_etc); if (magic & VFS_CAP_FLAGS_EFFECTIVE) nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; nscap->magic_etc = cpu_to_le32(nsmagic); memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); kvfree(*ivalue); *ivalue = nscap; return newsize; } /* * Calculate the new process capability sets from the capability sets attached * to a file. */ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, struct linux_binprm *bprm, bool *effective, bool *has_fcap) { struct cred *new = bprm->cred; unsigned i; int ret = 0; if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) *effective = true; if (caps->magic_etc & VFS_CAP_REVISION_MASK) *has_fcap = true; CAP_FOR_EACH_U32(i) { __u32 permitted = caps->permitted.cap[i]; __u32 inheritable = caps->inheritable.cap[i]; /* * pP' = (X & fP) | (pI & fI) * The addition of pA' is handled later. */ new->cap_permitted.cap[i] = (new->cap_bset.cap[i] & permitted) | (new->cap_inheritable.cap[i] & inheritable); if (permitted & ~new->cap_permitted.cap[i]) /* insufficient to execute correctly */ ret = -EPERM; } /* * For legacy apps, with no internal support for recognizing they * do not have enough capabilities, we return an error if they are * missing some "forced" (aka file-permitted) capabilities. */ return *effective ? ret : 0; } /* * Extract the on-exec-apply capability sets for an executable file. */ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) { struct inode *inode = d_backing_inode(dentry); __u32 magic_etc; unsigned tocopy, i; int size; struct vfs_ns_cap_data data, *nscaps = &data; struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; kuid_t rootkuid; struct user_namespace *fs_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); if (!inode) return -ENODATA; fs_ns = inode->i_sb->s_user_ns; size = __vfs_getxattr((struct dentry *)dentry, inode, XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ); if (size == -ENODATA || size == -EOPNOTSUPP) /* no data, that's ok */ return -ENODATA; if (size < 0) return size; if (size < sizeof(magic_etc)) return -EINVAL; cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc); rootkuid = make_kuid(fs_ns, 0); switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) return -EINVAL; tocopy = VFS_CAP_U32_1; break; case VFS_CAP_REVISION_2: if (size != XATTR_CAPS_SZ_2) return -EINVAL; tocopy = VFS_CAP_U32_2; break; case VFS_CAP_REVISION_3: if (size != XATTR_CAPS_SZ_3) return -EINVAL; tocopy = VFS_CAP_U32_3; rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); break; default: return -EINVAL; } /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ if (!rootid_owns_currentns(rootkuid)) return -ENODATA; CAP_FOR_EACH_U32(i) { if (i >= tocopy) break; cpu_caps->permitted.cap[i] = le32_to_cpu(caps->data[i].permitted); cpu_caps->inheritable.cap[i] = le32_to_cpu(caps->data[i].inheritable); } cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; cpu_caps->rootid = rootkuid; return 0; } /* * Attempt to get the on-exec apply capability sets for an executable file from * its xattrs and, if present, apply them to the proposed credentials being * constructed by execve(). */ static int get_file_caps(struct linux_binprm *bprm, struct file *file, bool *effective, bool *has_fcap) { int rc = 0; struct cpu_vfs_cap_data vcaps; cap_clear(bprm->cred->cap_permitted); if (!file_caps_enabled) return 0; if (!mnt_may_suid(file->f_path.mnt)) return 0; /* * This check is redundant with mnt_may_suid() but is kept to make * explicit that capability bits are limited to s_user_ns and its * descendants. */ if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns)) return 0; rc = get_vfs_caps_from_disk(file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", bprm->filename); else if (rc == -ENODATA) rc = 0; goto out; } rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_fcap); out: if (rc) cap_clear(bprm->cred->cap_permitted); return rc; } static inline bool root_privileged(void) { return !issecure(SECURE_NOROOT); } static inline bool __is_real(kuid_t uid, struct cred *cred) { return uid_eq(cred->uid, uid); } static inline bool __is_eff(kuid_t uid, struct cred *cred) { return uid_eq(cred->euid, uid); } static inline bool __is_suid(kuid_t uid, struct cred *cred) { return !__is_real(uid, cred) && __is_eff(uid, cred); } /* * handle_privileged_root - Handle case of privileged root * @bprm: The execution parameters, including the proposed creds * @has_fcap: Are any file capabilities set? * @effective: Do we have effective root privilege? * @root_uid: This namespace' root UID WRT initial USER namespace * * Handle the case where root is privileged and hasn't been neutered by * SECURE_NOROOT. If file capabilities are set, they won't be combined with * set UID root and nothing is changed. If we are root, cap_permitted is * updated. If we have become set UID root, the effective bit is set. */ static void handle_privileged_root(struct linux_binprm *bprm, bool has_fcap, bool *effective, kuid_t root_uid) { const struct cred *old = current_cred(); struct cred *new = bprm->cred; if (!root_privileged()) return; /* * If the legacy file capability is set, then don't set privs * for a setuid root binary run by a non-root user. Do set it * for a root user just to cause least surprise to an admin. */ if (has_fcap && __is_suid(root_uid, new)) { warn_setuid_and_fcaps_mixed(bprm->filename); return; } /* * To support inheritance of root-permissions and suid-root * executables under compatibility mode, we override the * capability sets for the file. */ if (__is_eff(root_uid, new) || __is_real(root_uid, new)) { /* pP' = (cap_bset & ~0) | (pI & ~0) */ new->cap_permitted = cap_combine(old->cap_bset, old->cap_inheritable); } /* * If only the real uid is 0, we do not set the effective bit. */ if (__is_eff(root_uid, new)) *effective = true; } #define __cap_gained(field, target, source) \ !cap_issubset(target->cap_##field, source->cap_##field) #define __cap_grew(target, source, cred) \ !cap_issubset(cred->cap_##target, cred->cap_##source) #define __cap_full(field, cred) \ cap_issubset(CAP_FULL_SET, cred->cap_##field) static inline bool __is_setuid(struct cred *new, const struct cred *old) { return !uid_eq(new->euid, old->uid); } static inline bool __is_setgid(struct cred *new, const struct cred *old) { return !gid_eq(new->egid, old->gid); } /* * 1) Audit candidate if current->cap_effective is set * * We do not bother to audit if 3 things are true: * 1) cap_effective has all caps * 2) we became root *OR* are were already root * 3) root is supposed to have all caps (SECURE_NOROOT) * Since this is just a normal root execing a process. * * Number 1 above might fail if you don't have a full bset, but I think * that is interesting information to audit. * * A number of other conditions require logging: * 2) something prevented setuid root getting all caps * 3) non-setuid root gets fcaps * 4) non-setuid root gets ambient */ static inline bool nonroot_raised_pE(struct cred *new, const struct cred *old, kuid_t root, bool has_fcap) { bool ret = false; if ((__cap_grew(effective, ambient, new) && !(__cap_full(effective, new) && (__is_eff(root, new) || __is_real(root, new)) && root_privileged())) || (root_privileged() && __is_suid(root, new) && !__cap_full(effective, new)) || (!__is_setuid(new, old) && ((has_fcap && __cap_gained(permitted, new, old)) || __cap_gained(ambient, new, old)))) ret = true; return ret; } /** * cap_bprm_creds_from_file - Set up the proposed credentials for execve(). * @bprm: The execution parameters, including the proposed creds * @file: The file to pull the credentials from * * Set up the proposed credentials for a new execution context being * constructed by execve(). The proposed creds in @bprm->cred is altered, * which won't take effect immediately. Returns 0 if successful, -ve on error. */ int cap_bprm_creds_from_file(struct linux_binprm *bprm, struct file *file) { /* Process setpcap binaries and capabilities for uid 0 */ const struct cred *old = current_cred(); struct cred *new = bprm->cred; bool effective = false, has_fcap = false, is_setid; int ret; kuid_t root_uid; if (WARN_ON(!cap_ambient_invariant_ok(old))) return -EPERM; ret = get_file_caps(bprm, file, &effective, &has_fcap); if (ret < 0) return ret; root_uid = make_kuid(new->user_ns, 0); handle_privileged_root(bprm, has_fcap, &effective, root_uid); /* if we have fs caps, clear dangerous personality flags */ if (__cap_gained(permitted, new, old)) bprm->per_clear |= PER_CLEAR_ON_SETID; /* Don't let someone trace a set[ug]id/setpcap binary with the revised * credentials unless they have the appropriate permit. * * In addition, if NO_NEW_PRIVS, then ensure we get no new privs. */ is_setid = __is_setuid(new, old) || __is_setgid(new, old); if ((is_setid || __cap_gained(permitted, new, old)) && ((bprm->unsafe & ~LSM_UNSAFE_PTRACE) || !ptracer_capable(current, new->user_ns))) { /* downgrade; they get no more than they had, and maybe less */ if (!ns_capable(new->user_ns, CAP_SETUID) || (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) { new->euid = new->uid; new->egid = new->gid; } new->cap_permitted = cap_intersect(new->cap_permitted, old->cap_permitted); } new->suid = new->fsuid = new->euid; new->sgid = new->fsgid = new->egid; /* File caps or setid cancels ambient. */ if (has_fcap || is_setid) cap_clear(new->cap_ambient); /* * Now that we've computed pA', update pP' to give: * pP' = (X & fP) | (pI & fI) | pA' */ new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient); /* * Set pE' = (fE ? pP' : pA'). Because pA' is zero if fE is set, * this is the same as pE' = (fE ? pP' : 0) | pA'. */ if (effective) new->cap_effective = new->cap_permitted; else new->cap_effective = new->cap_ambient; if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; if (nonroot_raised_pE(new, old, root_uid, has_fcap)) { ret = audit_log_bprm_fcaps(bprm, new, old); if (ret < 0) return ret; } new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; /* Check for privilege-elevated exec. */ if (is_setid || (!__is_real(root_uid, new) && (effective || __cap_grew(permitted, ambient, new)))) bprm->secureexec = 1; return 0; } /** * cap_inode_setxattr - Determine whether an xattr may be altered * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * @value: The value that the xattr will be changed to * @size: The size of value * @flags: The replacement flag * * Determine whether an xattr may be altered or set on an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get updated or set by those * who aren't privileged to do so. */ int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; /* * For XATTR_NAME_CAPS the check will be done in * cap_convert_nscap(), called by setxattr() */ if (strcmp(name, XATTR_NAME_CAPS) == 0) return 0; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /** * cap_inode_removexattr - Determine whether an xattr may be removed * @dentry: The inode/dentry being altered * @name: The name of the xattr to be changed * * Determine whether an xattr may be removed from an inode, returning 0 if * permission is granted, -ve if denied. * * This is used to make sure security xattrs don't get removed by those who * aren't privileged to remove them. */ int cap_inode_removexattr(struct dentry *dentry, const char *name) { struct user_namespace *user_ns = dentry->d_sb->s_user_ns; /* Ignore non-security xattrs */ if (strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) != 0) return 0; if (strcmp(name, XATTR_NAME_CAPS) == 0) { /* security.capability gets namespaced */ struct inode *inode = d_backing_inode(dentry); if (!inode) return -EINVAL; if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP)) return -EPERM; return 0; } if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; return 0; } /* * cap_emulate_setxuid() fixes the effective / permitted capabilities of * a process after a call to setuid, setreuid, or setresuid. * * 1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of * {r,e,s}uid != 0, the permitted and effective capabilities are * cleared. * * 2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective * capabilities of the process are cleared. * * 3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective * capabilities are set to the permitted capabilities. * * fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should * never happen. * * -astor * * cevans - New behaviour, Oct '99 * A process may, via prctl(), elect to keep its capabilities when it * calls setuid() and switches away from uid==0. Both permitted and * effective sets will be retained. * Without this change, it was impossible for a daemon to drop only some * of its privilege. The call to setuid(!=0) would drop all privileges! * Keeping uid 0 is not an option because uid 0 owns too many vital * files.. * Thanks to Olaf Kirch and Peter Benie for spotting this. */ static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old) { kuid_t root_uid = make_kuid(old->user_ns, 0); if ((uid_eq(old->uid, root_uid) || uid_eq(old->euid, root_uid) || uid_eq(old->suid, root_uid)) && (!uid_eq(new->uid, root_uid) && !uid_eq(new->euid, root_uid) && !uid_eq(new->suid, root_uid))) { if (!issecure(SECURE_KEEP_CAPS)) { cap_clear(new->cap_permitted); cap_clear(new->cap_effective); } /* * Pre-ambient programs expect setresuid to nonroot followed * by exec to drop capabilities. We should make sure that * this remains the case. */ cap_clear(new->cap_ambient); } if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid)) cap_clear(new->cap_effective); if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid)) new->cap_effective = new->cap_permitted; } /** * cap_task_fix_setuid - Fix up the results of setuid() call * @new: The proposed credentials * @old: The current task's current credentials * @flags: Indications of what has changed * * Fix up the results of setuid() call before the credential changes are * actually applied, returning 0 to grant the changes, -ve to deny them. */ int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { switch (flags) { case LSM_SETID_RE: case LSM_SETID_ID: case LSM_SETID_RES: /* juggle the capabilities to follow [RES]UID changes unless * otherwise suppressed */ if (!issecure(SECURE_NO_SETUID_FIXUP)) cap_emulate_setxuid(new, old); break; case LSM_SETID_FS: /* juggle the capabilties to follow FSUID changes, unless * otherwise suppressed * * FIXME - is fsuser used for all CAP_FS_MASK capabilities? * if not, we might be a bit too harsh here. */ if (!issecure(SECURE_NO_SETUID_FIXUP)) { kuid_t root_uid = make_kuid(old->user_ns, 0); if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_drop_fs_set(new->cap_effective); if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid)) new->cap_effective = cap_raise_fs_set(new->cap_effective, new->cap_permitted); } break; default: return -EINVAL; } return 0; } /* * Rationale: code calling task_setscheduler, task_setioprio, and * task_setnice, assumes that * . if capable(cap_sys_nice), then those actions should be allowed * . if not capable(cap_sys_nice), but acting on your own processes, * then those actions should be allowed * This is insufficient now since you can call code without suid, but * yet with increased caps. * So we check for increased caps on the target process. */ static int cap_safe_nice(struct task_struct *p) { int is_subset, ret = 0; rcu_read_lock(); is_subset = cap_issubset(__task_cred(p)->cap_permitted, current_cred()->cap_permitted); if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) ret = -EPERM; rcu_read_unlock(); return ret; } /** * cap_task_setscheduler - Detemine if scheduler policy change is permitted * @p: The task to affect * * Detemine if the requested scheduler policy change is permitted for the * specified task, returning 0 if permission is granted, -ve if denied. */ int cap_task_setscheduler(struct task_struct *p) { return cap_safe_nice(p); } /** * cap_task_ioprio - Detemine if I/O priority change is permitted * @p: The task to affect * @ioprio: The I/O priority to set * * Detemine if the requested I/O priority change is permitted for the specified * task, returning 0 if permission is granted, -ve if denied. */ int cap_task_setioprio(struct task_struct *p, int ioprio) { return cap_safe_nice(p); } /** * cap_task_ioprio - Detemine if task priority change is permitted * @p: The task to affect * @nice: The nice value to set * * Detemine if the requested task priority change is permitted for the * specified task, returning 0 if permission is granted, -ve if denied. */ int cap_task_setnice(struct task_struct *p, int nice) { return cap_safe_nice(p); } /* * Implement PR_CAPBSET_DROP. Attempt to remove the specified capability from * the current task's bounding set. Returns 0 on success, -ve on error. */ static int cap_prctl_drop(unsigned long cap) { struct cred *new; if (!ns_capable(current_user_ns(), CAP_SETPCAP)) return -EPERM; if (!cap_valid(cap)) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_lower(new->cap_bset, cap); return commit_creds(new); } /** * cap_task_prctl - Implement process control functions for this security module * @option: The process control function requested * @arg2, @arg3, @arg4, @arg5: The argument data for this function * * Allow process control functions (sys_prctl()) to alter capabilities; may * also deny access to other functions not otherwise implemented here. * * Returns 0 or +ve on success, -ENOSYS if this function is not implemented * here, other -ve on error. If -ENOSYS is returned, sys_prctl() and other LSM * modules will consider performing the function. */ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { const struct cred *old = current_cred(); struct cred *new; switch (option) { case PR_CAPBSET_READ: if (!cap_valid(arg2)) return -EINVAL; return !!cap_raised(old->cap_bset, arg2); case PR_CAPBSET_DROP: return cap_prctl_drop(arg2); /* * The next four prctl's remain to assist with transitioning a * system from legacy UID=0 based privilege (when filesystem * capabilities are not in use) to a system using filesystem * capabilities only - as the POSIX.1e draft intended. * * Note: * * PR_SET_SECUREBITS = * issecure_mask(SECURE_KEEP_CAPS_LOCKED) * | issecure_mask(SECURE_NOROOT) * | issecure_mask(SECURE_NOROOT_LOCKED) * | issecure_mask(SECURE_NO_SETUID_FIXUP) * | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED) * * will ensure that the current process and all of its * children will be locked into a pure * capability-based-privilege environment. */ case PR_SET_SECUREBITS: if ((((old->securebits & SECURE_ALL_LOCKS) >> 1) & (old->securebits ^ arg2)) /*[1]*/ || ((old->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ || (cap_capable(current_cred(), current_cred()->user_ns, CAP_SETPCAP, CAP_OPT_NONE) != 0) /*[4]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks * [3] no setting of unsupported bits * [4] doing anything requires privilege (go read about * the "sendmail capabilities bug") */ ) /* cannot change a locked bit */ return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; new->securebits = arg2; return commit_creds(new); case PR_GET_SECUREBITS: return old->securebits; case PR_GET_KEEPCAPS: return !!issecure(SECURE_KEEP_CAPS); case PR_SET_KEEPCAPS: if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */ return -EINVAL; if (issecure(SECURE_KEEP_CAPS_LOCKED)) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2) new->securebits |= issecure_mask(SECURE_KEEP_CAPS); else new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); return commit_creds(new); case PR_CAP_AMBIENT: if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) { if (arg3 | arg4 | arg5) return -EINVAL; new = prepare_creds(); if (!new) return -ENOMEM; cap_clear(new->cap_ambient); return commit_creds(new); } if (((!cap_valid(arg3)) | arg4 | arg5)) return -EINVAL; if (arg2 == PR_CAP_AMBIENT_IS_SET) { return !!cap_raised(current_cred()->cap_ambient, arg3); } else if (arg2 != PR_CAP_AMBIENT_RAISE && arg2 != PR_CAP_AMBIENT_LOWER) { return -EINVAL; } else { if (arg2 == PR_CAP_AMBIENT_RAISE && (!cap_raised(current_cred()->cap_permitted, arg3) || !cap_raised(current_cred()->cap_inheritable, arg3) || issecure(SECURE_NO_CAP_AMBIENT_RAISE))) return -EPERM; new = prepare_creds(); if (!new) return -ENOMEM; if (arg2 == PR_CAP_AMBIENT_RAISE) cap_raise(new->cap_ambient, arg3); else cap_lower(new->cap_ambient, arg3); return commit_creds(new); } default: /* No functionality available - continue with default */ return -ENOSYS; } } /** * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted * @mm: The VM space in which the new mapping is to be made * @pages: The size of the mapping * * Determine whether the allocation of a new virtual mapping by the current * task is permitted, returning 1 if permission is granted, 0 if not. */ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { int cap_sys_admin = 0; if (cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN, CAP_OPT_NOAUDIT) == 0) cap_sys_admin = 1; return cap_sys_admin; } /* * cap_mmap_addr - check if able to map given addr * @addr: address attempting to be mapped * * If the process is attempting to map memory below dac_mmap_min_addr they need * CAP_SYS_RAWIO. The other parameters to this function are unused by the * capability security module. Returns 0 if this mapping should be allowed * -EPERM if not. */ int cap_mmap_addr(unsigned long addr) { int ret = 0; if (addr < dac_mmap_min_addr) { ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO, CAP_OPT_NONE); /* set PF_SUPERPRIV if it turns out we allow the low mmap */ if (ret == 0) current->flags |= PF_SUPERPRIV; } return ret; } int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { return 0; } #ifdef CONFIG_SECURITY static struct security_hook_list capability_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(capable, cap_capable), LSM_HOOK_INIT(settime, cap_settime), LSM_HOOK_INIT(ptrace_access_check, cap_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme), LSM_HOOK_INIT(capget, cap_capget), LSM_HOOK_INIT(capset, cap_capset), LSM_HOOK_INIT(bprm_creds_from_file, cap_bprm_creds_from_file), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), LSM_HOOK_INIT(mmap_file, cap_mmap_file), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), LSM_HOOK_INIT(task_prctl, cap_task_prctl), LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler), LSM_HOOK_INIT(task_setioprio, cap_task_setioprio), LSM_HOOK_INIT(task_setnice, cap_task_setnice), LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory), }; static int __init capability_init(void) { security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks), "capability"); return 0; } DEFINE_LSM(capability) = { .name = "capability", .order = LSM_ORDER_FIRST, .init = capability_init, }; #endif /* CONFIG_SECURITY */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. * * 10Apr2002 Andrew Morton * Initial version */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/init.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/mpage.h> #include <linux/rmap.h> #include <linux/percpu.h> #include <linux/smp.h> #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/buffer_head.h> /* __set_page_dirty_buffers */ #include <linux/pagevec.h> #include <linux/timer.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> #include <linux/mm_inline.h> #include <trace/events/writeback.h> #include "internal.h" /* * Sleep at most 200ms at a time in balance_dirty_pages(). */ #define MAX_PAUSE max(HZ/5, 1) /* * Try to keep balance_dirty_pages() call intervals higher than this many pages * by raising pause time to max_pause when falls below it. */ #define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10)) /* * Estimate write bandwidth at 200ms intervals. */ #define BANDWIDTH_INTERVAL max(HZ/5, 1) #define RATELIMIT_CALC_SHIFT 10 /* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. */ static long ratelimit_pages = 32; /* The following parameters are exported via /proc/sys/vm */ /* * Start background writeback (via writeback threads) at this percentage */ int dirty_background_ratio = 10; /* * dirty_background_bytes starts at 0 (disabled) so that it is a function of * dirty_background_ratio * the amount of dirtyable memory */ unsigned long dirty_background_bytes; /* * free highmem will not be subtracted from the total free memory * for calculating free ratios if vm_highmem_is_dirtyable is true */ int vm_highmem_is_dirtyable; /* * The generator of dirty data starts writeback at this percentage */ int vm_dirty_ratio = 20; /* * vm_dirty_bytes starts at 0 (disabled) so that it is a function of * vm_dirty_ratio * the amount of dirtyable memory */ unsigned long vm_dirty_bytes; /* * The interval between `kupdate'-style writebacks */ unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ EXPORT_SYMBOL_GPL(dirty_writeback_interval); /* * The longest time for which data is allowed to remain dirty */ unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* * Flag that makes the machine dump writes/reads and block dirtyings. */ int block_dump; /* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. */ int laptop_mode; EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ struct wb_domain global_wb_domain; /* consolidated parameters for balance_dirty_pages() and its subroutines */ struct dirty_throttle_control { #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *dom; struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ #endif struct bdi_writeback *wb; struct fprop_local_percpu *wb_completions; unsigned long avail; /* dirtyable */ unsigned long dirty; /* file_dirty + write + nfs */ unsigned long thresh; /* dirty threshold */ unsigned long bg_thresh; /* dirty background threshold */ unsigned long wb_dirty; /* per-wb counterparts */ unsigned long wb_thresh; unsigned long wb_bg_thresh; unsigned long pos_ratio; }; /* * Length of period for aging writeout fractions of bdis. This is an * arbitrarily chosen number. The longer the period, the slower fractions will * reflect changes in current writeout rate. */ #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) #ifdef CONFIG_CGROUP_WRITEBACK #define GDTC_INIT(__wb) .wb = (__wb), \ .dom = &global_wb_domain, \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB .dom = &global_wb_domain #define MDTC_INIT(__wb, __gdtc) .wb = (__wb), \ .dom = mem_cgroup_wb_domain(__wb), \ .wb_completions = &(__wb)->memcg_completions, \ .gdtc = __gdtc static bool mdtc_valid(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return mdtc->gdtc; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return &wb->memcg_completions; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); unsigned long long min = wb->bdi->min_ratio; unsigned long long max = wb->bdi->max_ratio; /* * @wb may already be clean by the time control reaches here and * the total may not include its bw. */ if (this_bw < tot_bw) { if (min) { min *= this_bw; min = div64_ul(min, tot_bw); } if (max < 100) { max *= this_bw; max = div64_ul(max, tot_bw); } } *minp = min; *maxp = max; } #else /* CONFIG_CGROUP_WRITEBACK */ #define GDTC_INIT(__wb) .wb = (__wb), \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB #define MDTC_INIT(__wb, __gdtc) static bool mdtc_valid(struct dirty_throttle_control *dtc) { return false; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return &global_wb_domain; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return NULL; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return NULL; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { *minp = wb->bdi->min_ratio; *maxp = wb->bdi->max_ratio; } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of * free and reclaimable pages, minus some zone reserves to protect * lowmem and the ability to uphold the zone's watermarks without * requiring writeback. * * This number of dirtyable pages is the base value of which the * user-configurable dirty ratio is the effective number of pages that * are allowed to be actually dirtied. Per individual zone, or * globally by using the sum of dirtyable pages over all zones. * * Because the user is allowed to specify the dirty limit globally as * absolute number of bytes, calculating the per-zone dirty limit can * require translating the configured limit into a percentage of * global dirtyable memory first. */ /** * node_dirtyable_memory - number of dirtyable pages in a node * @pgdat: the node * * Return: the node's number of pages potentially available for dirty * page cache. This is the base value for the per-node dirty limits. */ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat) { unsigned long nr_pages = 0; int z; for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = pgdat->node_zones + z; if (!populated_zone(zone)) continue; nr_pages += zone_page_state(zone, NR_FREE_PAGES); } /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ nr_pages -= min(nr_pages, pgdat->totalreserve_pages); nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE); nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE); return nr_pages; } static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM int node; unsigned long x = 0; int i; for_each_node_state(node, N_HIGH_MEMORY) { for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) { struct zone *z; unsigned long nr_pages; if (!is_highmem_idx(i)) continue; z = &NODE_DATA(node)->node_zones[i]; if (!populated_zone(z)) continue; nr_pages = zone_page_state(z, NR_FREE_PAGES); /* watch for underflows */ nr_pages -= min(nr_pages, high_wmark_pages(z)); nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE); nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE); x += nr_pages; } } /* * Unreclaimable memory (kernel memory or anonymous memory * without swap) can bring down the dirtyable pages below * the zone's dirty balance reserve and the above calculation * will underflow. However we still want to add in nodes * which are below threshold (negative values) to get a more * accurate calculation but make sure that the total never * underflows. */ if ((long)x < 0) x = 0; /* * Make sure that the number of highmem pages is never larger * than the number of the total dirtyable memory. This can only * occur in very strange VM situations but we want to make sure * that this does not occur. */ return min(x, total); #else return 0; #endif } /** * global_dirtyable_memory - number of globally dirtyable pages * * Return: the global number of pages potentially available for dirty * page cache. This is the base value for the global dirty limits. */ static unsigned long global_dirtyable_memory(void) { unsigned long x; x = global_zone_page_state(NR_FREE_PAGES); /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ x -= min(x, totalreserve_pages); x += global_node_page_state(NR_INACTIVE_FILE); x += global_node_page_state(NR_ACTIVE_FILE); if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); return x + 1; /* Ensure that we never return 0 */ } /** * domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain * @dtc: dirty_throttle_control of interest * * Calculate @dtc->thresh and ->bg_thresh considering * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller * must ensure that @dtc->avail is set before calling this function. The * dirty limits will be lifted by 1/4 for real-time tasks. */ static void domain_dirty_limits(struct dirty_throttle_control *dtc) { const unsigned long available_memory = dtc->avail; struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); unsigned long bytes = vm_dirty_bytes; unsigned long bg_bytes = dirty_background_bytes; /* convert ratios to per-PAGE_SIZE for higher precision */ unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100; unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100; unsigned long thresh; unsigned long bg_thresh; struct task_struct *tsk; /* gdtc is !NULL iff @dtc is for memcg domain */ if (gdtc) { unsigned long global_avail = gdtc->avail; /* * The byte settings can't be applied directly to memcg * domains. Convert them to ratios by scaling against * globally available memory. As the ratios are in * per-PAGE_SIZE, they can be obtained by dividing bytes by * number of pages. */ if (bytes) ratio = min(DIV_ROUND_UP(bytes, global_avail), PAGE_SIZE); if (bg_bytes) bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail), PAGE_SIZE); bytes = bg_bytes = 0; } if (bytes) thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); else thresh = (ratio * available_memory) / PAGE_SIZE; if (bg_bytes) bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); else bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; tsk = current; if (rt_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } /* * Dirty throttling logic assumes the limits in page units fit into * 32-bits. This gives 16TB dirty limits max which is hopefully enough. */ if (thresh > UINT_MAX) thresh = UINT_MAX; /* This makes sure bg_thresh is within 32-bits as well */ if (bg_thresh >= thresh) bg_thresh = thresh / 2; dtc->thresh = thresh; dtc->bg_thresh = bg_thresh; /* we should eventually report the domain in the TP */ if (!gdtc) trace_global_dirty_state(bg_thresh, thresh); } /** * global_dirty_limits - background-writeback and dirty-throttling thresholds * @pbackground: out parameter for bg_thresh * @pdirty: out parameter for thresh * * Calculate bg_thresh and thresh for global_wb_domain. See * domain_dirty_limits() for details. */ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; gdtc.avail = global_dirtyable_memory(); domain_dirty_limits(&gdtc); *pbackground = gdtc.bg_thresh; *pdirty = gdtc.thresh; } /** * node_dirty_limit - maximum number of dirty pages allowed in a node * @pgdat: the node * * Return: the maximum number of dirty pages allowed in a node, based * on the node's dirtyable memory. */ static unsigned long node_dirty_limit(struct pglist_data *pgdat) { unsigned long node_memory = node_dirtyable_memory(pgdat); struct task_struct *tsk = current; unsigned long dirty; if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) * node_memory / global_dirtyable_memory(); else dirty = vm_dirty_ratio * node_memory / 100; if (rt_task(tsk)) dirty += dirty / 4; /* * Dirty throttling logic assumes the limits in page units fit into * 32-bits. This gives 16TB dirty limits max which is hopefully enough. */ return min_t(unsigned long, dirty, UINT_MAX); } /** * node_dirty_ok - tells whether a node is within its dirty limits * @pgdat: the node to check * * Return: %true when the dirty pages in @pgdat are within the node's * dirty limit, %false if the limit is exceeded. */ bool node_dirty_ok(struct pglist_data *pgdat) { unsigned long limit = node_dirty_limit(pgdat); unsigned long nr_pages = 0; nr_pages += node_page_state(pgdat, NR_FILE_DIRTY); nr_pages += node_page_state(pgdat, NR_WRITEBACK); return nr_pages <= limit; } int dirty_background_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_bytes = 0; return ret; } int dirty_background_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; unsigned long old_bytes = dirty_background_bytes; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) { if (DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE) > UINT_MAX) { dirty_background_bytes = old_bytes; return -ERANGE; } dirty_background_ratio = 0; } return ret; } int dirty_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { vm_dirty_bytes = 0; writeback_set_ratelimit(); } return ret; } int dirty_bytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned long old_bytes = vm_dirty_bytes; int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { if (DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) > UINT_MAX) { vm_dirty_bytes = old_bytes; return -ERANGE; } writeback_set_ratelimit(); vm_dirty_ratio = 0; } return ret; } static unsigned long wp_next_time(unsigned long cur_time) { cur_time += VM_COMPLETIONS_PERIOD_LEN; /* 0 has a special meaning... */ if (!cur_time) return 1; return cur_time; } static void wb_domain_writeout_inc(struct wb_domain *dom, struct fprop_local_percpu *completions, unsigned int max_prop_frac) { __fprop_inc_percpu_max(&dom->completions, completions, max_prop_frac); /* First event after period switching was turned off? */ if (unlikely(!dom->period_time)) { /* * We can race with other __bdi_writeout_inc calls here but * it does not cause any harm since the resulting time when * timer will fire and what is in writeout_period_time will be * roughly the same. */ dom->period_time = wp_next_time(jiffies); mod_timer(&dom->period_timer, dom->period_time); } } /* * Increment @wb's writeout completion count and the global writeout * completion count. Called from test_clear_page_writeback(). */ static inline void __wb_writeout_inc(struct bdi_writeback *wb) { struct wb_domain *cgdom; inc_wb_stat(wb, WB_WRITTEN); wb_domain_writeout_inc(&global_wb_domain, &wb->completions, wb->bdi->max_prop_frac); cgdom = mem_cgroup_wb_domain(wb); if (cgdom) wb_domain_writeout_inc(cgdom, wb_memcg_completions(wb), wb->bdi->max_prop_frac); } void wb_writeout_inc(struct bdi_writeback *wb) { unsigned long flags; local_irq_save(flags); __wb_writeout_inc(wb); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(wb_writeout_inc); /* * On idle system, we can be called long after we scheduled because we use * deferred timers so count with missed periods. */ static void writeout_period(struct timer_list *t) { struct wb_domain *dom = from_timer(dom, t, period_timer); int miss_periods = (jiffies - dom->period_time) / VM_COMPLETIONS_PERIOD_LEN; if (fprop_new_period(&dom->completions, miss_periods + 1)) { dom->period_time = wp_next_time(dom->period_time + miss_periods * VM_COMPLETIONS_PERIOD_LEN); mod_timer(&dom->period_timer, dom->period_time); } else { /* * Aging has zeroed all fractions. Stop wasting CPU on period * updates. */ dom->period_time = 0; } } int wb_domain_init(struct wb_domain *dom, gfp_t gfp) { memset(dom, 0, sizeof(*dom)); spin_lock_init(&dom->lock); timer_setup(&dom->period_timer, writeout_period, TIMER_DEFERRABLE); dom->dirty_limit_tstamp = jiffies; return fprop_global_init(&dom->completions, gfp); } #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom) { del_timer_sync(&dom->period_timer); fprop_global_destroy(&dom->completions); } #endif /* * bdi_min_ratio keeps the sum of the minimum dirty shares of all * registered backing devices, which, for obvious reasons, can not * exceed 100%. */ static unsigned int bdi_min_ratio; int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { int ret = 0; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { min_ratio -= bdi->min_ratio; if (bdi_min_ratio + min_ratio < 100) { bdi_min_ratio += min_ratio; bdi->min_ratio += min_ratio; } else { ret = -EINVAL; } } spin_unlock_bh(&bdi_lock); return ret; } int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) { int ret = 0; if (max_ratio > 100) return -EINVAL; spin_lock_bh(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / 100; } spin_unlock_bh(&bdi_lock); return ret; } EXPORT_SYMBOL(bdi_set_max_ratio); static unsigned long dirty_freerun_ceiling(unsigned long thresh, unsigned long bg_thresh) { return (thresh + bg_thresh) / 2; } static unsigned long hard_dirty_limit(struct wb_domain *dom, unsigned long thresh) { return max(thresh, dom->dirty_limit); } /* * Memory which can be further allocated to a memcg domain is capped by * system-wide clean memory excluding the amount being used in the domain. */ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, unsigned long filepages, unsigned long headroom) { struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); unsigned long clean = filepages - min(filepages, mdtc->dirty); unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); unsigned long other_clean = global_clean - min(global_clean, clean); mdtc->avail = filepages + min(headroom, other_clean); } /** * __wb_calc_thresh - @wb's share of dirty throttling threshold * @dtc: dirty_throttle_context of interest * * Note that balance_dirty_pages() will only seriously take it as a hard limit * when sleeping max_pause per page is not enough to keep the dirty pages under * control. For example, when the device is completely stalled due to some error * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key. * In the other normal situations, it acts more gently by throttling the tasks * more (rather than completely block them) when the wb dirty pages go high. * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * * The wb's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. * * Return: @wb's dirty limit in pages. The term "dirty" in the context of * dirty balancing includes all PG_dirty and PG_writeback pages. */ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; u64 wb_thresh; unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio; /* * Calculate this BDI's share of the thresh ratio. */ fprop_fraction_percpu(&dom->completions, dtc->wb_completions, &numerator, &denominator); wb_thresh = (thresh * (100 - bdi_min_ratio)) / 100; wb_thresh *= numerator; wb_thresh = div64_ul(wb_thresh, denominator); wb_min_max_ratio(dtc->wb, &wb_min_ratio, &wb_max_ratio); wb_thresh += (thresh * wb_min_ratio) / 100; if (wb_thresh > (thresh * wb_max_ratio) / 100) wb_thresh = thresh * wb_max_ratio / 100; return wb_thresh; } unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb), .thresh = thresh }; return __wb_calc_thresh(&gdtc); } /* * setpoint - dirty 3 * f(dirty) := 1.0 + (----------------) * limit - setpoint * * it's a 3rd order polynomial that subjects to * * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast * (2) f(setpoint) = 1.0 => the balance point * (3) f(limit) = 0 => the hard limit * (4) df/dx <= 0 => negative feedback control * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) * => fast response on large errors; small oscillation near setpoint */ static long long pos_ratio_polynom(unsigned long setpoint, unsigned long dirty, unsigned long limit) { long long pos_ratio; long x; x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, (limit - setpoint) | 1); pos_ratio = x; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio += 1 << RATELIMIT_CALC_SHIFT; return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT); } /* * Dirty position control. * * (o) global/bdi setpoints * * We want the dirty pages be balanced around the global/wb setpoints. * When the number of dirty pages is higher/lower than the setpoint, the * dirty position control ratio (and hence task dirty ratelimit) will be * decreased/increased to bring the dirty pages back to the setpoint. * * pos_ratio = 1 << RATELIMIT_CALC_SHIFT * * if (dirty < setpoint) scale up pos_ratio * if (dirty > setpoint) scale down pos_ratio * * if (wb_dirty < wb_setpoint) scale up pos_ratio * if (wb_dirty > wb_setpoint) scale down pos_ratio * * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT * * (o) global control line * * ^ pos_ratio * | * | |<===== global dirty control scope ======>| * 2.0 .............* * | .* * | . * * | . * * | . * * | . * * | . * * 1.0 ................................* * | . . * * | . . * * | . . * * | . . * * | . . * * 0 +------------.------------------.----------------------*-------------> * freerun^ setpoint^ limit^ dirty pages * * (o) wb control line * * ^ pos_ratio * | * | * * | * * | * * | * * | * |<=========== span ============>| * 1.0 .......................* * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * 1/4 ...............................................* * * * * * * * * * * * * | . . * | . . * | . . * 0 +----------------------.-------------------------------.-------------> * wb_setpoint^ x_intercept^ * * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can * be smoothly throttled down to normal if it starts high in situations like * - start writing to a slow SD card and a fast disk at the same time. The SD * card's wb_dirty may rush to many times higher than wb_setpoint. * - the wb dirty thresh drops quickly due to change of JBOD workload */ static void wb_position_ratio(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long write_bw = wb->avg_write_bandwidth; unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long wb_thresh = dtc->wb_thresh; unsigned long x_intercept; unsigned long setpoint; /* dirty pages' target balance point */ unsigned long wb_setpoint; unsigned long span; long long pos_ratio; /* for scaling up/down the rate limit */ long x; dtc->pos_ratio = 0; if (unlikely(dtc->dirty >= limit)) return; /* * global setpoint * * See comment for pos_ratio_polynom(). */ setpoint = (freerun + limit) / 2; pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit); /* * The strictlimit feature is a tool preventing mistrusted filesystems * from growing a large number of dirty pages before throttling. For * such filesystems balance_dirty_pages always checks wb counters * against wb limits. Even if global "nr_dirty" is under "freerun". * This is especially important for fuse which sets bdi->max_ratio to * 1% by default. Without strictlimit feature, fuse writeback may * consume arbitrary amount of RAM because it is accounted in * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty". * * Here, in wb_position_ratio(), we calculate pos_ratio based on * two values: wb_dirty and wb_thresh. Let's consider an example: * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global * limits are set by default to 10% and 20% (background and throttle). * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. * wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is * about ~6K pages (as the average of background and throttle wb * limits). The 3rd order polynomial will provide positive feedback if * wb_dirty is under wb_setpoint and vice versa. * * Note, that we cannot use global counters in these calculations * because we want to throttle process writing to a strictlimit wb * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB * in the example above). */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { long long wb_pos_ratio; if (dtc->wb_dirty < 8) { dtc->pos_ratio = min_t(long long, pos_ratio * 2, 2 << RATELIMIT_CALC_SHIFT); return; } if (dtc->wb_dirty >= wb_thresh) return; wb_setpoint = dirty_freerun_ceiling(wb_thresh, dtc->wb_bg_thresh); if (wb_setpoint == 0 || wb_setpoint == wb_thresh) return; wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty, wb_thresh); /* * Typically, for strictlimit case, wb_setpoint << setpoint * and pos_ratio >> wb_pos_ratio. In the other words global * state ("dirty") is not limiting factor and we have to * make decision based on wb counters. But there is an * important case when global pos_ratio should get precedence: * global limits are exceeded (e.g. due to activities on other * wb's) while given strictlimit wb is below limit. * * "pos_ratio * wb_pos_ratio" would work for the case above, * but it would look too non-natural for the case of all * activity in the system coming from a single strictlimit wb * with bdi->max_ratio == 100%. * * Note that min() below somewhat changes the dynamics of the * control system. Normally, pos_ratio value can be well over 3 * (when globally we are at freerun and wb is well below wb * setpoint). Now the maximum pos_ratio in the same situation * is 2. We might want to tweak this if we observe the control * system is too slow to adapt. */ dtc->pos_ratio = min(pos_ratio, wb_pos_ratio); return; } /* * We have computed basic pos_ratio above based on global situation. If * the wb is over/under its share of dirty pages, we want to scale * pos_ratio further down/up. That is done by the following mechanism. */ /* * wb setpoint * * f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint) * * x_intercept - wb_dirty * := -------------------------- * x_intercept - wb_setpoint * * The main wb control line is a linear function that subjects to * * (1) f(wb_setpoint) = 1.0 * (2) k = - 1 / (8 * write_bw) (in single wb case) * or equally: x_intercept = wb_setpoint + 8 * write_bw * * For single wb case, the dirty pages are observed to fluctuate * regularly within range * [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2] * for various filesystems, where (2) can yield in a reasonable 12.5% * fluctuation range for pos_ratio. * * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its * own size, so move the slope over accordingly and choose a slope that * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh. */ if (unlikely(wb_thresh > dtc->thresh)) wb_thresh = dtc->thresh; /* * It's very possible that wb_thresh is close to 0 not because the * device is slow, but that it has remained inactive for long time. * Honour such devices a reasonable good (hopefully IO efficient) * threshold, so that the occasional writes won't be blocked and active * writes can rampup the threshold quickly. */ wb_thresh = max(wb_thresh, (limit - dtc->dirty) / 8); /* * scale global setpoint to wb's: * wb_setpoint = setpoint * wb_thresh / thresh */ x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1); wb_setpoint = setpoint * (u64)x >> 16; /* * Use span=(8*write_bw) in single wb case as indicated by * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case. * * wb_thresh thresh - wb_thresh * span = --------- * (8 * write_bw) + ------------------ * wb_thresh * thresh thresh */ span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16; x_intercept = wb_setpoint + span; if (dtc->wb_dirty < x_intercept - span / 4) { pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty), (x_intercept - wb_setpoint) | 1); } else pos_ratio /= 4; /* * wb reserve area, safeguard against dirty pool underrun and disk idle * It may push the desired control point of global dirty pages higher * than setpoint. */ x_intercept = wb_thresh / 2; if (dtc->wb_dirty < x_intercept) { if (dtc->wb_dirty > x_intercept / 8) pos_ratio = div_u64(pos_ratio * x_intercept, dtc->wb_dirty); else pos_ratio *= 8; } dtc->pos_ratio = pos_ratio; } static void wb_update_write_bandwidth(struct bdi_writeback *wb, unsigned long elapsed, unsigned long written) { const unsigned long period = roundup_pow_of_two(3 * HZ); unsigned long avg = wb->avg_write_bandwidth; unsigned long old = wb->write_bandwidth; u64 bw; /* * bw = written * HZ / elapsed * * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period * * @written may have decreased due to account_page_redirty(). * Avoid underflowing @bw calculation. */ bw = written - min(written, wb->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { bw = div64_ul(bw, elapsed); avg = bw; goto out; } bw += (u64)wb->write_bandwidth * (period - elapsed); bw >>= ilog2(period); /* * one more level of smoothing, for filtering out sudden spikes */ if (avg > old && old >= (unsigned long)bw) avg -= (avg - old) >> 3; if (avg < old && old <= (unsigned long)bw) avg += (old - avg) >> 3; out: /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */ avg = max(avg, 1LU); if (wb_has_dirty_io(wb)) { long delta = avg - wb->avg_write_bandwidth; WARN_ON_ONCE(atomic_long_add_return(delta, &wb->bdi->tot_write_bandwidth) <= 0); } wb->write_bandwidth = bw; wb->avg_write_bandwidth = avg; } static void update_dirty_limit(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; unsigned long limit = dom->dirty_limit; /* * Follow up in one step. */ if (limit < thresh) { limit = thresh; goto update; } /* * Follow down slowly. Use the higher one as the target, because thresh * may drop below dirty. This is exactly the reason to introduce * dom->dirty_limit which is guaranteed to lie above the dirty pages. */ thresh = max(thresh, dtc->dirty); if (limit > thresh) { limit -= (limit - thresh) >> 5; goto update; } return; update: dom->dirty_limit = limit; } static void domain_update_bandwidth(struct dirty_throttle_control *dtc, unsigned long now) { struct wb_domain *dom = dtc_dom(dtc); /* * check locklessly first to optimize away locking for the most time */ if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) return; spin_lock(&dom->lock); if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) { update_dirty_limit(dtc); dom->dirty_limit_tstamp = now; } spin_unlock(&dom->lock); } /* * Maintain wb->dirty_ratelimit, the base dirty throttle rate. * * Normal wb tasks will be curbed at or below it in long term. * Obviously it should be around (write_bw / N) when there are N dd tasks. */ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, unsigned long dirtied, unsigned long elapsed) { struct bdi_writeback *wb = dtc->wb; unsigned long dirty = dtc->dirty; unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long setpoint = (freerun + limit) / 2; unsigned long write_bw = wb->avg_write_bandwidth; unsigned long dirty_ratelimit = wb->dirty_ratelimit; unsigned long dirty_rate; unsigned long task_ratelimit; unsigned long balanced_dirty_ratelimit; unsigned long step; unsigned long x; unsigned long shift; /* * The dirty rate will match the writeout rate in long term, except * when dirty pages are truncated by userspace or re-dirtied by FS. */ dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed; /* * task_ratelimit reflects each dd's dirty rate for the past 200ms. */ task_ratelimit = (u64)dirty_ratelimit * dtc->pos_ratio >> RATELIMIT_CALC_SHIFT; task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ /* * A linear estimation of the "balanced" throttle rate. The theory is, * if there are N dd tasks, each throttled at task_ratelimit, the wb's * dirty_rate will be measured to be (N * task_ratelimit). So the below * formula will yield the balanced rate limit (write_bw / N). * * Note that the expanded form is not a pure rate feedback: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1) * but also takes pos_ratio into account: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2) * * (1) is not realistic because pos_ratio also takes part in balancing * the dirty rate. Consider the state * pos_ratio = 0.5 (3) * rate = 2 * (write_bw / N) (4) * If (1) is used, it will stuck in that state! Because each dd will * be throttled at * task_ratelimit = pos_ratio * rate = (write_bw / N) (5) * yielding * dirty_rate = N * task_ratelimit = write_bw (6) * put (6) into (1) we get * rate_(i+1) = rate_(i) (7) * * So we end up using (2) to always keep * rate_(i+1) ~= (write_bw / N) (8) * regardless of the value of pos_ratio. As long as (8) is satisfied, * pos_ratio is able to drive itself to 1.0, which is not only where * the dirty count meet the setpoint, but also where the slope of * pos_ratio is most flat and hence task_ratelimit is least fluctuated. */ balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw, dirty_rate | 1); /* * balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw */ if (unlikely(balanced_dirty_ratelimit > write_bw)) balanced_dirty_ratelimit = write_bw; /* * We could safely do this and return immediately: * * wb->dirty_ratelimit = balanced_dirty_ratelimit; * * However to get a more stable dirty_ratelimit, the below elaborated * code makes use of task_ratelimit to filter out singular points and * limit the step size. * * The below code essentially only uses the relative value of * * task_ratelimit - dirty_ratelimit * = (pos_ratio - 1) * dirty_ratelimit * * which reflects the direction and size of dirty position error. */ /* * dirty_ratelimit will follow balanced_dirty_ratelimit iff * task_ratelimit is on the same side of dirty_ratelimit, too. * For example, when * - dirty_ratelimit > balanced_dirty_ratelimit * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint) * lowering dirty_ratelimit will help meet both the position and rate * control targets. Otherwise, don't update dirty_ratelimit if it will * only help meet the rate target. After all, what the users ultimately * feel and care are stable dirty rate and small position error. * * |task_ratelimit - dirty_ratelimit| is used to limit the step size * and filter out the singular points of balanced_dirty_ratelimit. Which * keeps jumping around randomly and can even leap far away at times * due to the small 200ms estimation period of dirty_rate (we want to * keep that period small to reduce time lags). */ step = 0; /* * For strictlimit case, calculations above were based on wb counters * and limits (starting from pos_ratio = wb_position_ratio() and up to * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). * Hence, to calculate "step" properly, we have to use wb_dirty as * "dirty" and wb_setpoint as "setpoint". * * We rampup dirty_ratelimit forcibly if wb_dirty is low because * it's possible that wb_thresh is close to zero due to inactivity * of backing device. */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { dirty = dtc->wb_dirty; if (dtc->wb_dirty < 8) setpoint = dtc->wb_dirty + 1; else setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; } if (dirty < setpoint) { x = min3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit < x) step = x - dirty_ratelimit; } else { x = max3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit > x) step = dirty_ratelimit - x; } /* * Don't pursue 100% rate matching. It's impossible since the balanced * rate itself is constantly fluctuating. So decrease the track speed * when it gets close to the target. Helps eliminate pointless tremors. */ shift = dirty_ratelimit / (2 * step + 1); if (shift < BITS_PER_LONG) step = DIV_ROUND_UP(step >> shift, 8); else step = 0; if (dirty_ratelimit < balanced_dirty_ratelimit) dirty_ratelimit += step; else dirty_ratelimit -= step; wb->dirty_ratelimit = max(dirty_ratelimit, 1UL); wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit; trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit); } static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, struct dirty_throttle_control *mdtc, unsigned long start_time, bool update_ratelimit) { struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; unsigned long elapsed = now - wb->bw_time_stamp; unsigned long dirtied; unsigned long written; lockdep_assert_held(&wb->list_lock); /* * rate-limit, only update once every 200ms. */ if (elapsed < BANDWIDTH_INTERVAL) return; dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); written = percpu_counter_read(&wb->stat[WB_WRITTEN]); /* * Skip quiet periods when disk bandwidth is under-utilized. * (at least 1s idle time between two flusher runs) */ if (elapsed > HZ && time_before(wb->bw_time_stamp, start_time)) goto snapshot; if (update_ratelimit) { domain_update_bandwidth(gdtc, now); wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); /* * @mdtc is always NULL if !CGROUP_WRITEBACK but the * compiler has no way to figure that out. Help it. */ if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) { domain_update_bandwidth(mdtc, now); wb_update_dirty_ratelimit(mdtc, dirtied, elapsed); } } wb_update_write_bandwidth(wb, elapsed, written); snapshot: wb->dirtied_stamp = dirtied; wb->written_stamp = written; wb->bw_time_stamp = now; } void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; __wb_update_bandwidth(&gdtc, NULL, start_time, false); } /* * After a task dirtied this many pages, balance_dirty_pages_ratelimited() * will look to see if it needs to start dirty throttling. * * If dirty_poll_interval is too low, big NUMA machines will call the expensive * global_zone_page_state() too often. So scale it near-sqrt to the safety margin * (the number of pages we may dirty without exceeding the dirty limits). */ static unsigned long dirty_poll_interval(unsigned long dirty, unsigned long thresh) { if (thresh > dirty) return 1UL << (ilog2(thresh - dirty) >> 1); return 1; } static unsigned long wb_max_pause(struct bdi_writeback *wb, unsigned long wb_dirty) { unsigned long bw = wb->avg_write_bandwidth; unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long * time, a small pool of dirty/writeback pages may go empty and disk go * idle. * * 8 serves as the safety ratio. */ t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; return min_t(unsigned long, t, MAX_PAUSE); } static long wb_min_pause(struct bdi_writeback *wb, long max_pause, unsigned long task_ratelimit, unsigned long dirty_ratelimit, int *nr_dirtied_pause) { long hi = ilog2(wb->avg_write_bandwidth); long lo = ilog2(wb->dirty_ratelimit); long t; /* target pause */ long pause; /* estimated next pause */ int pages; /* target nr_dirtied_pause */ /* target for 10ms pause on 1-dd case */ t = max(1, HZ / 100); /* * Scale up pause time for concurrent dirtiers in order to reduce CPU * overheads. * * (N * 10ms) on 2^N concurrent tasks. */ if (hi > lo) t += (hi - lo) * (10 * HZ) / 1024; /* * This is a bit convoluted. We try to base the next nr_dirtied_pause * on the much more stable dirty_ratelimit. However the next pause time * will be computed based on task_ratelimit and the two rate limits may * depart considerably at some time. Especially if task_ratelimit goes * below dirty_ratelimit/2 and the target pause is max_pause, the next * pause time will be max_pause*2 _trimmed down_ to max_pause. As a * result task_ratelimit won't be executed faithfully, which could * eventually bring down dirty_ratelimit. * * We apply two rules to fix it up: * 1) try to estimate the next pause time and if necessary, use a lower * nr_dirtied_pause so as not to exceed max_pause. When this happens, * nr_dirtied_pause will be "dancing" with task_ratelimit. * 2) limit the target pause time to max_pause/2, so that the normal * small fluctuations of task_ratelimit won't trigger rule (1) and * nr_dirtied_pause will remain as stable as dirty_ratelimit. */ t = min(t, 1 + max_pause / 2); pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); /* * Tiny nr_dirtied_pause is found to hurt I/O performance in the test * case fio-mmap-randwrite-64k, which does 16*{sync read, async write}. * When the 16 consecutive reads are often interrupted by some dirty * throttling pause during the async writes, cfq will go into idles * (deadline is fine). So push nr_dirtied_pause as high as possible * until reaches DIRTY_POLL_THRESH=32 pages. */ if (pages < DIRTY_POLL_THRESH) { t = max_pause; pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); if (pages > DIRTY_POLL_THRESH) { pages = DIRTY_POLL_THRESH; t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit; } } pause = HZ * pages / (task_ratelimit + 1); if (pause > max_pause) { t = max_pause; pages = task_ratelimit * t / roundup_pow_of_two(HZ); } *nr_dirtied_pause = pages; /* * The minimal pause time will normally be half the target pause time. */ return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long wb_reclaimable; /* * wb_thresh is not treated as some limiting factor as * dirty_thresh, due to reasons * - in JBOD setup, wb_thresh can fluctuate a lot * - in a system with HDD and USB key, the USB key may somehow * go into state (wb_dirty >> wb_thresh) either because * wb_dirty starts high, or because wb_thresh drops low. * In this case we don't want to hard throttle the USB key * dirtiers for 100 seconds until wb_dirty drops under * wb_thresh. Instead the auxiliary wb control line in * wb_position_ratio() will let the dirtier task progress * at some rate <= (write_bw / 2) for bringing down wb_dirty. */ dtc->wb_thresh = __wb_calc_thresh(dtc); dtc->wb_bg_thresh = dtc->thresh ? div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (dtc->wb_thresh < 2 * wb_stat_error()) { wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); } else { wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); } } /* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2. * If we're over `background_thresh' then the writeback threads are woken to * perform some writeout. */ static void balance_dirty_pages(struct bdi_writeback *wb, unsigned long pages_dirtied) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; struct dirty_throttle_control *sdtc; unsigned long nr_reclaimable; /* = file_dirty */ long period; long pause; long max_pause; long min_pause; int nr_dirtied_pause; bool dirty_exceeded = false; unsigned long task_ratelimit; unsigned long dirty_ratelimit; struct backing_dev_info *bdi = wb->bdi; bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; for (;;) { unsigned long now = jiffies; unsigned long dirty, thresh, bg_thresh; unsigned long m_dirty = 0; /* stop bogus uninit warnings */ unsigned long m_thresh = 0; unsigned long m_bg_thresh = 0; nr_reclaimable = global_node_page_state(NR_FILE_DIRTY); gdtc->avail = global_dirtyable_memory(); gdtc->dirty = nr_reclaimable + global_node_page_state(NR_WRITEBACK); domain_dirty_limits(gdtc); if (unlikely(strictlimit)) { wb_dirty_limits(gdtc); dirty = gdtc->wb_dirty; thresh = gdtc->wb_thresh; bg_thresh = gdtc->wb_bg_thresh; } else { dirty = gdtc->dirty; thresh = gdtc->thresh; bg_thresh = gdtc->bg_thresh; } if (mdtc) { unsigned long filepages, headroom, writeback; /* * If @wb belongs to !root memcg, repeat the same * basic calculations for the memcg domain. */ mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, &writeback); mdtc->dirty += writeback; mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); if (unlikely(strictlimit)) { wb_dirty_limits(mdtc); m_dirty = mdtc->wb_dirty; m_thresh = mdtc->wb_thresh; m_bg_thresh = mdtc->wb_bg_thresh; } else { m_dirty = mdtc->dirty; m_thresh = mdtc->thresh; m_bg_thresh = mdtc->bg_thresh; } } /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts * when the wb limits are ramping up in case of !strictlimit. * * In strictlimit case make decision based on the wb counters * and limits. Small writeouts when the wb limits are ramping * up are the price we consciously pay for strictlimit-ing. * * If memcg domain is in effect, @dirty should be under * both global and memcg freerun ceilings. */ if (dirty <= dirty_freerun_ceiling(thresh, bg_thresh) && (!mdtc || m_dirty <= dirty_freerun_ceiling(m_thresh, m_bg_thresh))) { unsigned long intv; unsigned long m_intv; free_running: intv = dirty_poll_interval(dirty, thresh); m_intv = ULONG_MAX; current->dirty_paused_when = now; current->nr_dirtied = 0; if (mdtc) m_intv = dirty_poll_interval(m_dirty, m_thresh); current->nr_dirtied_pause = min(intv, m_intv); break; } if (unlikely(!writeback_in_progress(wb))) wb_start_background_writeback(wb); mem_cgroup_flush_foreign(wb); /* * Calculate global domain's pos_ratio and select the * global dtc by default. */ if (!strictlimit) { wb_dirty_limits(gdtc); if ((current->flags & PF_LOCAL_THROTTLE) && gdtc->wb_dirty < dirty_freerun_ceiling(gdtc->wb_thresh, gdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be throttled * when below the per-wb freerun ceiling. */ goto free_running; } dirty_exceeded = (gdtc->wb_dirty > gdtc->wb_thresh) && ((gdtc->dirty > gdtc->thresh) || strictlimit); wb_position_ratio(gdtc); sdtc = gdtc; if (mdtc) { /* * If memcg domain is in effect, calculate its * pos_ratio. @wb should satisfy constraints from * both global and memcg domains. Choose the one * w/ lower pos_ratio. */ if (!strictlimit) { wb_dirty_limits(mdtc); if ((current->flags & PF_LOCAL_THROTTLE) && mdtc->wb_dirty < dirty_freerun_ceiling(mdtc->wb_thresh, mdtc->wb_bg_thresh)) /* * LOCAL_THROTTLE tasks must not be * throttled when below the per-wb * freerun ceiling. */ goto free_running; } dirty_exceeded |= (mdtc->wb_dirty > mdtc->wb_thresh) && ((mdtc->dirty > mdtc->thresh) || strictlimit); wb_position_ratio(mdtc); if (mdtc->pos_ratio < gdtc->pos_ratio) sdtc = mdtc; } if (dirty_exceeded && !wb->dirty_exceeded) wb->dirty_exceeded = 1; if (time_is_before_jiffies(wb->bw_time_stamp + BANDWIDTH_INTERVAL)) { spin_lock(&wb->list_lock); __wb_update_bandwidth(gdtc, mdtc, start_time, true); spin_unlock(&wb->list_lock); } /* throttle according to the chosen dtc */ dirty_ratelimit = wb->dirty_ratelimit; task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> RATELIMIT_CALC_SHIFT; max_pause = wb_max_pause(wb, sdtc->wb_dirty); min_pause = wb_min_pause(wb, max_pause, task_ratelimit, dirty_ratelimit, &nr_dirtied_pause); if (unlikely(task_ratelimit == 0)) { period = max_pause; pause = max_pause; goto pause; } period = HZ * pages_dirtied / task_ratelimit; pause = period; if (current->dirty_paused_when) pause -= now - current->dirty_paused_when; /* * For less than 1s think time (ext3/4 may block the dirtier * for up to 800ms from time to time on 1-HDD; so does xfs, * however at much less frequency), try to compensate it in * future periods by updating the virtual time; otherwise just * do a reset, as it may be a light dirtier. */ if (pause < min_pause) { trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, min(pause, 0L), start_time); if (pause < -HZ) { current->dirty_paused_when = now; current->nr_dirtied = 0; } else if (period) { current->dirty_paused_when += period; current->nr_dirtied = 0; } else if (current->nr_dirtied_pause <= pages_dirtied) current->nr_dirtied_pause += pages_dirtied; break; } if (unlikely(pause > max_pause)) { /* for occasional dropped task_ratelimit */ now += min(pause - max_pause, max_pause); pause = max_pause; } pause: trace_balance_dirty_pages(wb, sdtc->thresh, sdtc->bg_thresh, sdtc->dirty, sdtc->wb_thresh, sdtc->wb_dirty, dirty_ratelimit, task_ratelimit, pages_dirtied, period, pause, start_time); __set_current_state(TASK_KILLABLE); wb->dirty_sleep = now; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; current->nr_dirtied = 0; current->nr_dirtied_pause = nr_dirtied_pause; /* * This is typically equal to (dirty < thresh) and can also * keep "1000+ dd on a slow USB stick" under control. */ if (task_ratelimit) break; /* * In the case of an unresponding NFS server and the NFS dirty * pages exceeds dirty_thresh, give the other good wb's a pipe * to go through, so that tasks on them still remain responsive. * * In theory 1 page is enough to keep the consumer-producer * pipe going: the flusher cleans 1 page => the task dirties 1 * more page. However wb_dirty has accounting errors. So use * the larger and more IO friendly wb_stat_error. */ if (sdtc->wb_dirty <= wb_stat_error()) break; if (fatal_signal_pending(current)) break; } if (!dirty_exceeded && wb->dirty_exceeded) wb->dirty_exceeded = 0; if (writeback_in_progress(wb)) return; /* * In laptop mode, we wait until hitting the higher threshold before * starting background writeout, and then write out all the way down * to the lower threshold. So slow writers cause minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if (laptop_mode) return; if (nr_reclaimable > gdtc->bg_thresh) wb_start_background_writeback(wb); } static DEFINE_PER_CPU(int, bdp_ratelimits); /* * Normal tasks are throttled by * loop { * dirty tsk->nr_dirtied_pause pages; * take a snap in balance_dirty_pages(); * } * However there is a worst case. If every task exit immediately when dirtied * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be * called to throttle the page dirties. The solution is to save the not yet * throttled page dirties in dirty_throttle_leaks on task exit and charge them * randomly into the running tasks. This works well for the above worst case, * as the new task will pick up and accumulate the old task's leaked dirty * count and eventually get throttled. */ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; /** * balance_dirty_pages_ratelimited - balance dirty memory state * @mapping: address_space which was dirtied * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * On really big machines, get_writeback_state is expensive, so try to avoid * calling it too often (ratelimiting). But once we're over the dirty memory * limit we decrease the ratelimiting by a lot, to prevent individual processes * from overshooting the limit by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; int ratelimit; int *p; if (!(bdi->capabilities & BDI_CAP_WRITEBACK)) return; if (inode_cgwb_enabled(inode)) wb = wb_get_create_current(bdi, GFP_KERNEL); if (!wb) wb = &bdi->wb; ratelimit = current->nr_dirtied_pause; if (wb->dirty_exceeded) ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); preempt_disable(); /* * This prevents one CPU to accumulate too many dirtied pages without * calling into balance_dirty_pages(), which can happen when there are * 1000+ tasks, all of them start dirtying pages at exactly the same * time, hence all honoured too large initial task->nr_dirtied_pause. */ p = this_cpu_ptr(&bdp_ratelimits); if (unlikely(current->nr_dirtied >= ratelimit)) *p = 0; else if (unlikely(*p >= ratelimit_pages)) { *p = 0; ratelimit = 0; } /* * Pick up the dirtied pages by the exited tasks. This avoids lots of * short-lived tasks (eg. gcc invocations in a kernel build) escaping * the dirty throttling and livelock other long-run dirtiers. */ p = this_cpu_ptr(&dirty_throttle_leaks); if (*p > 0 && current->nr_dirtied < ratelimit) { unsigned long nr_pages_dirtied; nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); *p -= nr_pages_dirtied; current->nr_dirtied += nr_pages_dirtied; } preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) balance_dirty_pages(wb, current->nr_dirtied); wb_put(wb); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited); /** * wb_over_bg_thresh - does @wb need to be written back? * @wb: bdi_writeback of interest * * Determines whether background writeback should keep writing @wb or it's * clean enough. * * Return: %true if writeback should continue. */ bool wb_over_bg_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; /* * Similar to balance_dirty_pages() but ignores pages being written * as we're trying to decide whether to put more under writeback. */ gdtc->avail = global_dirtyable_memory(); gdtc->dirty = global_node_page_state(NR_FILE_DIRTY); domain_dirty_limits(gdtc); if (gdtc->dirty > gdtc->bg_thresh) return true; if (wb_stat(wb, WB_RECLAIMABLE) > wb_calc_thresh(gdtc->wb, gdtc->bg_thresh)) return true; if (mdtc) { unsigned long filepages, headroom, writeback; mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty, &writeback); mdtc_calc_avail(mdtc, filepages, headroom); domain_dirty_limits(mdtc); /* ditto, ignore writeback */ if (mdtc->dirty > mdtc->bg_thresh) return true; if (wb_stat(wb, WB_RECLAIMABLE) > wb_calc_thresh(mdtc->wb, mdtc->bg_thresh)) return true; } return false; } /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ int dirty_writeback_centisecs_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { unsigned int old_interval = dirty_writeback_interval; int ret; ret = proc_dointvec(table, write, buffer, length, ppos); /* * Writing 0 to dirty_writeback_interval will disable periodic writeback * and a different non-zero value will wakeup the writeback threads. * wb_wakeup_delayed() would be more appropriate, but it's a pain to * iterate over all bdis and wbs. * The reason we do this is to make the change take effect immediately. */ if (!ret && write && dirty_writeback_interval && dirty_writeback_interval != old_interval) wakeup_flusher_threads(WB_REASON_PERIODIC); return ret; } #ifdef CONFIG_BLOCK void laptop_mode_timer_fn(struct timer_list *t) { struct backing_dev_info *backing_dev_info = from_timer(backing_dev_info, t, laptop_mode_wb_timer); wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER); } /* * We've spun up the disk and we're in laptop mode: schedule writeback * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ void laptop_io_completion(struct backing_dev_info *info) { mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* * We're in laptop mode and we've just synced. The sync's writes will have * caused another writeback to be scheduled by laptop_io_completion. * Nothing needs to be written back anymore, so we unschedule the writeback. */ void laptop_sync_completion(void) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) del_timer(&bdi->laptop_mode_wb_timer); rcu_read_unlock(); } #endif /* * If ratelimit_pages is too high then we can get into dirty-data overload * if a large number of processes all perform writes at the same time. * If it is too low then SMP machines will call the (expensive) * get_writeback_state too often. * * Here we set ratelimit_pages to a level which ensures that when all CPUs are * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory * thresholds. */ void writeback_set_ratelimit(void) { struct wb_domain *dom = &global_wb_domain; unsigned long background_thresh; unsigned long dirty_thresh; global_dirty_limits(&background_thresh, &dirty_thresh); dom->dirty_limit = dirty_thresh; ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; } static int page_writeback_cpu_online(unsigned int cpu) { writeback_set_ratelimit(); return 0; } /* * Called early on to tune the page writeback dirty limits. * * We used to scale dirty pages according to how total memory * related to pages that could be allocated for buffers. * * However, that was when we used "dirty_ratio" to scale with * all memory, and we don't do that any more. "dirty_ratio" * is now applied to total non-HIGHPAGE memory, and as such we can't * get into the old insane situation any more where we had * large amounts of dirty pages compared to a small amount of * non-HIGHMEM memory. * * But we might still want to scale the dirty_ratio by how * much memory the box has.. */ void __init page_writeback_init(void) { BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online", page_writeback_cpu_online, NULL); cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL, page_writeback_cpu_online); } /** * tag_pages_for_writeback - tag pages to be written by write_cache_pages * @mapping: address space structure to write * @start: starting page index * @end: ending page index (inclusive) * * This function scans the page range from @start to @end (inclusive) and tags * all pages that have DIRTY tag set with a special TOWRITE tag. The idea is * that write_cache_pages (or whoever calls this function) will then use * TOWRITE tag to identify pages eligible for writeback. This mechanism is * used to avoid livelocking of writeback by a process steadily creating new * dirty pages in the file (thus it is important for this function to be quick * so that it can tag pages faster than a dirtying process can create them). */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); unsigned int tagged = 0; void *page; xas_lock_irq(&xas); xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) { xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); if (++tagged % XA_CHECK_SCHED) continue; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } EXPORT_SYMBOL(tag_pages_for_writeback); /** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @writepage: function called for each page * @data: data passed to writepage function * * If a page is already under I/O, write_cache_pages() skips it, even * if it's dirty. This is desirable behaviour for memory-cleaning writeback, * but it is INCORRECT for data-integrity system calls such as fsync(). fsync() * and msync() need to guarantee that all the data which was dirty at the time * the call was made get new I/O started against them. If wbc->sync_mode is * WB_SYNC_ALL then we were called for data integrity and we must wait for * existing IO to complete. * * To avoid livelocks (when other process dirties new pages), we first tag * pages which should be written back with TOWRITE tag and only then start * writing them. For data-integrity sync we have to be careful so that we do * not miss some pages (e.g., because some other process has cleared TOWRITE * tag we set). The rule we follow is that TOWRITE tag can be cleared only * by the process clearing the DIRTY tag (and submitting the page for IO). * * To avoid deadlocks between range_cyclic writeback and callers that hold * pages in PageWriteback to aggregate IO until write_cache_pages() returns, * we do not loop back to the start of the file. Doing so causes a page * lock/page writeback access order inversion - we should only ever lock * multiple pages in ascending page->index order, and looping back to the start * of the file violates that rule and causes deadlocks. * * Return: %0 on success, negative error code otherwise */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { int ret = 0; int done = 0; int error; struct pagevec pvec; int nr_pages; pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; int range_whole = 0; xa_mark_t tag; pagevec_init(&pvec); if (wbc->range_cyclic) { index = mapping->writeback_index; /* prev offset */ end = -1; } else { index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; } if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) { tag_pages_for_writeback(mapping, index, end); tag = PAGECACHE_TAG_TOWRITE; } else { tag = PAGECACHE_TAG_DIRTY; } done_index = index; while (!done && (index <= end)) { int i; nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, tag); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; done_index = page->index; lock_page(page); /* * Page truncated or invalidated. We can freely skip it * then, even for data integrity operations: the page * has disappeared concurrently, so there could be no * real expectation of this data interity operation * even if there is now a new, dirty page at the same * pagecache address. */ if (unlikely(page->mapping != mapping)) { continue_unlock: unlock_page(page); continue; } if (!PageDirty(page)) { /* someone wrote it for us */ goto continue_unlock; } if (PageWriteback(page)) { if (wbc->sync_mode != WB_SYNC_NONE) wait_on_page_writeback(page); else goto continue_unlock; } BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); error = (*writepage)(page, wbc, data); if (unlikely(error)) { /* * Handle errors according to the type of * writeback. There's no need to continue for * background writeback. Just push done_index * past this page so media errors won't choke * writeout for the entire file. For integrity * writeback, we must process the entire dirty * set regardless of errors because the fs may * still have state to clear for each page. In * that case we continue processing and return * the first error. */ if (error == AOP_WRITEPAGE_ACTIVATE) { unlock_page(page); error = 0; } else if (wbc->sync_mode != WB_SYNC_ALL) { ret = error; done_index = page->index + 1; done = 1; break; } if (!ret) ret = error; } /* * We stop writing back only if we are not doing * integrity sync. In case of integrity sync we have to * keep going until we have written all the pages * we tagged for writeback prior to entering this loop. */ if (--wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) { done = 1; break; } } pagevec_release(&pvec); cond_resched(); } /* * If we hit the last page and there is more work to be done: wrap * back the index back to the start of the file for the next * time we are called. */ if (wbc->range_cyclic && !done) done_index = 0; if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; return ret; } EXPORT_SYMBOL(write_cache_pages); /* * Function used by generic_writepages to call the real writepage * function and set the mapping flags on error */ static int __writepage(struct page *page, struct writeback_control *wbc, void *data) { struct address_space *mapping = data; int ret = mapping->a_ops->writepage(page, wbc); mapping_set_error(mapping, ret); return ret; } /** * generic_writepages - walk the list of dirty pages of the given address space and writepage() all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * * This is a library function, which implements the writepages() * address_space_operation. * * Return: %0 on success, negative error code otherwise */ int generic_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct blk_plug plug; int ret; /* deal with chardevs and other special file */ if (!mapping->a_ops->writepage) return 0; blk_start_plug(&plug); ret = write_cache_pages(mapping, wbc, __writepage, mapping); blk_finish_plug(&plug); return ret; } EXPORT_SYMBOL(generic_writepages); int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; if (wbc->nr_to_write <= 0) return 0; while (1) { if (mapping->a_ops->writepages) ret = mapping->a_ops->writepages(mapping, wbc); else ret = generic_writepages(mapping, wbc); if ((ret != -ENOMEM) || (wbc->sync_mode != WB_SYNC_ALL)) break; cond_resched(); congestion_wait(BLK_RW_ASYNC, HZ/50); } return ret; } /** * write_one_page - write out a single page and wait on I/O * @page: the page to write * * The page must be locked by the caller and will be unlocked upon return. * * Note that the mapping's AS_EIO/AS_ENOSPC flags will be cleared when this * function returns. * * Return: %0 on success, negative error code otherwise */ int write_one_page(struct page *page) { struct address_space *mapping = page->mapping; int ret = 0; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = 1, }; BUG_ON(!PageLocked(page)); wait_on_page_writeback(page); if (clear_page_dirty_for_io(page)) { get_page(page); ret = mapping->a_ops->writepage(page, &wbc); if (ret == 0) wait_on_page_writeback(page); put_page(page); } else { unlock_page(page); } if (!ret) ret = filemap_check_errors(mapping); return ret; } EXPORT_SYMBOL(write_one_page); /* * For address_spaces which do not use buffers nor write back. */ int __set_page_dirty_no_writeback(struct page *page) { if (!PageDirty(page)) return !TestSetPageDirty(page); return 0; } /* * Helper function for set_page_dirty family. * * Caller must hold lock_page_memcg(). * * NOTE: This relies on being atomic wrt interrupts. */ void account_page_dirtied(struct page *page, struct address_space *mapping) { struct inode *inode = mapping->host; trace_writeback_dirty_page(page, mapping); if (mapping_can_writeback(mapping)) { struct bdi_writeback *wb; inode_attach_wb(inode, page); wb = inode_to_wb(inode); __inc_lruvec_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); __inc_node_page_state(page, NR_DIRTIED); inc_wb_stat(wb, WB_RECLAIMABLE); inc_wb_stat(wb, WB_DIRTIED); task_io_account_write(PAGE_SIZE); current->nr_dirtied++; this_cpu_inc(bdp_ratelimits); mem_cgroup_track_foreign_dirty(page, wb); } } /* * Helper function for deaccounting dirty page without writeback. * * Caller must hold lock_page_memcg(). */ void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb) { if (mapping_can_writeback(mapping)) { dec_lruvec_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); task_io_account_cancelled_write(PAGE_SIZE); } } /* * For address_spaces which do not use buffers. Just tag the page as dirty in * the xarray. * * This is also used when a single buffer is being dirtied: we want to set the * page dirty in that case, but not all the buffers. This is a "bottom-up" * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying. * * The caller must ensure this doesn't race with truncation. Most will simply * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and * the pte lock held, which also locks out truncation. */ int __set_page_dirty_nobuffers(struct page *page) { lock_page_memcg(page); if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); unsigned long flags; if (!mapping) { unlock_page_memcg(page); return 1; } xa_lock_irqsave(&mapping->i_pages, flags); BUG_ON(page_mapping(page) != mapping); WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); account_page_dirtied(page, mapping); __xa_set_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); xa_unlock_irqrestore(&mapping->i_pages, flags); unlock_page_memcg(page); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return 1; } unlock_page_memcg(page); return 0; } EXPORT_SYMBOL(__set_page_dirty_nobuffers); /* * Call this whenever redirtying a page, to de-account the dirty counters * (NR_DIRTIED, WB_DIRTIED, tsk->nr_dirtied), so that they match the written * counters (NR_WRITTEN, WB_WRITTEN) in long term. The mismatches will lead to * systematic errors in balanced_dirty_ratelimit and the dirty pages position * control. */ void account_page_redirty(struct page *page) { struct address_space *mapping = page->mapping; if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied--; dec_node_page_state(page, NR_DIRTIED); dec_wb_stat(wb, WB_DIRTIED); unlocked_inode_to_wb_end(inode, &cookie); } } EXPORT_SYMBOL(account_page_redirty); /* * When a writepage implementation decides that it doesn't want to write this * page for some reason, it should redirty the locked page via * redirty_page_for_writepage() and it should then unlock the page and return 0 */ int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page) { int ret; wbc->pages_skipped++; ret = __set_page_dirty_nobuffers(page); account_page_redirty(page); return ret; } EXPORT_SYMBOL(redirty_page_for_writepage); /* * Dirty a page. * * For pages with a mapping this should be done under the page lock * for the benefit of asynchronous memory errors who prefer a consistent * dirty state. This rule can be broken in some special cases, * but should be better not to. * * If the mapping doesn't provide a set_page_dirty a_op, then * just fall through and assume that it wants buffer_heads. */ int set_page_dirty(struct page *page) { struct address_space *mapping = page_mapping(page); page = compound_head(page); if (likely(mapping)) { int (*spd)(struct page *) = mapping->a_ops->set_page_dirty; /* * readahead/lru_deactivate_page could remain * PG_readahead/PG_reclaim due to race with end_page_writeback * About readahead, if the page is written, the flags would be * reset. So no problem. * About lru_deactivate_page, if the page is redirty, the flag * will be reset. So no problem. but if the page is used by readahead * it will confuse readahead and make it restart the size rampup * process. But it's a trivial problem. */ if (PageReclaim(page)) ClearPageReclaim(page); #ifdef CONFIG_BLOCK if (!spd) spd = __set_page_dirty_buffers; #endif return (*spd)(page); } if (!PageDirty(page)) { if (!TestSetPageDirty(page)) return 1; } return 0; } EXPORT_SYMBOL(set_page_dirty); /* * set_page_dirty() is racy if the caller has no reference against * page->mapping->host, and if the page is unlocked. This is because another * CPU could truncate the page off the mapping and then free the mapping. * * Usually, the page _is_ locked, or the caller is a user-space process which * holds a reference on the inode by having an open file. * * In other cases, the page should be locked before running set_page_dirty(). */ int set_page_dirty_lock(struct page *page) { int ret; lock_page(page); ret = set_page_dirty(page); unlock_page(page); return ret; } EXPORT_SYMBOL(set_page_dirty_lock); /* * This cancels just the dirty bit on the kernel page itself, it does NOT * actually remove dirty bits on any mmap's that may be around. It also * leaves the page tagged dirty, so any sync activity will still find it on * the dirty lists, and in particular, clear_page_dirty_for_io() will still * look at the dirty bits in the VM. * * Doing this should *normally* only ever be done when a page is truncated, * and is not actually mapped anywhere at all. However, fs/buffer.c does * this when it notices that somebody has cleaned out all the buffers on a * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ void __cancel_dirty_page(struct page *page) { struct address_space *mapping = page_mapping(page); if (mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; lock_page_memcg(page); wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) account_page_cleaned(page, mapping, wb); unlocked_inode_to_wb_end(inode, &cookie); unlock_page_memcg(page); } else { ClearPageDirty(page); } } EXPORT_SYMBOL(__cancel_dirty_page); /* * Clear a page's dirty flag, while caring for dirty memory accounting. * Returns true if the page was previously dirty. * * This is for preparing to put the page under writeout. We leave the page * tagged as dirty in the xarray so that a concurrent write-for-sync * can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage * implementation will run either set_page_writeback() or set_page_dirty(), * at which stage we bring the page's dirty flag and xarray dirty tag * back into sync. * * This incoherency between the page's dirty flag and xarray tag is * unfortunate, but it only exists while the page is locked. */ int clear_page_dirty_for_io(struct page *page) { struct address_space *mapping = page_mapping(page); int ret = 0; VM_BUG_ON_PAGE(!PageLocked(page), page); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. * * We use this sequence to make sure that * (a) we account for dirty stats properly * (b) we tell the low-level filesystem to * mark the whole page dirty if it was * dirty in a pagetable. Only to then * (c) clean the page again and return 1 to * cause the writeback. * * This way we avoid all nasty races with the * dirty bit in multiple places and clearing * them concurrently from different threads. * * Note! Normally the "set_page_dirty(page)" * has no effect on the actual dirty bit - since * that will already usually be set. But we * need the side effects, and it can help us * avoid races. * * We basically use the page "master dirty bit" * as a serialization point for all the different * threads doing their things. */ if (page_mkclean(page)) set_page_dirty(page); /* * We carefully synchronise fault handlers against * installing a dirty pte and marking the page dirty * at this point. We do this by having them hold the * page lock while dirtying the page, and pages are * always locked coming in here, so we get the desired * exclusion. */ wb = unlocked_inode_to_wb_begin(inode, &cookie); if (TestClearPageDirty(page)) { dec_lruvec_page_state(page, NR_FILE_DIRTY); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); dec_wb_stat(wb, WB_RECLAIMABLE); ret = 1; } unlocked_inode_to_wb_end(inode, &cookie); return ret; } return TestClearPageDirty(page); } EXPORT_SYMBOL(clear_page_dirty_for_io); int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); struct mem_cgroup *memcg; struct lruvec *lruvec; int ret; memcg = lock_page_memcg(page); lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); ret = TestClearPageWriteback(page); if (ret) { __xa_clear_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); dec_wb_stat(wb, WB_WRITEBACK); __wb_writeout_inc(wb); } } if (mapping->host && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) sb_clear_inode_writeback(mapping->host); xa_unlock_irqrestore(&mapping->i_pages, flags); } else { ret = TestClearPageWriteback(page); } if (ret) { dec_lruvec_state(lruvec, NR_WRITEBACK); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); inc_node_page_state(page, NR_WRITTEN); } __unlock_page_memcg(memcg); return ret; } int __test_set_page_writeback(struct page *page, bool keep_write) { struct address_space *mapping = page_mapping(page); int ret, access_ret; lock_page_memcg(page); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, page_index(page)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xas_lock_irqsave(&xas, flags); xas_load(&xas); ret = TestSetPageWriteback(page); if (!ret) { bool on_wblist; on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); /* * We can come through here when swapping anonymous * pages, so we don't necessarily have an inode to track * for sync. */ if (mapping->host && !on_wblist) sb_mark_inode_writeback(mapping->host); } if (!PageDirty(page)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { ret = TestSetPageWriteback(page); } if (!ret) { inc_lruvec_page_state(page, NR_WRITEBACK); inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); } unlock_page_memcg(page); access_ret = arch_make_page_accessible(page); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ VM_BUG_ON_PAGE(access_ret != 0, page); return ret; } EXPORT_SYMBOL(__test_set_page_writeback); /* * Wait for a page to complete writeback */ void wait_on_page_writeback(struct page *page) { while (PageWriteback(page)) { trace_wait_on_page_writeback(page, page_mapping(page)); wait_on_page_bit(page, PG_writeback); } } EXPORT_SYMBOL_GPL(wait_on_page_writeback); /** * wait_for_stable_page() - wait for writeback to finish, if necessary. * @page: The page to wait on. * * This function determines if the given page is related to a backing device * that requires page contents to be held stable during writeback. If so, then * it will wait for any pending writeback to complete. */ void wait_for_stable_page(struct page *page) { page = thp_head(page); if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) wait_on_page_writeback(page); } EXPORT_SYMBOL_GPL(wait_for_stable_page); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_H #define _LINUX_RCULIST_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list.h> #include <linux/rcupdate.h> /* * Why is there no list_empty_rcu()? Because list_empty() serves this * purpose. The list_empty() function fetches the RCU-protected pointer * and compares it to the address of the list head, but neither dereferences * this pointer itself nor provides this pointer to the caller. Therefore, * it is not necessary to use rcu_dereference(), so that list_empty() can * be used anywhere you would want to use a list_empty_rcu(). */ /* * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers * @list: list to be initialized * * You should instead use INIT_LIST_HEAD() for normal initialization and * cleanup tasks, when readers have no access to the list being initialized. * However, if the list being initialized is visible to readers, you * need to keep the compiler from being too mischievous. */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } /* * return the ->next pointer of a list_head in an rcu safe * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) /** * list_tail_rcu - returns the prev pointer of the head of the list * @head: the head of the list * * Note: This should only be used with the list header, and even then * only if list_del() and similar primitives are not also used on the * list header. */ #define list_tail_rcu(head) (*((struct list_head __rcu **)(&(head)->prev))) /* * Check during list traversal that we are within an RCU reader */ #define check_arg_count_one(dummy) #ifdef CONFIG_PROVE_RCU_LIST #define __list_check_rcu(dummy, cond, extra...) \ ({ \ check_arg_count_one(extra); \ RCU_LOCKDEP_WARN(!(cond) && !rcu_read_lock_any_held(), \ "RCU-list traversed in non-reader section!"); \ }) #define __list_check_srcu(cond) \ ({ \ RCU_LOCKDEP_WARN(!(cond), \ "RCU-list traversed without holding the required lock!");\ }) #else #define __list_check_rcu(dummy, cond, extra...) \ ({ check_arg_count_one(extra); }) #define __list_check_srcu(cond) ({ }) #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; new->next = next; new->prev = prev; rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } /** * list_add_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head, head->next); } /** * list_add_tail_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_tail_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_tail_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head->prev, head); } /** * list_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * Note: list_empty() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_del_rcu() * or list_add_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_del_rcu(struct list_head *entry) { __list_del_entry(entry); entry->prev = LIST_POISON2; } /** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_add_head_rcu() or * hlist_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_for_each_entry_rcu(). */ static inline void hlist_del_init_rcu(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, struct list_head *new) { new->next = old->next; new->prev = old->prev; rcu_assign_pointer(list_next_rcu(new->prev), new); new->next->prev = new; old->prev = LIST_POISON2; } /** * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. * * Note that this function blocks. * * Important note: the caller must take whatever action is necessary to prevent * any other updates to the existing list. In principle, it is possible to * modify the list as soon as sync() begins execution. If this sort of thing * becomes necessary, an alternative version based on call_rcu() could be * created. But only if -really- needed -- there is no shortage of RCU API * members. */ static inline void __list_splice_init_rcu(struct list_head *list, struct list_head *prev, struct list_head *next, void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; /* * "first" and "last" tracking list, so initialize it. RCU readers * have access to this list, so we must use INIT_LIST_HEAD_RCU() * instead of INIT_LIST_HEAD(). */ INIT_LIST_HEAD_RCU(list); /* * At this point, the list body still points to the source list. * Wait for any readers to finish using the list before splicing * the list body into the new list. Any new readers will see * an empty list. */ sync(); ASSERT_EXCLUSIVE_ACCESS(*first); ASSERT_EXCLUSIVE_ACCESS(*last); /* * Readers are finished with the source list, so perform splice. * The order is important if the new list is global and accessible * to concurrent RCU readers. Note that RCU readers are not * permitted to traverse the prev pointers without excluding * this function. */ last->next = next; rcu_assign_pointer(list_next_rcu(prev), first); first->prev = prev; next->prev = last; } /** * list_splice_init_rcu - splice an RCU-protected list into an existing list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head, head->next, sync); } /** * list_splice_tail_init_rcu - splice an RCU-protected list into an existing * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head->prev, head, sync); } /** * list_entry_rcu - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? * * Implementing those functions following their counterparts list_empty() and * list_first_entry() is not advisable because they lead to subtle race * conditions as the following snippet shows: * * if (!list_empty_rcu(mylist)) { * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); * do_something(bar); * } * * The list may not be empty when list_empty_rcu checks it, but it may be when * list_first_entry_rcu rereads the ->next pointer. * * Rereading the ->next pointer is not a problem for list_empty() and * list_first_entry() because they would be protected by a lock that blocks * writers. * * See list_first_or_null_rcu for an alternative. */ /** * list_first_or_null_rcu - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) /** * list_next_or_null_rcu - get the first element from a list * @head: the head for the list. * @ptr: the list head to take the next element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the ptr is at the end of the list, NULL is returned. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_next_or_null_rcu(head, ptr, type, member) \ ({ \ struct list_head *__head = (head); \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__next != __head) ? list_entry_rcu(__next, type, \ member) : NULL; \ }) /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define list_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_entry_lockless - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_struct within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position which must have been in the list when the RCU read * lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_from_rcu() except * this starts after the given position and that one starts at the given * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_from_rcu - iterate over a list from current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_node within the struct. * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_continue_rcu() except * this starts from the given position and that one starts from the position * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member)) /** * hlist_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry(). */ static inline void hlist_del_rcu(struct hlist_node *n) { __hlist_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) { struct hlist_node *next = old->next; new->next = next; WRITE_ONCE(new->pprev, old->pprev); rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) WRITE_ONCE(new->next->pprev, &new->next); WRITE_ONCE(old->pprev, LIST_POISON2); } /** * hlists_swap_heads_rcu - swap the lists the hlist heads point to * @left: The hlist head on the left * @right: The hlist head on the right * * The lists start out as [@left ][node1 ... ] and * [@right ][node2 ... ] * The lists end up as [@left ][node2 ... ] * [@right ][node1 ... ] */ static inline void hlists_swap_heads_rcu(struct hlist_head *left, struct hlist_head *right) { struct hlist_node *node1 = left->first; struct hlist_node *node2 = right->first; rcu_assign_pointer(left->first, node2); rcu_assign_pointer(right->first, node1); WRITE_ONCE(node2->pprev, &left->first); WRITE_ONCE(node1->pprev, &right->first); } /* * return the first or the next element in an RCU protected hlist */ #define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first))) #define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next))) #define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev))) /** * hlist_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_head_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_first_rcu(h), n); if (first) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_add_tail_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_tail_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; i; i = i->next) last = i; if (last) { n->next = last->next; WRITE_ONCE(n->pprev, &last->next); rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_add_head_rcu(n, h); } } /** * hlist_add_before_rcu * @n: the new element to add to the hash list. * @next: the existing element to add the new element before. * * Description: * Adds the specified element to the specified hlist * before the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { WRITE_ONCE(n->pprev, next->pprev); n->next = next; rcu_assign_pointer(hlist_pprev_rcu(n), n); WRITE_ONCE(next->pprev, &n->next); } /** * hlist_add_behind_rcu * @n: the new element to add to the hash list. * @prev: the existing element to add the new element after. * * Description: * Adds the specified element to the specified hlist * after the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_behind_rcu(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; WRITE_ONCE(n->pprev, &prev->next); rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) WRITE_ONCE(n->next->pprev, &n->next); } #define __hlist_for_each_rcu(pos, head) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos; \ pos = rcu_dereference(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_srcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: lockdep expression for the lock required to traverse the list. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by srcu_read_lock(). * The lockdep expression srcu_read_lock_held() can be passed as the * cond argument from read side. */ #define hlist_for_each_entry_srcu(pos, head, member, cond) \ for (__list_check_srcu(cond), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). * * This is the same as hlist_for_each_entry_rcu() except that it does * not do any RCU debugging or tracing. */ #define hlist_for_each_entry_rcu_notrace(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu_bh(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 | // SPDX-License-Identifier: GPL-2.0 #include <linux/err.h> #include <linux/bug.h> #include <linux/atomic.h> #include <linux/errseq.h> /* * An errseq_t is a way of recording errors in one place, and allowing any * number of "subscribers" to tell whether it has changed since a previous * point where it was sampled. * * It's implemented as an unsigned 32-bit value. The low order bits are * designated to hold an error code (between 0 and -MAX_ERRNO). The upper bits * are used as a counter. This is done with atomics instead of locking so that * these functions can be called from any context. * * The general idea is for consumers to sample an errseq_t value. That value * can later be used to tell whether any new errors have occurred since that * sampling was done. * * Note that there is a risk of collisions if new errors are being recorded * frequently, since we have so few bits to use as a counter. * * To mitigate this, one bit is used as a flag to tell whether the value has * been sampled since a new value was recorded. That allows us to avoid bumping * the counter if no one has sampled it since the last time an error was * recorded. * * A new errseq_t should always be zeroed out. A errseq_t value of all zeroes * is the special (but common) case where there has never been an error. An all * zero value thus serves as the "epoch" if one wishes to know whether there * has ever been an error set since it was first initialized. */ /* The low bits are designated for error code (max of MAX_ERRNO) */ #define ERRSEQ_SHIFT ilog2(MAX_ERRNO + 1) /* This bit is used as a flag to indicate whether the value has been seen */ #define ERRSEQ_SEEN (1 << ERRSEQ_SHIFT) /* The lowest bit of the counter */ #define ERRSEQ_CTR_INC (1 << (ERRSEQ_SHIFT + 1)) /** * errseq_set - set a errseq_t for later reporting * @eseq: errseq_t field that should be set * @err: error to set (must be between -1 and -MAX_ERRNO) * * This function sets the error in @eseq, and increments the sequence counter * if the last sequence was sampled at some point in the past. * * Any error set will always overwrite an existing error. * * Return: The previous value, primarily for debugging purposes. The * return value should not be used as a previously sampled value in later * calls as it will not have the SEEN flag set. */ errseq_t errseq_set(errseq_t *eseq, int err) { errseq_t cur, old; /* MAX_ERRNO must be able to serve as a mask */ BUILD_BUG_ON_NOT_POWER_OF_2(MAX_ERRNO + 1); /* * Ensure the error code actually fits where we want it to go. If it * doesn't then just throw a warning and don't record anything. We * also don't accept zero here as that would effectively clear a * previous error. */ old = READ_ONCE(*eseq); if (WARN(unlikely(err == 0 || (unsigned int)-err > MAX_ERRNO), "err = %d\n", err)) return old; for (;;) { errseq_t new; /* Clear out error bits and set new error */ new = (old & ~(MAX_ERRNO|ERRSEQ_SEEN)) | -err; /* Only increment if someone has looked at it */ if (old & ERRSEQ_SEEN) new += ERRSEQ_CTR_INC; /* If there would be no change, then call it done */ if (new == old) { cur = new; break; } /* Try to swap the new value into place */ cur = cmpxchg(eseq, old, new); /* * Call it success if we did the swap or someone else beat us * to it for the same value. */ if (likely(cur == old || cur == new)) break; /* Raced with an update, try again */ old = cur; } return cur; } EXPORT_SYMBOL(errseq_set); /** * errseq_sample() - Grab current errseq_t value. * @eseq: Pointer to errseq_t to be sampled. * * This function allows callers to initialise their errseq_t variable. * If the error has been "seen", new callers will not see an old error. * If there is an unseen error in @eseq, the caller of this function will * see it the next time it checks for an error. * * Context: Any context. * Return: The current errseq value. */ errseq_t errseq_sample(errseq_t *eseq) { errseq_t old = READ_ONCE(*eseq); /* If nobody has seen this error yet, then we can be the first. */ if (!(old & ERRSEQ_SEEN)) old = 0; return old; } EXPORT_SYMBOL(errseq_sample); /** * errseq_check() - Has an error occurred since a particular sample point? * @eseq: Pointer to errseq_t value to be checked. * @since: Previously-sampled errseq_t from which to check. * * Grab the value that eseq points to, and see if it has changed @since * the given value was sampled. The @since value is not advanced, so there * is no need to mark the value as seen. * * Return: The latest error set in the errseq_t or 0 if it hasn't changed. */ int errseq_check(errseq_t *eseq, errseq_t since) { errseq_t cur = READ_ONCE(*eseq); if (likely(cur == since)) return 0; return -(cur & MAX_ERRNO); } EXPORT_SYMBOL(errseq_check); /** * errseq_check_and_advance() - Check an errseq_t and advance to current value. * @eseq: Pointer to value being checked and reported. * @since: Pointer to previously-sampled errseq_t to check against and advance. * * Grab the eseq value, and see whether it matches the value that @since * points to. If it does, then just return 0. * * If it doesn't, then the value has changed. Set the "seen" flag, and try to * swap it into place as the new eseq value. Then, set that value as the new * "since" value, and return whatever the error portion is set to. * * Note that no locking is provided here for concurrent updates to the "since" * value. The caller must provide that if necessary. Because of this, callers * may want to do a lockless errseq_check before taking the lock and calling * this. * * Return: Negative errno if one has been stored, or 0 if no new error has * occurred. */ int errseq_check_and_advance(errseq_t *eseq, errseq_t *since) { int err = 0; errseq_t old, new; /* * Most callers will want to use the inline wrapper to check this, * so that the common case of no error is handled without needing * to take the lock that protects the "since" value. */ old = READ_ONCE(*eseq); if (old != *since) { /* * Set the flag and try to swap it into place if it has * changed. * * We don't care about the outcome of the swap here. If the * swap doesn't occur, then it has either been updated by a * writer who is altering the value in some way (updating * counter or resetting the error), or another reader who is * just setting the "seen" flag. Either outcome is OK, and we * can advance "since" and return an error based on what we * have. */ new = old | ERRSEQ_SEEN; if (new != old) cmpxchg(eseq, old, new); *since = new; err = -(new & MAX_ERRNO); } return err; } EXPORT_SYMBOL(errseq_check_and_advance); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the extensible bitmap type. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ /* * Updated: Hewlett-Packard <paul@paul-moore.com> * * Added support to import/export the NetLabel category bitmap * * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 */ /* * Updated: KaiGai Kohei <kaigai@ak.jp.nec.com> * Applied standard bit operations to improve bitmap scanning. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/jhash.h> #include <net/netlabel.h> #include "ebitmap.h" #include "policydb.h" #define BITS_PER_U64 (sizeof(u64) * 8) static struct kmem_cache *ebitmap_node_cachep; int ebitmap_cmp(struct ebitmap *e1, struct ebitmap *e2) { struct ebitmap_node *n1, *n2; if (e1->highbit != e2->highbit) return 0; n1 = e1->node; n2 = e2->node; while (n1 && n2 && (n1->startbit == n2->startbit) && !memcmp(n1->maps, n2->maps, EBITMAP_SIZE / 8)) { n1 = n1->next; n2 = n2->next; } if (n1 || n2) return 0; return 1; } int ebitmap_cpy(struct ebitmap *dst, struct ebitmap *src) { struct ebitmap_node *n, *new, *prev; ebitmap_init(dst); n = src->node; prev = NULL; while (n) { new = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC); if (!new) { ebitmap_destroy(dst); return -ENOMEM; } new->startbit = n->startbit; memcpy(new->maps, n->maps, EBITMAP_SIZE / 8); new->next = NULL; if (prev) prev->next = new; else dst->node = new; prev = new; n = n->next; } dst->highbit = src->highbit; return 0; } int ebitmap_and(struct ebitmap *dst, struct ebitmap *e1, struct ebitmap *e2) { struct ebitmap_node *n; int bit, rc; ebitmap_init(dst); ebitmap_for_each_positive_bit(e1, n, bit) { if (ebitmap_get_bit(e2, bit)) { rc = ebitmap_set_bit(dst, bit, 1); if (rc < 0) return rc; } } return 0; } #ifdef CONFIG_NETLABEL /** * ebitmap_netlbl_export - Export an ebitmap into a NetLabel category bitmap * @ebmap: the ebitmap to export * @catmap: the NetLabel category bitmap * * Description: * Export a SELinux extensibile bitmap into a NetLabel category bitmap. * Returns zero on success, negative values on error. * */ int ebitmap_netlbl_export(struct ebitmap *ebmap, struct netlbl_lsm_catmap **catmap) { struct ebitmap_node *e_iter = ebmap->node; unsigned long e_map; u32 offset; unsigned int iter; int rc; if (e_iter == NULL) { *catmap = NULL; return 0; } if (*catmap != NULL) netlbl_catmap_free(*catmap); *catmap = NULL; while (e_iter) { offset = e_iter->startbit; for (iter = 0; iter < EBITMAP_UNIT_NUMS; iter++) { e_map = e_iter->maps[iter]; if (e_map != 0) { rc = netlbl_catmap_setlong(catmap, offset, e_map, GFP_ATOMIC); if (rc != 0) goto netlbl_export_failure; } offset += EBITMAP_UNIT_SIZE; } e_iter = e_iter->next; } return 0; netlbl_export_failure: netlbl_catmap_free(*catmap); return -ENOMEM; } /** * ebitmap_netlbl_import - Import a NetLabel category bitmap into an ebitmap * @ebmap: the ebitmap to import * @catmap: the NetLabel category bitmap * * Description: * Import a NetLabel category bitmap into a SELinux extensibile bitmap. * Returns zero on success, negative values on error. * */ int ebitmap_netlbl_import(struct ebitmap *ebmap, struct netlbl_lsm_catmap *catmap) { int rc; struct ebitmap_node *e_iter = NULL; struct ebitmap_node *e_prev = NULL; u32 offset = 0, idx; unsigned long bitmap; for (;;) { rc = netlbl_catmap_getlong(catmap, &offset, &bitmap); if (rc < 0) goto netlbl_import_failure; if (offset == (u32)-1) return 0; /* don't waste ebitmap space if the netlabel bitmap is empty */ if (bitmap == 0) { offset += EBITMAP_UNIT_SIZE; continue; } if (e_iter == NULL || offset >= e_iter->startbit + EBITMAP_SIZE) { e_prev = e_iter; e_iter = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC); if (e_iter == NULL) goto netlbl_import_failure; e_iter->startbit = offset - (offset % EBITMAP_SIZE); if (e_prev == NULL) ebmap->node = e_iter; else e_prev->next = e_iter; ebmap->highbit = e_iter->startbit + EBITMAP_SIZE; } /* offset will always be aligned to an unsigned long */ idx = EBITMAP_NODE_INDEX(e_iter, offset); e_iter->maps[idx] = bitmap; /* next */ offset += EBITMAP_UNIT_SIZE; } /* NOTE: we should never reach this return */ return 0; netlbl_import_failure: ebitmap_destroy(ebmap); return -ENOMEM; } #endif /* CONFIG_NETLABEL */ /* * Check to see if all the bits set in e2 are also set in e1. Optionally, * if last_e2bit is non-zero, the highest set bit in e2 cannot exceed * last_e2bit. */ int ebitmap_contains(struct ebitmap *e1, struct ebitmap *e2, u32 last_e2bit) { struct ebitmap_node *n1, *n2; int i; if (e1->highbit < e2->highbit) return 0; n1 = e1->node; n2 = e2->node; while (n1 && n2 && (n1->startbit <= n2->startbit)) { if (n1->startbit < n2->startbit) { n1 = n1->next; continue; } for (i = EBITMAP_UNIT_NUMS - 1; (i >= 0) && !n2->maps[i]; ) i--; /* Skip trailing NULL map entries */ if (last_e2bit && (i >= 0)) { u32 lastsetbit = n2->startbit + i * EBITMAP_UNIT_SIZE + __fls(n2->maps[i]); if (lastsetbit > last_e2bit) return 0; } while (i >= 0) { if ((n1->maps[i] & n2->maps[i]) != n2->maps[i]) return 0; i--; } n1 = n1->next; n2 = n2->next; } if (n2) return 0; return 1; } int ebitmap_get_bit(struct ebitmap *e, unsigned long bit) { struct ebitmap_node *n; if (e->highbit < bit) return 0; n = e->node; while (n && (n->startbit <= bit)) { if ((n->startbit + EBITMAP_SIZE) > bit) return ebitmap_node_get_bit(n, bit); n = n->next; } return 0; } int ebitmap_set_bit(struct ebitmap *e, unsigned long bit, int value) { struct ebitmap_node *n, *prev, *new; prev = NULL; n = e->node; while (n && n->startbit <= bit) { if ((n->startbit + EBITMAP_SIZE) > bit) { if (value) { ebitmap_node_set_bit(n, bit); } else { unsigned int s; ebitmap_node_clr_bit(n, bit); s = find_first_bit(n->maps, EBITMAP_SIZE); if (s < EBITMAP_SIZE) return 0; /* drop this node from the bitmap */ if (!n->next) { /* * this was the highest map * within the bitmap */ if (prev) e->highbit = prev->startbit + EBITMAP_SIZE; else e->highbit = 0; } if (prev) prev->next = n->next; else e->node = n->next; kmem_cache_free(ebitmap_node_cachep, n); } return 0; } prev = n; n = n->next; } if (!value) return 0; new = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC); if (!new) return -ENOMEM; new->startbit = bit - (bit % EBITMAP_SIZE); ebitmap_node_set_bit(new, bit); if (!n) /* this node will be the highest map within the bitmap */ e->highbit = new->startbit + EBITMAP_SIZE; if (prev) { new->next = prev->next; prev->next = new; } else { new->next = e->node; e->node = new; } return 0; } void ebitmap_destroy(struct ebitmap *e) { struct ebitmap_node *n, *temp; if (!e) return; n = e->node; while (n) { temp = n; n = n->next; kmem_cache_free(ebitmap_node_cachep, temp); } e->highbit = 0; e->node = NULL; return; } int ebitmap_read(struct ebitmap *e, void *fp) { struct ebitmap_node *n = NULL; u32 mapunit, count, startbit, index; __le32 ebitmap_start; u64 map; __le64 mapbits; __le32 buf[3]; int rc, i; ebitmap_init(e); rc = next_entry(buf, fp, sizeof buf); if (rc < 0) goto out; mapunit = le32_to_cpu(buf[0]); e->highbit = le32_to_cpu(buf[1]); count = le32_to_cpu(buf[2]); if (mapunit != BITS_PER_U64) { pr_err("SELinux: ebitmap: map size %u does not " "match my size %zd (high bit was %d)\n", mapunit, BITS_PER_U64, e->highbit); goto bad; } /* round up e->highbit */ e->highbit += EBITMAP_SIZE - 1; e->highbit -= (e->highbit % EBITMAP_SIZE); if (!e->highbit) { e->node = NULL; goto ok; } if (e->highbit && !count) goto bad; for (i = 0; i < count; i++) { rc = next_entry(&ebitmap_start, fp, sizeof(u32)); if (rc < 0) { pr_err("SELinux: ebitmap: truncated map\n"); goto bad; } startbit = le32_to_cpu(ebitmap_start); if (startbit & (mapunit - 1)) { pr_err("SELinux: ebitmap start bit (%d) is " "not a multiple of the map unit size (%u)\n", startbit, mapunit); goto bad; } if (startbit > e->highbit - mapunit) { pr_err("SELinux: ebitmap start bit (%d) is " "beyond the end of the bitmap (%u)\n", startbit, (e->highbit - mapunit)); goto bad; } if (!n || startbit >= n->startbit + EBITMAP_SIZE) { struct ebitmap_node *tmp; tmp = kmem_cache_zalloc(ebitmap_node_cachep, GFP_KERNEL); if (!tmp) { pr_err("SELinux: ebitmap: out of memory\n"); rc = -ENOMEM; goto bad; } /* round down */ tmp->startbit = startbit - (startbit % EBITMAP_SIZE); if (n) n->next = tmp; else e->node = tmp; n = tmp; } else if (startbit <= n->startbit) { pr_err("SELinux: ebitmap: start bit %d" " comes after start bit %d\n", startbit, n->startbit); goto bad; } rc = next_entry(&mapbits, fp, sizeof(u64)); if (rc < 0) { pr_err("SELinux: ebitmap: truncated map\n"); goto bad; } map = le64_to_cpu(mapbits); index = (startbit - n->startbit) / EBITMAP_UNIT_SIZE; while (map) { n->maps[index++] = map & (-1UL); map = EBITMAP_SHIFT_UNIT_SIZE(map); } } ok: rc = 0; out: return rc; bad: if (!rc) rc = -EINVAL; ebitmap_destroy(e); goto out; } int ebitmap_write(struct ebitmap *e, void *fp) { struct ebitmap_node *n; u32 count; __le32 buf[3]; u64 map; int bit, last_bit, last_startbit, rc; buf[0] = cpu_to_le32(BITS_PER_U64); count = 0; last_bit = 0; last_startbit = -1; ebitmap_for_each_positive_bit(e, n, bit) { if (rounddown(bit, (int)BITS_PER_U64) > last_startbit) { count++; last_startbit = rounddown(bit, BITS_PER_U64); } last_bit = roundup(bit + 1, BITS_PER_U64); } buf[1] = cpu_to_le32(last_bit); buf[2] = cpu_to_le32(count); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; map = 0; last_startbit = INT_MIN; ebitmap_for_each_positive_bit(e, n, bit) { if (rounddown(bit, (int)BITS_PER_U64) > last_startbit) { __le64 buf64[1]; /* this is the very first bit */ if (!map) { last_startbit = rounddown(bit, BITS_PER_U64); map = (u64)1 << (bit - last_startbit); continue; } /* write the last node */ buf[0] = cpu_to_le32(last_startbit); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; buf64[0] = cpu_to_le64(map); rc = put_entry(buf64, sizeof(u64), 1, fp); if (rc) return rc; /* set up for the next node */ map = 0; last_startbit = rounddown(bit, BITS_PER_U64); } map |= (u64)1 << (bit - last_startbit); } /* write the last node */ if (map) { __le64 buf64[1]; /* write the last node */ buf[0] = cpu_to_le32(last_startbit); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; buf64[0] = cpu_to_le64(map); rc = put_entry(buf64, sizeof(u64), 1, fp); if (rc) return rc; } return 0; } u32 ebitmap_hash(const struct ebitmap *e, u32 hash) { struct ebitmap_node *node; /* need to change hash even if ebitmap is empty */ hash = jhash_1word(e->highbit, hash); for (node = e->node; node; node = node->next) { hash = jhash_1word(node->startbit, hash); hash = jhash(node->maps, sizeof(node->maps), hash); } return hash; } void __init ebitmap_cache_init(void) { ebitmap_node_cachep = kmem_cache_create("ebitmap_node", sizeof(struct ebitmap_node), 0, SLAB_PANIC, NULL); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Runtime locking correctness validator * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * see Documentation/locking/lockdep-design.rst for more details. */ #ifndef __LINUX_LOCKDEP_H #define __LINUX_LOCKDEP_H #include <linux/lockdep_types.h> #include <linux/smp.h> #include <asm/percpu.h> struct task_struct; /* for sysctl */ extern int prove_locking; extern int lock_stat; #ifdef CONFIG_LOCKDEP #include <linux/linkage.h> #include <linux/list.h> #include <linux/debug_locks.h> #include <linux/stacktrace.h> static inline void lockdep_copy_map(struct lockdep_map *to, struct lockdep_map *from) { int i; *to = *from; /* * Since the class cache can be modified concurrently we could observe * half pointers (64bit arch using 32bit copy insns). Therefore clear * the caches and take the performance hit. * * XXX it doesn't work well with lockdep_set_class_and_subclass(), since * that relies on cache abuse. */ for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++) to->class_cache[i] = NULL; } /* * Every lock has a list of other locks that were taken after it. * We only grow the list, never remove from it: */ struct lock_list { struct list_head entry; struct lock_class *class; struct lock_class *links_to; const struct lock_trace *trace; u16 distance; /* bitmap of different dependencies from head to this */ u8 dep; /* used by BFS to record whether "prev -> this" only has -(*R)-> */ u8 only_xr; /* * The parent field is used to implement breadth-first search, and the * bit 0 is reused to indicate if the lock has been accessed in BFS. */ struct lock_list *parent; }; /** * struct lock_chain - lock dependency chain record * * @irq_context: the same as irq_context in held_lock below * @depth: the number of held locks in this chain * @base: the index in chain_hlocks for this chain * @entry: the collided lock chains in lock_chain hash list * @chain_key: the hash key of this lock_chain */ struct lock_chain { /* see BUILD_BUG_ON()s in add_chain_cache() */ unsigned int irq_context : 2, depth : 6, base : 24; /* 4 byte hole */ struct hlist_node entry; u64 chain_key; }; #define MAX_LOCKDEP_KEYS_BITS 13 #define MAX_LOCKDEP_KEYS (1UL << MAX_LOCKDEP_KEYS_BITS) #define INITIAL_CHAIN_KEY -1 struct held_lock { /* * One-way hash of the dependency chain up to this point. We * hash the hashes step by step as the dependency chain grows. * * We use it for dependency-caching and we skip detection * passes and dependency-updates if there is a cache-hit, so * it is absolutely critical for 100% coverage of the validator * to have a unique key value for every unique dependency path * that can occur in the system, to make a unique hash value * as likely as possible - hence the 64-bit width. * * The task struct holds the current hash value (initialized * with zero), here we store the previous hash value: */ u64 prev_chain_key; unsigned long acquire_ip; struct lockdep_map *instance; struct lockdep_map *nest_lock; #ifdef CONFIG_LOCK_STAT u64 waittime_stamp; u64 holdtime_stamp; #endif /* * class_idx is zero-indexed; it points to the element in * lock_classes this held lock instance belongs to. class_idx is in * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive. */ unsigned int class_idx:MAX_LOCKDEP_KEYS_BITS; /* * The lock-stack is unified in that the lock chains of interrupt * contexts nest ontop of process context chains, but we 'separate' * the hashes by starting with 0 if we cross into an interrupt * context, and we also keep do not add cross-context lock * dependencies - the lock usage graph walking covers that area * anyway, and we'd just unnecessarily increase the number of * dependencies otherwise. [Note: hardirq and softirq contexts * are separated from each other too.] * * The following field is used to detect when we cross into an * interrupt context: */ unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */ unsigned int trylock:1; /* 16 bits */ unsigned int read:2; /* see lock_acquire() comment */ unsigned int check:1; /* see lock_acquire() comment */ unsigned int hardirqs_off:1; unsigned int references:12; /* 32 bits */ unsigned int pin_count; }; /* * Initialization, self-test and debugging-output methods: */ extern void lockdep_init(void); extern void lockdep_reset(void); extern void lockdep_reset_lock(struct lockdep_map *lock); extern void lockdep_free_key_range(void *start, unsigned long size); extern asmlinkage void lockdep_sys_exit(void); extern void lockdep_set_selftest_task(struct task_struct *task); extern void lockdep_init_task(struct task_struct *task); /* * Split the recrursion counter in two to readily detect 'off' vs recursion. */ #define LOCKDEP_RECURSION_BITS 16 #define LOCKDEP_OFF (1U << LOCKDEP_RECURSION_BITS) #define LOCKDEP_RECURSION_MASK (LOCKDEP_OFF - 1) /* * lockdep_{off,on}() are macros to avoid tracing and kprobes; not inlines due * to header dependencies. */ #define lockdep_off() \ do { \ current->lockdep_recursion += LOCKDEP_OFF; \ } while (0) #define lockdep_on() \ do { \ current->lockdep_recursion -= LOCKDEP_OFF; \ } while (0) extern void lockdep_register_key(struct lock_class_key *key); extern void lockdep_unregister_key(struct lock_class_key *key); /* * These methods are used by specific locking variants (spinlocks, * rwlocks, mutexes and rwsems) to pass init/acquire/release events * to lockdep: */ extern void lockdep_init_map_type(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass, u8 inner, u8 outer, u8 lock_type); static inline void lockdep_init_map_waits(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass, u8 inner, u8 outer) { lockdep_init_map_type(lock, name, key, subclass, inner, outer, LD_LOCK_NORMAL); } static inline void lockdep_init_map_wait(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass, u8 inner) { lockdep_init_map_waits(lock, name, key, subclass, inner, LD_WAIT_INV); } static inline void lockdep_init_map(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass) { lockdep_init_map_wait(lock, name, key, subclass, LD_WAIT_INV); } /* * Reinitialize a lock key - for cases where there is special locking or * special initialization of locks so that the validator gets the scope * of dependencies wrong: they are either too broad (they need a class-split) * or they are too narrow (they suffer from a false class-split): */ #define lockdep_set_class(lock, key) \ lockdep_init_map_type(&(lock)->dep_map, #key, key, 0, \ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) #define lockdep_set_class_and_name(lock, key, name) \ lockdep_init_map_type(&(lock)->dep_map, name, key, 0, \ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) #define lockdep_set_class_and_subclass(lock, key, sub) \ lockdep_init_map_type(&(lock)->dep_map, #key, key, sub, \ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) #define lockdep_set_subclass(lock, sub) \ lockdep_init_map_type(&(lock)->dep_map, (lock)->dep_map.name, (lock)->dep_map.key, sub,\ (lock)->dep_map.wait_type_inner, \ (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) #define lockdep_set_novalidate_class(lock) \ lockdep_set_class_and_name(lock, &__lockdep_no_validate__, #lock) /* * Compare locking classes */ #define lockdep_match_class(lock, key) lockdep_match_key(&(lock)->dep_map, key) static inline int lockdep_match_key(struct lockdep_map *lock, struct lock_class_key *key) { return lock->key == key; } /* * Acquire a lock. * * Values for "read": * * 0: exclusive (write) acquire * 1: read-acquire (no recursion allowed) * 2: read-acquire with same-instance recursion allowed * * Values for check: * * 0: simple checks (freeing, held-at-exit-time, etc.) * 1: full validation */ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, struct lockdep_map *nest_lock, unsigned long ip); extern void lock_release(struct lockdep_map *lock, unsigned long ip); /* * Same "read" as for lock_acquire(), except -1 means any. */ extern int lock_is_held_type(const struct lockdep_map *lock, int read); static inline int lock_is_held(const struct lockdep_map *lock) { return lock_is_held_type(lock, -1); } #define lockdep_is_held(lock) lock_is_held(&(lock)->dep_map) #define lockdep_is_held_type(lock, r) lock_is_held_type(&(lock)->dep_map, (r)) extern void lock_set_class(struct lockdep_map *lock, const char *name, struct lock_class_key *key, unsigned int subclass, unsigned long ip); static inline void lock_set_subclass(struct lockdep_map *lock, unsigned int subclass, unsigned long ip) { lock_set_class(lock, lock->name, lock->key, subclass, ip); } extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip); #define NIL_COOKIE (struct pin_cookie){ .val = 0U, } extern struct pin_cookie lock_pin_lock(struct lockdep_map *lock); extern void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie); extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); #define lockdep_depth(tsk) (debug_locks ? (tsk)->lockdep_depth : 0) #define lockdep_assert_held(l) do { \ WARN_ON(debug_locks && !lockdep_is_held(l)); \ } while (0) #define lockdep_assert_held_write(l) do { \ WARN_ON(debug_locks && !lockdep_is_held_type(l, 0)); \ } while (0) #define lockdep_assert_held_read(l) do { \ WARN_ON(debug_locks && !lockdep_is_held_type(l, 1)); \ } while (0) #define lockdep_assert_held_once(l) do { \ WARN_ON_ONCE(debug_locks && !lockdep_is_held(l)); \ } while (0) #define lockdep_assert_none_held_once() do { \ WARN_ON_ONCE(debug_locks && current->lockdep_depth); \ } while (0) #define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) #define lockdep_pin_lock(l) lock_pin_lock(&(l)->dep_map) #define lockdep_repin_lock(l,c) lock_repin_lock(&(l)->dep_map, (c)) #define lockdep_unpin_lock(l,c) lock_unpin_lock(&(l)->dep_map, (c)) #else /* !CONFIG_LOCKDEP */ static inline void lockdep_init_task(struct task_struct *task) { } static inline void lockdep_off(void) { } static inline void lockdep_on(void) { } static inline void lockdep_set_selftest_task(struct task_struct *task) { } # define lock_acquire(l, s, t, r, c, n, i) do { } while (0) # define lock_release(l, i) do { } while (0) # define lock_downgrade(l, i) do { } while (0) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) # define lockdep_init_map_type(lock, name, key, sub, inner, outer, type) \ do { (void)(name); (void)(key); } while (0) # define lockdep_init_map_waits(lock, name, key, sub, inner, outer) \ do { (void)(name); (void)(key); } while (0) # define lockdep_init_map_wait(lock, name, key, sub, inner) \ do { (void)(name); (void)(key); } while (0) # define lockdep_init_map(lock, name, key, sub) \ do { (void)(name); (void)(key); } while (0) # define lockdep_set_class(lock, key) do { (void)(key); } while (0) # define lockdep_set_class_and_name(lock, key, name) \ do { (void)(key); (void)(name); } while (0) #define lockdep_set_class_and_subclass(lock, key, sub) \ do { (void)(key); } while (0) #define lockdep_set_subclass(lock, sub) do { } while (0) #define lockdep_set_novalidate_class(lock) do { } while (0) /* * We don't define lockdep_match_class() and lockdep_match_key() for !LOCKDEP * case since the result is not well defined and the caller should rather * #ifdef the call himself. */ # define lockdep_reset() do { debug_locks = 1; } while (0) # define lockdep_free_key_range(start, size) do { } while (0) # define lockdep_sys_exit() do { } while (0) static inline void lockdep_register_key(struct lock_class_key *key) { } static inline void lockdep_unregister_key(struct lock_class_key *key) { } #define lockdep_depth(tsk) (0) #define lockdep_is_held_type(l, r) (1) #define lockdep_assert_held(l) do { (void)(l); } while (0) #define lockdep_assert_held_write(l) do { (void)(l); } while (0) #define lockdep_assert_held_read(l) do { (void)(l); } while (0) #define lockdep_assert_held_once(l) do { (void)(l); } while (0) #define lockdep_assert_none_held_once() do { } while (0) #define lockdep_recursing(tsk) (0) #define NIL_COOKIE (struct pin_cookie){ } #define lockdep_pin_lock(l) ({ struct pin_cookie cookie = { }; cookie; }) #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) #endif /* !LOCKDEP */ enum xhlock_context_t { XHLOCK_HARD, XHLOCK_SOFT, XHLOCK_CTX_NR, }; #define lockdep_init_map_crosslock(m, n, k, s) do {} while (0) /* * To initialize a lockdep_map statically use this macro. * Note that _name must not be NULL. */ #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ { .name = (_name), .key = (void *)(_key), } static inline void lockdep_invariant_state(bool force) {} static inline void lockdep_free_task(struct task_struct *task) {} #ifdef CONFIG_LOCK_STAT extern void lock_contended(struct lockdep_map *lock, unsigned long ip); extern void lock_acquired(struct lockdep_map *lock, unsigned long ip); #define LOCK_CONTENDED(_lock, try, lock) \ do { \ if (!try(_lock)) { \ lock_contended(&(_lock)->dep_map, _RET_IP_); \ lock(_lock); \ } \ lock_acquired(&(_lock)->dep_map, _RET_IP_); \ } while (0) #define LOCK_CONTENDED_RETURN(_lock, try, lock) \ ({ \ int ____err = 0; \ if (!try(_lock)) { \ lock_contended(&(_lock)->dep_map, _RET_IP_); \ ____err = lock(_lock); \ } \ if (!____err) \ lock_acquired(&(_lock)->dep_map, _RET_IP_); \ ____err; \ }) #else /* CONFIG_LOCK_STAT */ #define lock_contended(lockdep_map, ip) do {} while (0) #define lock_acquired(lockdep_map, ip) do {} while (0) #define LOCK_CONTENDED(_lock, try, lock) \ lock(_lock) #define LOCK_CONTENDED_RETURN(_lock, try, lock) \ lock(_lock) #endif /* CONFIG_LOCK_STAT */ #ifdef CONFIG_LOCKDEP /* * On lockdep we dont want the hand-coded irq-enable of * _raw_*_lock_flags() code, because lockdep assumes * that interrupts are not re-enabled during lock-acquire: */ #define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \ LOCK_CONTENDED((_lock), (try), (lock)) #else /* CONFIG_LOCKDEP */ #define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \ lockfl((_lock), (flags)) #endif /* CONFIG_LOCKDEP */ #ifdef CONFIG_PROVE_LOCKING extern void print_irqtrace_events(struct task_struct *curr); #else static inline void print_irqtrace_events(struct task_struct *curr) { } #endif /* Variable used to make lockdep treat read_lock() as recursive in selftests */ #ifdef CONFIG_DEBUG_LOCKING_API_SELFTESTS extern unsigned int force_read_lock_recursive; #else /* CONFIG_DEBUG_LOCKING_API_SELFTESTS */ #define force_read_lock_recursive 0 #endif /* CONFIG_DEBUG_LOCKING_API_SELFTESTS */ #ifdef CONFIG_LOCKDEP extern bool read_lock_is_recursive(void); #else /* CONFIG_LOCKDEP */ /* If !LOCKDEP, the value is meaningless */ #define read_lock_is_recursive() 0 #endif /* * For trivial one-depth nesting of a lock-class, the following * global define can be used. (Subsystems with multiple levels * of nesting should define their own lock-nesting subclasses.) */ #define SINGLE_DEPTH_NESTING 1 /* * Map the dependency ops to NOP or to real lockdep ops, depending * on the per lock-class debug mode: */ #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i) #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 1, n, i) #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 1, n, i) #define spin_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define spin_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) #define spin_release(l, i) lock_release(l, i) #define rwlock_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define rwlock_acquire_read(l, s, t, i) \ do { \ if (read_lock_is_recursive()) \ lock_acquire_shared_recursive(l, s, t, NULL, i); \ else \ lock_acquire_shared(l, s, t, NULL, i); \ } while (0) #define rwlock_release(l, i) lock_release(l, i) #define seqcount_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define seqcount_acquire_read(l, s, t, i) lock_acquire_shared_recursive(l, s, t, NULL, i) #define seqcount_release(l, i) lock_release(l, i) #define mutex_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define mutex_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) #define mutex_release(l, i) lock_release(l, i) #define rwsem_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i) #define rwsem_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i) #define rwsem_acquire_read(l, s, t, i) lock_acquire_shared(l, s, t, NULL, i) #define rwsem_release(l, i) lock_release(l, i) #define lock_map_acquire(l) lock_acquire_exclusive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_read(l) lock_acquire_shared_recursive(l, 0, 0, NULL, _THIS_IP_) #define lock_map_acquire_tryread(l) lock_acquire_shared_recursive(l, 0, 1, NULL, _THIS_IP_) #define lock_map_release(l) lock_release(l, _THIS_IP_) #ifdef CONFIG_PROVE_LOCKING # define might_lock(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, 0, 0, 0, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) # define might_lock_read(lock) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_); \ lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) # define might_lock_nested(lock, subclass) \ do { \ typecheck(struct lockdep_map *, &(lock)->dep_map); \ lock_acquire(&(lock)->dep_map, subclass, 0, 1, 1, NULL, \ _THIS_IP_); \ lock_release(&(lock)->dep_map, _THIS_IP_); \ } while (0) DECLARE_PER_CPU(int, hardirqs_enabled); DECLARE_PER_CPU(int, hardirq_context); DECLARE_PER_CPU(unsigned int, lockdep_recursion); #define __lockdep_enabled (debug_locks && !this_cpu_read(lockdep_recursion)) #define lockdep_assert_irqs_enabled() \ do { \ WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_irqs_disabled() \ do { \ WARN_ON_ONCE(__lockdep_enabled && this_cpu_read(hardirqs_enabled)); \ } while (0) #define lockdep_assert_in_irq() \ do { \ WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirq_context)); \ } while (0) #define lockdep_assert_preemption_enabled() \ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ __lockdep_enabled && \ (preempt_count() != 0 || \ !this_cpu_read(hardirqs_enabled))); \ } while (0) #define lockdep_assert_preemption_disabled() \ do { \ WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT) && \ __lockdep_enabled && \ (preempt_count() == 0 && \ this_cpu_read(hardirqs_enabled))); \ } while (0) #else # define might_lock(lock) do { } while (0) # define might_lock_read(lock) do { } while (0) # define might_lock_nested(lock, subclass) do { } while (0) # define lockdep_assert_irqs_enabled() do { } while (0) # define lockdep_assert_irqs_disabled() do { } while (0) # define lockdep_assert_in_irq() do { } while (0) # define lockdep_assert_preemption_enabled() do { } while (0) # define lockdep_assert_preemption_disabled() do { } while (0) #endif #ifdef CONFIG_PROVE_RAW_LOCK_NESTING # define lockdep_assert_RT_in_threaded_ctx() do { \ WARN_ONCE(debug_locks && !current->lockdep_recursion && \ lockdep_hardirq_context() && \ !(current->hardirq_threaded || current->irq_config), \ "Not in threaded context on PREEMPT_RT as expected\n"); \ } while (0) #else # define lockdep_assert_RT_in_threaded_ctx() do { } while (0) #endif #ifdef CONFIG_LOCKDEP void lockdep_rcu_suspicious(const char *file, const int line, const char *s); #else static inline void lockdep_rcu_suspicious(const char *file, const int line, const char *s) { } #endif #endif /* __LINUX_LOCKDEP_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BITOPS_H #define _ASM_X86_BITOPS_H /* * Copyright 1992, Linus Torvalds. * * Note: inlines with more than a single statement should be marked * __always_inline to avoid problems with older gcc's inlining heuristics. */ #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif #include <linux/compiler.h> #include <asm/alternative.h> #include <asm/rmwcc.h> #include <asm/barrier.h> #if BITS_PER_LONG == 32 # define _BITOPS_LONG_SHIFT 5 #elif BITS_PER_LONG == 64 # define _BITOPS_LONG_SHIFT 6 #else # error "Unexpected BITS_PER_LONG" #endif #define BIT_64(n) (U64_C(1) << (n)) /* * These have to be done with inline assembly: that way the bit-setting * is guaranteed to be atomic. All bit operations return 0 if the bit * was cleared before the operation and != 0 if it was not. * * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). */ #define RLONG_ADDR(x) "m" (*(volatile long *) (x)) #define WBYTE_ADDR(x) "+m" (*(volatile char *) (x)) #define ADDR RLONG_ADDR(addr) /* * We do the locked ops that don't return the old value as * a mask operation on a byte. */ #define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3)) #define CONST_MASK(nr) (1 << ((nr) & 7)) static __always_inline void arch_set_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "orb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (CONST_MASK(nr)) : "memory"); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline void arch___set_bit(long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline void arch_clear_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "andb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (~CONST_MASK(nr))); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline void arch_clear_bit_unlock(long nr, volatile unsigned long *addr) { barrier(); arch_clear_bit(nr, addr); } static __always_inline void arch___clear_bit(long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline bool arch_clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) { bool negative; asm volatile(LOCK_PREFIX "andb %2,%1" CC_SET(s) : CC_OUT(s) (negative), WBYTE_ADDR(addr) : "ir" ((char) ~(1 << nr)) : "memory"); return negative; } #define arch_clear_bit_unlock_is_negative_byte \ arch_clear_bit_unlock_is_negative_byte static __always_inline void arch___clear_bit_unlock(long nr, volatile unsigned long *addr) { arch___clear_bit(nr, addr); } static __always_inline void arch___change_bit(long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline void arch_change_bit(long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { asm volatile(LOCK_PREFIX "xorb %b1,%0" : CONST_MASK_ADDR(nr, addr) : "iq" (CONST_MASK(nr))); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } static __always_inline bool arch_test_and_set_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr); } static __always_inline bool arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr) { return arch_test_and_set_bit(nr, addr); } static __always_inline bool arch___test_and_set_bit(long nr, volatile unsigned long *addr) { bool oldbit; asm(__ASM_SIZE(bts) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_and_clear_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr); } /* * Note: the operation is performed atomically with respect to * the local CPU, but not other CPUs. Portable code should not * rely on this behaviour. * KVM relies on this behaviour on x86 for modifying memory that is also * accessed from a hypervisor on the same CPU if running in a VM: don't change * this without also updating arch/x86/kernel/kvm.c */ static __always_inline bool arch___test_and_clear_bit(long nr, volatile unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(btr) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch___test_and_change_bit(long nr, volatile unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(btc) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : ADDR, "Ir" (nr) : "memory"); return oldbit; } static __always_inline bool arch_test_and_change_bit(long nr, volatile unsigned long *addr) { return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); } static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) { return ((1UL << (nr & (BITS_PER_LONG-1))) & (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr) { bool oldbit; asm volatile(__ASM_SIZE(bt) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory"); return oldbit; } #define arch_test_bit(nr, addr) \ (__builtin_constant_p((nr)) \ ? constant_test_bit((nr), (addr)) \ : variable_test_bit((nr), (addr))) /** * __ffs - find first set bit in word * @word: The word to search * * Undefined if no bit exists, so code should check against 0 first. */ static __always_inline unsigned long __ffs(unsigned long word) { asm("rep; bsf %1,%0" : "=r" (word) : "rm" (word)); return word; } /** * ffz - find first zero bit in word * @word: The word to search * * Undefined if no zero exists, so code should check against ~0UL first. */ static __always_inline unsigned long ffz(unsigned long word) { asm("rep; bsf %1,%0" : "=r" (word) : "r" (~word)); return word; } /* * __fls: find last set bit in word * @word: The word to search * * Undefined if no set bit exists, so code should check against 0 first. */ static __always_inline unsigned long __fls(unsigned long word) { asm("bsr %1,%0" : "=r" (word) : "rm" (word)); return word; } #undef ADDR #ifdef __KERNEL__ /** * ffs - find first set bit in word * @x: the word to search * * This is defined the same way as the libc and compiler builtin ffs * routines, therefore differs in spirit from the other bitops. * * ffs(value) returns 0 if value is 0 or the position of the first * set bit if value is nonzero. The first (least significant) bit * is at position 1. */ static __always_inline int ffs(int x) { int r; #ifdef CONFIG_X86_64 /* * AMD64 says BSFL won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before, except that the * top 32 bits will be cleared. * * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ asm("bsfl %1,%0" : "=r" (r) : "rm" (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsfl %1,%0\n\t" "cmovzl %2,%0" : "=&r" (r) : "rm" (x), "r" (-1)); #else asm("bsfl %1,%0\n\t" "jnz 1f\n\t" "movl $-1,%0\n" "1:" : "=r" (r) : "rm" (x)); #endif return r + 1; } /** * fls - find last set bit in word * @x: the word to search * * This is defined in a similar way as the libc and compiler builtin * ffs, but returns the position of the most significant set bit. * * fls(value) returns 0 if value is 0 or the position of the last * set bit if value is nonzero. The last (most significant) bit is * at position 32. */ static __always_inline int fls(unsigned int x) { int r; #ifdef CONFIG_X86_64 /* * AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before, except that the * top 32 bits will be cleared. * * We cannot do this on 32 bits because at the very least some * 486 CPUs did not behave this way. */ asm("bsrl %1,%0" : "=r" (r) : "rm" (x), "0" (-1)); #elif defined(CONFIG_X86_CMOV) asm("bsrl %1,%0\n\t" "cmovzl %2,%0" : "=&r" (r) : "rm" (x), "rm" (-1)); #else asm("bsrl %1,%0\n\t" "jnz 1f\n\t" "movl $-1,%0\n" "1:" : "=r" (r) : "rm" (x)); #endif return r + 1; } /** * fls64 - find last set bit in a 64-bit word * @x: the word to search * * This is defined in a similar way as the libc and compiler builtin * ffsll, but returns the position of the most significant set bit. * * fls64(value) returns 0 if value is 0 or the position of the last * set bit if value is nonzero. The last (most significant) bit is * at position 64. */ #ifdef CONFIG_X86_64 static __always_inline int fls64(__u64 x) { int bitpos = -1; /* * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its * value is written to set it to the same as before. */ asm("bsrq %1,%q0" : "+r" (bitpos) : "rm" (x)); return bitpos + 1; } #else #include <asm-generic/bitops/fls64.h> #endif #include <asm-generic/bitops/find.h> #include <asm-generic/bitops/sched.h> #include <asm/arch_hweight.h> #include <asm-generic/bitops/const_hweight.h> #include <asm-generic/bitops/instrumented-atomic.h> #include <asm-generic/bitops/instrumented-non-atomic.h> #include <asm-generic/bitops/instrumented-lock.h> #include <asm-generic/bitops/le.h> #include <asm-generic/bitops/ext2-atomic-setbit.h> #endif /* __KERNEL__ */ #endif /* _ASM_X86_BITOPS_H */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/mmap.c * * Written by obz. * * Address space accounting code <alan@lxorguk.ukuu.org.uk> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> #include <linux/vmacache.h> #include <linux/shm.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/capability.h> #include <linux/init.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <linux/profile.h> #include <linux/export.h> #include <linux/mount.h> #include <linux/mempolicy.h> #include <linux/rmap.h> #include <linux/mmu_notifier.h> #include <linux/mmdebug.h> #include <linux/perf_event.h> #include <linux/audit.h> #include <linux/khugepaged.h> #include <linux/uprobes.h> #include <linux/rbtree_augmented.h> #include <linux/notifier.h> #include <linux/memory.h> #include <linux/printk.h> #include <linux/userfaultfd_k.h> #include <linux/moduleparam.h> #include <linux/pkeys.h> #include <linux/oom.h> #include <linux/sched/mm.h> #include <linux/memfd.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> #include <asm/tlb.h> #include <asm/mmu_context.h> #define CREATE_TRACE_POINTS #include <trace/events/mmap.h> #include "internal.h" #ifndef arch_mmap_check #define arch_mmap_check(addr, len, flags) (0) #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN; const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX; int mmap_rnd_bits __read_mostly = CONFIG_ARCH_MMAP_RND_BITS; #endif #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS const int mmap_rnd_compat_bits_min = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MIN; const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; #endif static bool ignore_rlimit_data; core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end); /* description of effects of mapping type and prot in current implementation. * this is due to the limited x86 page protection hardware. The expected * behavior is in parens: * * map_type prot * PROT_NONE PROT_READ PROT_WRITE PROT_EXEC * MAP_SHARED r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (yes) yes w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes * * MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes * w: (no) no w: (no) no w: (copy) copy w: (no) no * x: (no) no x: (no) yes x: (no) yes x: (yes) yes */ pgprot_t protection_map[16] __ro_after_init = { __P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111, __S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111 }; #ifndef CONFIG_ARCH_HAS_FILTER_PGPROT static inline pgprot_t arch_filter_pgprot(pgprot_t prot) { return prot; } #endif pgprot_t vm_get_page_prot(unsigned long vm_flags) { pgprot_t ret = __pgprot(pgprot_val(protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) | pgprot_val(arch_vm_get_page_prot(vm_flags))); return arch_filter_pgprot(ret); } EXPORT_SYMBOL(vm_get_page_prot); static pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags) { return pgprot_modify(oldprot, vm_get_page_prot(vm_flags)); } /* Update vma->vm_page_prot to reflect vma->vm_flags. */ void vma_set_page_prot(struct vm_area_struct *vma) { unsigned long vm_flags = vma->vm_flags; pgprot_t vm_page_prot; vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags); if (vma_wants_writenotify(vma, vm_page_prot)) { vm_flags &= ~VM_SHARED; vm_page_prot = vm_pgprot_modify(vm_page_prot, vm_flags); } /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */ WRITE_ONCE(vma->vm_page_prot, vm_page_prot); } /* * Requires inode->i_mapping->i_mmap_rwsem */ static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct file *file, struct address_space *mapping) { if (vma->vm_flags & VM_DENYWRITE) allow_write_access(file); if (vma_is_shared_maywrite(vma)) mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } /* * Unlink a file-based vm structure from its interval tree, to hide * vma from rmap and vmtruncate before freeing its page tables. */ void unlink_file_vma(struct vm_area_struct *vma) { struct file *file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; i_mmap_lock_write(mapping); __remove_shared_vm_struct(vma, file, mapping); i_mmap_unlock_write(mapping); } } /* * Close a vm structure and free it, returning the next. */ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) { struct vm_area_struct *next = vma->vm_next; might_sleep(); vma_close(vma); if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); vm_area_free(vma); return next; } static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, struct list_head *uf); SYSCALL_DEFINE1(brk, unsigned long, brk) { unsigned long retval; unsigned long newbrk, oldbrk, origbrk; struct mm_struct *mm = current->mm; struct vm_area_struct *next; unsigned long min_brk; bool populate; bool downgraded = false; LIST_HEAD(uf); if (mmap_write_lock_killable(mm)) return -EINTR; origbrk = mm->brk; #ifdef CONFIG_COMPAT_BRK /* * CONFIG_COMPAT_BRK can still be overridden by setting * randomize_va_space to 2, which will still cause mm->start_brk * to be arbitrarily shifted */ if (current->brk_randomized) min_brk = mm->start_brk; else min_brk = mm->end_data; #else min_brk = mm->start_brk; #endif if (brk < min_brk) goto out; /* * Check against rlimit here. If this check is done later after the test * of oldbrk with newbrk then it can escape the test and let the data * segment grow beyond its set limit the in case where the limit is * not page aligned -Ram Gupta */ if (check_data_rlimit(rlimit(RLIMIT_DATA), brk, mm->start_brk, mm->end_data, mm->start_data)) goto out; newbrk = PAGE_ALIGN(brk); oldbrk = PAGE_ALIGN(mm->brk); if (oldbrk == newbrk) { mm->brk = brk; goto success; } /* * Always allow shrinking brk. * __do_munmap() may downgrade mmap_lock to read. */ if (brk <= mm->brk) { int ret; /* * mm->brk must to be protected by write mmap_lock so update it * before downgrading mmap_lock. When __do_munmap() fails, * mm->brk will be restored from origbrk. */ mm->brk = brk; ret = __do_munmap(mm, newbrk, oldbrk-newbrk, &uf, true); if (ret < 0) { mm->brk = origbrk; goto out; } else if (ret == 1) { downgraded = true; } goto success; } /* Check against existing mmap mappings. */ next = find_vma(mm, oldbrk); if (next && newbrk + PAGE_SIZE > vm_start_gap(next)) goto out; /* Ok, looks good - let it rip. */ if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0) goto out; mm->brk = brk; success: populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0; if (downgraded) mmap_read_unlock(mm); else mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(oldbrk, newbrk - oldbrk); return brk; out: retval = origbrk; mmap_write_unlock(mm); return retval; } static inline unsigned long vma_compute_gap(struct vm_area_struct *vma) { unsigned long gap, prev_end; /* * Note: in the rare case of a VM_GROWSDOWN above a VM_GROWSUP, we * allow two stack_guard_gaps between them here, and when choosing * an unmapped area; whereas when expanding we only require one. * That's a little inconsistent, but keeps the code here simpler. */ gap = vm_start_gap(vma); if (vma->vm_prev) { prev_end = vm_end_gap(vma->vm_prev); if (gap > prev_end) gap -= prev_end; else gap = 0; } return gap; } #ifdef CONFIG_DEBUG_VM_RB static unsigned long vma_compute_subtree_gap(struct vm_area_struct *vma) { unsigned long max = vma_compute_gap(vma), subtree_gap; if (vma->vm_rb.rb_left) { subtree_gap = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb)->rb_subtree_gap; if (subtree_gap > max) max = subtree_gap; } if (vma->vm_rb.rb_right) { subtree_gap = rb_entry(vma->vm_rb.rb_right, struct vm_area_struct, vm_rb)->rb_subtree_gap; if (subtree_gap > max) max = subtree_gap; } return max; } static int browse_rb(struct mm_struct *mm) { struct rb_root *root = &mm->mm_rb; int i = 0, j, bug = 0; struct rb_node *nd, *pn = NULL; unsigned long prev = 0, pend = 0; for (nd = rb_first(root); nd; nd = rb_next(nd)) { struct vm_area_struct *vma; vma = rb_entry(nd, struct vm_area_struct, vm_rb); if (vma->vm_start < prev) { pr_emerg("vm_start %lx < prev %lx\n", vma->vm_start, prev); bug = 1; } if (vma->vm_start < pend) { pr_emerg("vm_start %lx < pend %lx\n", vma->vm_start, pend); bug = 1; } if (vma->vm_start > vma->vm_end) { pr_emerg("vm_start %lx > vm_end %lx\n", vma->vm_start, vma->vm_end); bug = 1; } spin_lock(&mm->page_table_lock); if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) { pr_emerg("free gap %lx, correct %lx\n", vma->rb_subtree_gap, vma_compute_subtree_gap(vma)); bug = 1; } spin_unlock(&mm->page_table_lock); i++; pn = nd; prev = vma->vm_start; pend = vma->vm_end; } j = 0; for (nd = pn; nd; nd = rb_prev(nd)) j++; if (i != j) { pr_emerg("backwards %d, forwards %d\n", j, i); bug = 1; } return bug ? -1 : i; } static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore) { struct rb_node *nd; for (nd = rb_first(root); nd; nd = rb_next(nd)) { struct vm_area_struct *vma; vma = rb_entry(nd, struct vm_area_struct, vm_rb); VM_BUG_ON_VMA(vma != ignore && vma->rb_subtree_gap != vma_compute_subtree_gap(vma), vma); } } static void validate_mm(struct mm_struct *mm) { int bug = 0; int i = 0; unsigned long highest_address = 0; struct vm_area_struct *vma = mm->mmap; while (vma) { struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; if (anon_vma) { anon_vma_lock_read(anon_vma); list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_verify(avc); anon_vma_unlock_read(anon_vma); } highest_address = vm_end_gap(vma); vma = vma->vm_next; i++; } if (i != mm->map_count) { pr_emerg("map_count %d vm_next %d\n", mm->map_count, i); bug = 1; } if (highest_address != mm->highest_vm_end) { pr_emerg("mm->highest_vm_end %lx, found %lx\n", mm->highest_vm_end, highest_address); bug = 1; } i = browse_rb(mm); if (i != mm->map_count) { if (i != -1) pr_emerg("map_count %d rb %d\n", mm->map_count, i); bug = 1; } VM_BUG_ON_MM(bug, mm); } #else #define validate_mm_rb(root, ignore) do { } while (0) #define validate_mm(mm) do { } while (0) #endif RB_DECLARE_CALLBACKS_MAX(static, vma_gap_callbacks, struct vm_area_struct, vm_rb, unsigned long, rb_subtree_gap, vma_compute_gap) /* * Update augmented rbtree rb_subtree_gap values after vma->vm_start or * vma->vm_prev->vm_end values changed, without modifying the vma's position * in the rbtree. */ static void vma_gap_update(struct vm_area_struct *vma) { /* * As it turns out, RB_DECLARE_CALLBACKS_MAX() already created * a callback function that does exactly what we want. */ vma_gap_callbacks_propagate(&vma->vm_rb, NULL); } static inline void vma_rb_insert(struct vm_area_struct *vma, struct rb_root *root) { /* All rb_subtree_gap values must be consistent prior to insertion */ validate_mm_rb(root, NULL); rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks); } static void __vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root) { /* * Note rb_erase_augmented is a fairly large inline function, * so make sure we instantiate it only once with our desired * augmented rbtree callbacks. */ rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks); } static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma, struct rb_root *root, struct vm_area_struct *ignore) { /* * All rb_subtree_gap values must be consistent prior to erase, * with the possible exception of * * a. the "next" vma being erased if next->vm_start was reduced in * __vma_adjust() -> __vma_unlink() * b. the vma being erased in detach_vmas_to_be_unmapped() -> * vma_rb_erase() */ validate_mm_rb(root, ignore); __vma_rb_erase(vma, root); } static __always_inline void vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root) { vma_rb_erase_ignore(vma, root, vma); } /* * vma has some anon_vma assigned, and is already inserted on that * anon_vma's interval trees. * * Before updating the vma's vm_start / vm_end / vm_pgoff fields, the * vma must be removed from the anon_vma's interval trees using * anon_vma_interval_tree_pre_update_vma(). * * After the update, the vma will be reinserted using * anon_vma_interval_tree_post_update_vma(). * * The entire update must be protected by exclusive mmap_lock and by * the root anon_vma's mutex. */ static inline void anon_vma_interval_tree_pre_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_remove(avc, &avc->anon_vma->rb_root); } static inline void anon_vma_interval_tree_post_update_vma(struct vm_area_struct *vma) { struct anon_vma_chain *avc; list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) anon_vma_interval_tree_insert(avc, &avc->anon_vma->rb_root); } static int find_vma_links(struct mm_struct *mm, unsigned long addr, unsigned long end, struct vm_area_struct **pprev, struct rb_node ***rb_link, struct rb_node **rb_parent) { struct rb_node **__rb_link, *__rb_parent, *rb_prev; __rb_link = &mm->mm_rb.rb_node; rb_prev = __rb_parent = NULL; while (*__rb_link) { struct vm_area_struct *vma_tmp; __rb_parent = *__rb_link; vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb); if (vma_tmp->vm_end > addr) { /* Fail if an existing vma overlaps the area */ if (vma_tmp->vm_start < end) return -ENOMEM; __rb_link = &__rb_parent->rb_left; } else { rb_prev = __rb_parent; __rb_link = &__rb_parent->rb_right; } } *pprev = NULL; if (rb_prev) *pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb); *rb_link = __rb_link; *rb_parent = __rb_parent; return 0; } /* * vma_next() - Get the next VMA. * @mm: The mm_struct. * @vma: The current vma. * * If @vma is NULL, return the first vma in the mm. * * Returns: The next VMA after @vma. */ static inline struct vm_area_struct *vma_next(struct mm_struct *mm, struct vm_area_struct *vma) { if (!vma) return mm->mmap; return vma->vm_next; } /* * munmap_vma_range() - munmap VMAs that overlap a range. * @mm: The mm struct * @start: The start of the range. * @len: The length of the range. * @pprev: pointer to the pointer that will be set to previous vm_area_struct * @rb_link: the rb_node * @rb_parent: the parent rb_node * * Find all the vm_area_struct that overlap from @start to * @end and munmap them. Set @pprev to the previous vm_area_struct. * * Returns: -ENOMEM on munmap failure or 0 on success. */ static inline int munmap_vma_range(struct mm_struct *mm, unsigned long start, unsigned long len, struct vm_area_struct **pprev, struct rb_node ***link, struct rb_node **parent, struct list_head *uf) { while (find_vma_links(mm, start, start + len, pprev, link, parent)) if (do_munmap(mm, start, len, uf)) return -ENOMEM; return 0; } static unsigned long count_vma_pages_range(struct mm_struct *mm, unsigned long addr, unsigned long end) { unsigned long nr_pages = 0; struct vm_area_struct *vma; /* Find first overlaping mapping */ vma = find_vma_intersection(mm, addr, end); if (!vma) return 0; nr_pages = (min(end, vma->vm_end) - max(addr, vma->vm_start)) >> PAGE_SHIFT; /* Iterate over the rest of the overlaps */ for (vma = vma->vm_next; vma; vma = vma->vm_next) { unsigned long overlap_len; if (vma->vm_start > end) break; overlap_len = min(end, vma->vm_end) - vma->vm_start; nr_pages += overlap_len >> PAGE_SHIFT; } return nr_pages; } void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, struct rb_node **rb_link, struct rb_node *rb_parent) { /* Update tracking information for the gap following the new vma. */ if (vma->vm_next) vma_gap_update(vma->vm_next); else mm->highest_vm_end = vm_end_gap(vma); /* * vma->vm_prev wasn't known when we followed the rbtree to find the * correct insertion point for that vma. As a result, we could not * update the vma vm_rb parents rb_subtree_gap values on the way down. * So, we first insert the vma with a zero rb_subtree_gap value * (to be consistent with what we did on the way down), and then * immediately update the gap to the correct value. Finally we * rebalance the rbtree after all augmented values have been set. */ rb_link_node(&vma->vm_rb, rb_parent, rb_link); vma->rb_subtree_gap = 0; vma_gap_update(vma); vma_rb_insert(vma, &mm->mm_rb); } static void __vma_link_file(struct vm_area_struct *vma) { struct file *file; file = vma->vm_file; if (file) { struct address_space *mapping = file->f_mapping; if (vma->vm_flags & VM_DENYWRITE) put_write_access(file_inode(file)); if (vma_is_shared_maywrite(vma)) mapping_allow_writable(mapping); flush_dcache_mmap_lock(mapping); vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } } static void __vma_link(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node **rb_link, struct rb_node *rb_parent) { __vma_link_list(mm, vma, prev); __vma_link_rb(mm, vma, rb_link, rb_parent); } static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node **rb_link, struct rb_node *rb_parent) { struct address_space *mapping = NULL; if (vma->vm_file) { mapping = vma->vm_file->f_mapping; i_mmap_lock_write(mapping); } __vma_link(mm, vma, prev, rb_link, rb_parent); __vma_link_file(vma); if (mapping) i_mmap_unlock_write(mapping); mm->map_count++; validate_mm(mm); } /* * Helper for vma_adjust() in the split_vma insert case: insert a vma into the * mm's list and rbtree. It has already been inserted into the interval tree. */ static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { struct vm_area_struct *prev; struct rb_node **rb_link, *rb_parent; if (find_vma_links(mm, vma->vm_start, vma->vm_end, &prev, &rb_link, &rb_parent)) BUG(); __vma_link(mm, vma, prev, rb_link, rb_parent); mm->map_count++; } static __always_inline void __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *ignore) { vma_rb_erase_ignore(vma, &mm->mm_rb, ignore); __vma_unlink_list(mm, vma); /* Kill the cache */ vmacache_invalidate(mm); } /* * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that * is already present in an i_mmap tree without adjusting the tree. * The following helper function should be used when such adjustments * are necessary. The "insert" vma (if any) is to be inserted * before we drop the necessary locks. */ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, struct vm_area_struct *expand) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next = vma->vm_next, *orig_vma = vma; struct address_space *mapping = NULL; struct rb_root_cached *root = NULL; struct anon_vma *anon_vma = NULL; struct file *file = vma->vm_file; bool start_changed = false, end_changed = false; long adjust_next = 0; int remove_next = 0; if (next && !insert) { struct vm_area_struct *exporter = NULL, *importer = NULL; if (end >= next->vm_end) { /* * vma expands, overlapping all the next, and * perhaps the one after too (mprotect case 6). * The only other cases that gets here are * case 1, case 7 and case 8. */ if (next == expand) { /* * The only case where we don't expand "vma" * and we expand "next" instead is case 8. */ VM_WARN_ON(end != next->vm_end); /* * remove_next == 3 means we're * removing "vma" and that to do so we * swapped "vma" and "next". */ remove_next = 3; VM_WARN_ON(file != next->vm_file); swap(vma, next); } else { VM_WARN_ON(expand != vma); /* * case 1, 6, 7, remove_next == 2 is case 6, * remove_next == 1 is case 1 or 7. */ remove_next = 1 + (end > next->vm_end); VM_WARN_ON(remove_next == 2 && end != next->vm_next->vm_end); /* trim end to next, for case 6 first pass */ end = next->vm_end; } exporter = next; importer = vma; /* * If next doesn't have anon_vma, import from vma after * next, if the vma overlaps with it. */ if (remove_next == 2 && !next->anon_vma) exporter = next->vm_next; } else if (end > next->vm_start) { /* * vma expands, overlapping part of the next: * mprotect case 5 shifting the boundary up. */ adjust_next = (end - next->vm_start); exporter = next; importer = vma; VM_WARN_ON(expand != importer); } else if (end < vma->vm_end) { /* * vma shrinks, and !insert tells it's not * split_vma inserting another: so it must be * mprotect case 4 shifting the boundary down. */ adjust_next = -(vma->vm_end - end); exporter = vma; importer = next; VM_WARN_ON(expand != importer); } /* * Easily overlooked: when mprotect shifts the boundary, * make sure the expanding vma has anon_vma set if the * shrinking vma had, to cover any anon pages imported. */ if (exporter && exporter->anon_vma && !importer->anon_vma) { int error; importer->anon_vma = exporter->anon_vma; error = anon_vma_clone(importer, exporter); if (error) return error; } } again: /* * Get rid of huge pages and shared page tables straddling the split * boundary. */ vma_adjust_trans_huge(orig_vma, start, end, adjust_next); if (is_vm_hugetlb_page(orig_vma)) { hugetlb_split(orig_vma, start); hugetlb_split(orig_vma, end); } if (file) { mapping = file->f_mapping; root = &mapping->i_mmap; uprobe_munmap(vma, vma->vm_start, vma->vm_end); if (adjust_next) uprobe_munmap(next, next->vm_start, next->vm_end); i_mmap_lock_write(mapping); if (insert) { /* * Put into interval tree now, so instantiated pages * are visible to arm/parisc __flush_dcache_page * throughout; but we cannot insert into address * space until vma start or end is updated. */ __vma_link_file(insert); } } anon_vma = vma->anon_vma; if (!anon_vma && adjust_next) anon_vma = next->anon_vma; if (anon_vma) { VM_WARN_ON(adjust_next && next->anon_vma && anon_vma != next->anon_vma); anon_vma_lock_write(anon_vma); anon_vma_interval_tree_pre_update_vma(vma); if (adjust_next) anon_vma_interval_tree_pre_update_vma(next); } if (file) { flush_dcache_mmap_lock(mapping); vma_interval_tree_remove(vma, root); if (adjust_next) vma_interval_tree_remove(next, root); } if (start != vma->vm_start) { vma->vm_start = start; start_changed = true; } if (end != vma->vm_end) { vma->vm_end = end; end_changed = true; } vma->vm_pgoff = pgoff; if (adjust_next) { next->vm_start += adjust_next; next->vm_pgoff += adjust_next >> PAGE_SHIFT; } if (file) { if (adjust_next) vma_interval_tree_insert(next, root); vma_interval_tree_insert(vma, root); flush_dcache_mmap_unlock(mapping); } if (remove_next) { /* * vma_merge has merged next into vma, and needs * us to remove next before dropping the locks. */ if (remove_next != 3) __vma_unlink(mm, next, next); else /* * vma is not before next if they've been * swapped. * * pre-swap() next->vm_start was reduced so * tell validate_mm_rb to ignore pre-swap() * "next" (which is stored in post-swap() * "vma"). */ __vma_unlink(mm, next, vma); if (file) __remove_shared_vm_struct(next, file, mapping); } else if (insert) { /* * split_vma has split insert from vma, and needs * us to insert it before dropping the locks * (it may either follow vma or precede it). */ __insert_vm_struct(mm, insert); } else { if (start_changed) vma_gap_update(vma); if (end_changed) { if (!next) mm->highest_vm_end = vm_end_gap(vma); else if (!adjust_next) vma_gap_update(next); } } if (anon_vma) { anon_vma_interval_tree_post_update_vma(vma); if (adjust_next) anon_vma_interval_tree_post_update_vma(next); anon_vma_unlock_write(anon_vma); } if (file) { i_mmap_unlock_write(mapping); uprobe_mmap(vma); if (adjust_next) uprobe_mmap(next); } if (remove_next) { if (file) { uprobe_munmap(next, next->vm_start, next->vm_end); fput(file); } if (next->anon_vma) anon_vma_merge(vma, next); mm->map_count--; mpol_put(vma_policy(next)); vm_area_free(next); /* * In mprotect's case 6 (see comments on vma_merge), * we must remove another next too. It would clutter * up the code too much to do both in one go. */ if (remove_next != 3) { /* * If "next" was removed and vma->vm_end was * expanded (up) over it, in turn * "next->vm_prev->vm_end" changed and the * "vma->vm_next" gap must be updated. */ next = vma->vm_next; } else { /* * For the scope of the comment "next" and * "vma" considered pre-swap(): if "vma" was * removed, next->vm_start was expanded (down) * over it and the "next" gap must be updated. * Because of the swap() the post-swap() "vma" * actually points to pre-swap() "next" * (post-swap() "next" as opposed is now a * dangling pointer). */ next = vma; } if (remove_next == 2) { remove_next = 1; end = next->vm_end; goto again; } else if (next) vma_gap_update(next); else { /* * If remove_next == 2 we obviously can't * reach this path. * * If remove_next == 3 we can't reach this * path because pre-swap() next is always not * NULL. pre-swap() "next" is not being * removed and its next->vm_end is not altered * (and furthermore "end" already matches * next->vm_end in remove_next == 3). * * We reach this only in the remove_next == 1 * case if the "next" vma that was removed was * the highest vma of the mm. However in such * case next->vm_end == "end" and the extended * "vma" has vma->vm_end == next->vm_end so * mm->highest_vm_end doesn't need any update * in remove_next == 1 case. */ VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma)); } } if (insert && file) uprobe_mmap(insert); validate_mm(mm); return 0; } /* * If the vma has a ->close operation then the driver probably needs to release * per-vma resources, so we don't attempt to merge those. */ static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, struct vm_userfaultfd_ctx vm_userfaultfd_ctx) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we * match the flags but dirty bit -- the caller should mark * merged VMA as dirty. If dirty bit won't be excluded from * comparison, we increase pressure on the memory system forcing * the kernel to generate new VMAs when old one could be * extended instead. */ if ((vma->vm_flags ^ vm_flags) & ~VM_SOFTDIRTY) return 0; if (vma->vm_file != file) return 0; if (vma->vm_ops && vma->vm_ops->close) return 0; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return 0; return 1; } static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1, struct anon_vma *anon_vma2, struct vm_area_struct *vma) { /* * The list_is_singular() test is to avoid merging VMA cloned from * parents. This can improve scalability caused by anon_vma lock. */ if ((!anon_vma1 || !anon_vma2) && (!vma || list_is_singular(&vma->anon_vma_chain))) return 1; return anon_vma1 == anon_vma2; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * in front of (at a lower virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. * * We don't check here for the merged mmap wrapping around the end of pagecache * indices (16TB on ia32) because do_mmap() does not permit mmap's which * wrap, nor mmaps which cover the final page at index -1UL. */ static int can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return 1; } return 0; } /* * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff) * beyond (at a higher virtual address and file offset than) the vma. * * We cannot merge two vmas if they have differently assigned (non-NULL) * anon_vmas, nor if same anon_vma is assigned but offsets incompatible. */ static int can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; vm_pglen = vma_pages(vma); if (vma->vm_pgoff + vm_pglen == vm_pgoff) return 1; } return 0; } /* * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out * whether that can be merged with its predecessor or its successor. * Or both (it neatly fills a hole). * * In most cases - when called for mmap, brk or mremap - [addr,end) is * certain not to be mapped by the time vma_merge is called; but when * called for mprotect, it is certain to be already mapped (either at * an offset within prev, or at the start of next), and the flags of * this area are about to be changed to vm_flags - and the no-change * case has already been eliminated. * * The following mprotect cases have to be considered, where AAAA is * the area passed down from mprotect_fixup, never extending beyond one * vma, PPPPPP is the prev vma specified, and NNNNNN the next vma after: * * AAAA AAAA AAAA * PPPPPPNNNNNN PPPPPPNNNNNN PPPPPPNNNNNN * cannot merge might become might become * PPNNNNNNNNNN PPPPPPPPPPNN * mmap, brk or case 4 below case 5 below * mremap move: * AAAA AAAA * PPPP NNNN PPPPNNNNXXXX * might become might become * PPPPPPPPPPPP 1 or PPPPPPPPPPPP 6 or * PPPPPPPPNNNN 2 or PPPPPPPPXXXX 7 or * PPPPNNNNNNNN 3 PPPPXXXXXXXX 8 * * It is important for case 8 that the vma NNNN overlapping the * region AAAA is never going to extended over XXXX. Instead XXXX must * be extended in region AAAA and NNNN must be removed. This way in * all cases where vma_merge succeeds, the moment vma_adjust drops the * rmap_locks, the properties of the merged vma will be already * correct for the whole merged range. Some of those properties like * vm_page_prot/vm_flags may be accessed by rmap_walks and they must * be correct for the whole merged range immediately after the * rmap_locks are released. Otherwise if XXXX would be removed and * NNNN would be extended over the XXXX range, remove_migration_ptes * or other rmap walkers (if working on addresses beyond the "end" * parameter) may establish ptes with the wrong permissions of NNNN * instead of the right permissions of XXXX. */ struct vm_area_struct *vma_merge(struct mm_struct *mm, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy, struct vm_userfaultfd_ctx vm_userfaultfd_ctx) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; int err; /* * We later require that vma->vm_flags == vm_flags, * so this tests vma->vm_flags & VM_SPECIAL, too. */ if (vm_flags & VM_SPECIAL) return NULL; next = vma_next(mm, prev); area = next; if (area && area->vm_end == end) /* cases 6, 7, 8 */ next = next->vm_next; /* verify some invariant that must be enforced by the caller */ VM_WARN_ON(prev && addr <= prev->vm_start); VM_WARN_ON(area && end > area->vm_end); VM_WARN_ON(addr >= end); /* * Can it merge with the predecessor? */ if (prev && prev->vm_end == addr && mpol_equal(vma_policy(prev), policy) && can_vma_merge_after(prev, vm_flags, anon_vma, file, pgoff, vm_userfaultfd_ctx)) { /* * OK, it can. Can we now merge in the successor as well? */ if (next && end == next->vm_start && mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, vm_userfaultfd_ctx) && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { /* cases 1, 6 */ err = __vma_adjust(prev, prev->vm_start, next->vm_end, prev->vm_pgoff, NULL, prev); } else /* cases 2, 5, 7 */ err = __vma_adjust(prev, prev->vm_start, end, prev->vm_pgoff, NULL, prev); if (err) return NULL; khugepaged_enter_vma_merge(prev, vm_flags); return prev; } /* * Can this new request be merged in front of next? */ if (next && end == next->vm_start && mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, vm_userfaultfd_ctx)) { if (prev && addr < prev->vm_end) /* case 4 */ err = __vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL, next); else { /* cases 3, 8 */ err = __vma_adjust(area, addr, next->vm_end, next->vm_pgoff - pglen, NULL, next); /* * In case 3 area is already equal to next and * this is a noop, but in case 8 "area" has * been removed and next was expanded over it. */ area = next; } if (err) return NULL; khugepaged_enter_vma_merge(area, vm_flags); return area; } return NULL; } /* * Rough compatibility check to quickly see if it's even worth looking * at sharing an anon_vma. * * They need to have the same vm_file, and the flags can only differ * in things that mprotect may change. * * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that * we can merge the two vma's. For example, we refuse to merge a vma if * there is a vm_ops->close() function, because that indicates that the * driver is doing some kind of reference counting. But that doesn't * really matter for the anon_vma sharing case. */ static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b) { return a->vm_end == b->vm_start && mpol_equal(vma_policy(a), vma_policy(b)) && a->vm_file == b->vm_file && !((a->vm_flags ^ b->vm_flags) & ~(VM_ACCESS_FLAGS | VM_SOFTDIRTY)) && b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT); } /* * Do some basic sanity checking to see if we can re-use the anon_vma * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be * the same as 'old', the other will be the new one that is trying * to share the anon_vma. * * NOTE! This runs with mm_sem held for reading, so it is possible that * the anon_vma of 'old' is concurrently in the process of being set up * by another page fault trying to merge _that_. But that's ok: if it * is being set up, that automatically means that it will be a singleton * acceptable for merging, so we can do all of this optimistically. But * we do that READ_ONCE() to make sure that we never re-load the pointer. * * IOW: that the "list_is_singular()" test on the anon_vma_chain only * matters for the 'stable anon_vma' case (ie the thing we want to avoid * is to return an anon_vma that is "complex" due to having gone through * a fork). * * We also make sure that the two vma's are compatible (adjacent, * and with the same memory policies). That's all stable, even with just * a read lock on the mm_sem. */ static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b) { if (anon_vma_compatible(a, b)) { struct anon_vma *anon_vma = READ_ONCE(old->anon_vma); if (anon_vma && list_is_singular(&old->anon_vma_chain)) return anon_vma; } return NULL; } /* * find_mergeable_anon_vma is used by anon_vma_prepare, to check * neighbouring vmas for a suitable anon_vma, before it goes off * to allocate a new anon_vma. It checks because a repetitive * sequence of mprotects and faults may otherwise lead to distinct * anon_vmas being allocated, preventing vma merge in subsequent * mprotect. */ struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma) { struct anon_vma *anon_vma = NULL; /* Try next first. */ if (vma->vm_next) { anon_vma = reusable_anon_vma(vma->vm_next, vma, vma->vm_next); if (anon_vma) return anon_vma; } /* Try prev next. */ if (vma->vm_prev) anon_vma = reusable_anon_vma(vma->vm_prev, vma->vm_prev, vma); /* * We might reach here with anon_vma == NULL if we can't find * any reusable anon_vma. * There's no absolute need to look only at touching neighbours: * we could search further afield for "compatible" anon_vmas. * But it would probably just be a waste of time searching, * or lead to too many vmas hanging off the same anon_vma. * We're trying to allow mprotect remerging later on, * not trying to minimize memory used for anon_vmas. */ return anon_vma; } /* * If a hint addr is less than mmap_min_addr change hint to be as * low as possible but still greater than mmap_min_addr */ static inline unsigned long round_hint_to_min(unsigned long hint) { hint &= PAGE_MASK; if (((void *)hint != NULL) && (hint < mmap_min_addr)) return PAGE_ALIGN(mmap_min_addr); return hint; } static inline int mlock_future_check(struct mm_struct *mm, unsigned long flags, unsigned long len) { unsigned long locked, lock_limit; /* mlock MCL_FUTURE? */ if (flags & VM_LOCKED) { locked = len >> PAGE_SHIFT; locked += mm->locked_vm; lock_limit = rlimit(RLIMIT_MEMLOCK); lock_limit >>= PAGE_SHIFT; if (locked > lock_limit && !capable(CAP_IPC_LOCK)) return -EAGAIN; } return 0; } static inline u64 file_mmap_size_max(struct file *file, struct inode *inode) { if (S_ISREG(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISBLK(inode->i_mode)) return MAX_LFS_FILESIZE; if (S_ISSOCK(inode->i_mode)) return MAX_LFS_FILESIZE; /* Special "we do even unsigned file positions" case */ if (file->f_mode & FMODE_UNSIGNED_OFFSET) return 0; /* Yes, random drivers might want more. But I'm tired of buggy drivers */ return ULONG_MAX; } static inline bool file_mmap_ok(struct file *file, struct inode *inode, unsigned long pgoff, unsigned long len) { u64 maxsize = file_mmap_size_max(file, inode); if (maxsize && len > maxsize) return false; maxsize -= len; if (pgoff > maxsize >> PAGE_SHIFT) return false; return true; } /* * The caller must write-lock current->mm->mmap_lock. */ unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf) { struct mm_struct *mm = current->mm; vm_flags_t vm_flags; int pkey = 0; *populate = 0; if (!len) return -EINVAL; /* * Does the application expect PROT_READ to imply PROT_EXEC? * * (the exception is when the underlying filesystem is noexec * mounted, in which case we dont add PROT_EXEC.) */ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) if (!(file && path_noexec(&file->f_path))) prot |= PROT_EXEC; /* force arch specific MAP_FIXED handling in get_unmapped_area */ if (flags & MAP_FIXED_NOREPLACE) flags |= MAP_FIXED; if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); /* Careful about overflows.. */ len = PAGE_ALIGN(len); if (!len) return -ENOMEM; /* offset overflow? */ if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) return -EOVERFLOW; /* Too many mappings? */ if (mm->map_count > sysctl_max_map_count) return -ENOMEM; /* Obtain the address to map to. we verify (or select) it and ensure * that it represents a valid section of the address space. */ addr = get_unmapped_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) return addr; if (flags & MAP_FIXED_NOREPLACE) { struct vm_area_struct *vma = find_vma(mm, addr); if (vma && vma->vm_start < addr + len) return -EEXIST; } if (prot == PROT_EXEC) { pkey = execute_only_pkey(mm); if (pkey < 0) pkey = 0; } /* Do simple checking here so the lower-level routines won't have * to. we assume access permissions have been handled by the open * of the memory object, so we don't do any here. */ vm_flags = calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(file, flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; if (flags & MAP_LOCKED) if (!can_do_mlock()) return -EPERM; if (mlock_future_check(mm, vm_flags, len)) return -EAGAIN; if (file) { struct inode *inode = file_inode(file); unsigned int seals = memfd_file_seals(file); unsigned long flags_mask; if (!file_mmap_ok(file, inode, pgoff, len)) return -EOVERFLOW; flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags; switch (flags & MAP_TYPE) { case MAP_SHARED: /* * Force use of MAP_SHARED_VALIDATE with non-legacy * flags. E.g. MAP_SYNC is dangerous to use with * MAP_SHARED as you don't know which consistency model * you will get. We silently ignore unsupported flags * with MAP_SHARED to preserve backward compatibility. */ flags &= LEGACY_MAP_MASK; fallthrough; case MAP_SHARED_VALIDATE: if (flags & ~flags_mask) return -EOPNOTSUPP; if (prot & PROT_WRITE) { if (!(file->f_mode & FMODE_WRITE)) return -EACCES; if (IS_SWAPFILE(file->f_mapping->host)) return -ETXTBSY; } /* * Make sure we don't allow writing to an append-only * file.. */ if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE)) return -EACCES; /* * Make sure there are no mandatory locks on the file. */ if (locks_verify_locked(file)) return -EAGAIN; vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); else if (is_readonly_sealed(seals, vm_flags)) vm_flags &= ~VM_MAYWRITE; fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) return -EACCES; if (path_noexec(&file->f_path)) { if (vm_flags & VM_EXEC) return -EPERM; vm_flags &= ~VM_MAYEXEC; } if (!file->f_op->mmap) return -ENODEV; if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; break; default: return -EINVAL; } } else { switch (flags & MAP_TYPE) { case MAP_SHARED: if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) return -EINVAL; /* * Ignore pgoff. */ pgoff = 0; vm_flags |= VM_SHARED | VM_MAYSHARE; break; case MAP_PRIVATE: /* * Set pgoff according to addr for anon_vma. */ pgoff = addr >> PAGE_SHIFT; break; default: return -EINVAL; } } /* * Set 'VM_NORESERVE' if we should not account for the * memory use of this mapping. */ if (flags & MAP_NORESERVE) { /* We honor MAP_NORESERVE if allowed to overcommit */ if (sysctl_overcommit_memory != OVERCOMMIT_NEVER) vm_flags |= VM_NORESERVE; /* hugetlb applies strict overcommit unless MAP_NORESERVE */ if (file && is_file_hugepages(file)) vm_flags |= VM_NORESERVE; } addr = mmap_region(file, addr, len, vm_flags, pgoff, uf); if (!IS_ERR_VALUE(addr) && ((vm_flags & VM_LOCKED) || (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) *populate = len; return addr; } unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) { struct file *file = NULL; unsigned long retval; if (!(flags & MAP_ANONYMOUS)) { audit_mmap_fd(fd, flags); file = fget(fd); if (!file) return -EBADF; if (is_file_hugepages(file)) { len = ALIGN(len, huge_page_size(hstate_file(file))); } else if (unlikely(flags & MAP_HUGETLB)) { retval = -EINVAL; goto out_fput; } } else if (flags & MAP_HUGETLB) { struct user_struct *user = NULL; struct hstate *hs; hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (!hs) return -EINVAL; len = ALIGN(len, huge_page_size(hs)); /* * VM_NORESERVE is used because the reservations will be * taken when vm_ops->mmap() is called * A dummy user value is used because we are not locking * memory so no accounting is necessary */ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, &user, HUGETLB_ANONHUGE_INODE, (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (IS_ERR(file)) return PTR_ERR(file); } flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); out_fput: if (file) fput(file); return retval; } SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, unsigned long, pgoff) { return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } #ifdef __ARCH_WANT_SYS_OLD_MMAP struct mmap_arg_struct { unsigned long addr; unsigned long len; unsigned long prot; unsigned long flags; unsigned long fd; unsigned long offset; }; SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) { struct mmap_arg_struct a; if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; if (offset_in_page(a.offset)) return -EINVAL; return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset >> PAGE_SHIFT); } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ /* * Some shared mappings will want the pages marked read-only * to track write events. If so, we'll downgrade vm_page_prot * to the private version (using protection_map[] without the * VM_SHARED bit). */ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) { vm_flags_t vm_flags = vma->vm_flags; const struct vm_operations_struct *vm_ops = vma->vm_ops; /* If it was private or non-writable, the write bit is already clear */ if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED))) return 0; /* The backer wishes to know when pages are first written to? */ if (vm_ops && (vm_ops->page_mkwrite || vm_ops->pfn_mkwrite)) return 1; /* The open routine did something to the protections that pgprot_modify * won't preserve? */ if (pgprot_val(vm_page_prot) != pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags))) return 0; /* * Do we need to track softdirty? hugetlb does not support softdirty * tracking yet. */ if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY) && !is_vm_hugetlb_page(vma)) return 1; /* Specialty mapping? */ if (vm_flags & VM_PFNMAP) return 0; /* Can the mapping track the dirty pages? */ return vma->vm_file && vma->vm_file->f_mapping && mapping_can_writeback(vma->vm_file->f_mapping); } /* * We account for memory if it's a private writeable mapping, * not hugepages and VM_NORESERVE wasn't set. */ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags) { /* * hugetlb has its own accounting separate from the core VM * VM_HUGETLB may not be set yet so we cannot check for that flag. */ if (file && is_file_hugepages(file)) return 0; return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE; } static unsigned long __mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev, *merge; int error; struct rb_node **rb_link, *rb_parent; unsigned long charged = 0; /* Check against address space limit. */ if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) { unsigned long nr_pages; /* * MAP_FIXED may remove pages of mappings that intersects with * requested mapping. Account for the pages it would unmap. */ nr_pages = count_vma_pages_range(mm, addr, addr + len); if (!may_expand_vm(mm, vm_flags, (len >> PAGE_SHIFT) - nr_pages)) return -ENOMEM; } /* Clear old maps, set up prev, rb_link, rb_parent, and uf */ if (munmap_vma_range(mm, addr, len, &prev, &rb_link, &rb_parent, uf)) return -ENOMEM; /* * Private writable mapping: check memory availability */ if (accountable_mapping(file, vm_flags)) { charged = len >> PAGE_SHIFT; if (security_vm_enough_memory_mm(mm, charged)) return -ENOMEM; vm_flags |= VM_ACCOUNT; } /* * Can we just expand an old mapping? */ vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX); if (vma) goto out; /* * Determine the object being mapped and call the appropriate * specific mapper. the address has already been validated, but * not unmapped, but the maps are removed from the list. */ vma = vm_area_alloc(mm); if (!vma) { error = -ENOMEM; goto unacct_error; } vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags; vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff; if (file) { if (vm_flags & VM_DENYWRITE) { error = deny_write_access(file); if (error) goto free_vma; } /* ->mmap() can change vma->vm_file, but must guarantee that * vma_link() below can deny write-access if VM_DENYWRITE is set * and map writably if VM_SHARED is set. This usually means the * new file must not have been exposed to user-space, yet. */ vma->vm_file = get_file(file); error = mmap_file(file, vma); if (error) goto unmap_and_free_file_vma; /* Can addr have changed?? * * Answer: Yes, several device drivers can do it in their * f_op->mmap method. -DaveM * Bug: If addr is changed, prev, rb_link, rb_parent should * be updated for vma_link() */ WARN_ON_ONCE(addr != vma->vm_start); /* * Drivers should not permit writability when previously it was * disallowed. */ VM_WARN_ON_ONCE(vm_flags != vma->vm_flags && !(vm_flags & VM_MAYWRITE) && (vma->vm_flags & VM_MAYWRITE)); addr = vma->vm_start; /* If vm_flags changed after mmap_file(), we should try merge vma again * as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && prev)) { merge = vma_merge(mm, prev, vma->vm_start, vma->vm_end, vma->vm_flags, NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX); if (merge) { /* ->mmap() can change vma->vm_file and fput the original file. So * fput the vma->vm_file here or we would add an extra fput for file * and cause general protection fault ultimately. */ fput(vma->vm_file); vm_area_free(vma); vma = merge; /* Update vm_flags to pick up the change. */ vm_flags = vma->vm_flags; goto unmap_writable; } } vm_flags = vma->vm_flags; } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); if (error) goto free_vma; } else { vma_set_anonymous(vma); } #ifdef CONFIG_SPARC64 /* TODO: Fix SPARC ADI! */ WARN_ON_ONCE(!arch_validate_flags(vm_flags)); #endif vma_link(mm, vma, prev, rb_link, rb_parent); if (file) { unmap_writable: if (vm_flags & VM_DENYWRITE) allow_write_access(file); } file = vma->vm_file; out: perf_event_mmap(vma); vm_stat_account(mm, vm_flags, len >> PAGE_SHIFT); if (vm_flags & VM_LOCKED) { if ((vm_flags & VM_SPECIAL) || vma_is_dax(vma) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm)) vma->vm_flags &= VM_LOCKED_CLEAR_MASK; else mm->locked_vm += (len >> PAGE_SHIFT); } if (file) uprobe_mmap(vma); /* * New (or expanded) vma always get soft dirty status. * Otherwise user-space soft-dirty page tracker won't * be able to distinguish situation when vma area unmapped, * then new mapped in-place (which must be aimed as * a completely new data area). */ vma->vm_flags |= VM_SOFTDIRTY; vma_set_page_prot(vma); return addr; unmap_and_free_file_vma: vma->vm_file = NULL; fput(file); /* Undo any partial mapping done by a device driver. */ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); if (vm_flags & VM_DENYWRITE) allow_write_access(file); free_vma: vm_area_free(vma); unacct_error: if (charged) vm_unacct_memory(charged); return error; } static unsigned long unmapped_area(struct vm_unmapped_area_info *info) { /* * We implement the search by looking for an rbtree node that * immediately follows a suitable gap. That is, * - gap_start = vma->vm_prev->vm_end <= info->high_limit - length; * - gap_end = vma->vm_start >= info->low_limit + length; * - gap_end - gap_start >= length */ struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long length, low_limit, high_limit, gap_start, gap_end; /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask; if (length < info->length) return -ENOMEM; /* Adjust search limits by the desired length */ if (info->high_limit < length) return -ENOMEM; high_limit = info->high_limit - length; if (info->low_limit > high_limit) return -ENOMEM; low_limit = info->low_limit + length; /* Check if rbtree root looks promising */ if (RB_EMPTY_ROOT(&mm->mm_rb)) goto check_highest; vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb); if (vma->rb_subtree_gap < length) goto check_highest; while (true) { /* Visit left subtree if it looks promising */ gap_end = vm_start_gap(vma); if (gap_end >= low_limit && vma->vm_rb.rb_left) { struct vm_area_struct *left = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb); if (left->rb_subtree_gap >= length) { vma = left; continue; } } gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; check_current: /* Check if current node has a suitable gap */ if (gap_start > high_limit) return -ENOMEM; if (gap_end >= low_limit && gap_end > gap_start && gap_end - gap_start >= length) goto found; /* Visit right subtree if it looks promising */ if (vma->vm_rb.rb_right) { struct vm_area_struct *right = rb_entry(vma->vm_rb.rb_right, struct vm_area_struct, vm_rb); if (right->rb_subtree_gap >= length) { vma = right; continue; } } /* Go back up the rbtree to find next candidate node */ while (true) { struct rb_node *prev = &vma->vm_rb; if (!rb_parent(prev)) goto check_highest; vma = rb_entry(rb_parent(prev), struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_left) { gap_start = vm_end_gap(vma->vm_prev); gap_end = vm_start_gap(vma); goto check_current; } } } check_highest: /* Check highest gap, which does not precede any rbtree node */ gap_start = mm->highest_vm_end; gap_end = ULONG_MAX; /* Only for VM_BUG_ON below */ if (gap_start > high_limit) return -ENOMEM; found: /* We found a suitable gap. Clip it with the original low_limit. */ if (gap_start < info->low_limit) gap_start = info->low_limit; /* Adjust gap address to the desired alignment */ gap_start += (info->align_offset - gap_start) & info->align_mask; VM_BUG_ON(gap_start + info->length > info->high_limit); VM_BUG_ON(gap_start + info->length > gap_end); return gap_start; } static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long length, low_limit, high_limit, gap_start, gap_end; /* Adjust search length to account for worst case alignment overhead */ length = info->length + info->align_mask; if (length < info->length) return -ENOMEM; /* * Adjust search limits by the desired length. * See implementation comment at top of unmapped_area(). */ gap_end = info->high_limit; if (gap_end < length) return -ENOMEM; high_limit = gap_end - length; if (info->low_limit > high_limit) return -ENOMEM; low_limit = info->low_limit + length; /* Check highest gap, which does not precede any rbtree node */ gap_start = mm->highest_vm_end; if (gap_start <= high_limit) goto found_highest; /* Check if rbtree root looks promising */ if (RB_EMPTY_ROOT(&mm->mm_rb)) return -ENOMEM; vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb); if (vma->rb_subtree_gap < length) return -ENOMEM; while (true) { /* Visit right subtree if it looks promising */ gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; if (gap_start <= high_limit && vma->vm_rb.rb_right) { struct vm_area_struct *right = rb_entry(vma->vm_rb.rb_right, struct vm_area_struct, vm_rb); if (right->rb_subtree_gap >= length) { vma = right; continue; } } check_current: /* Check if current node has a suitable gap */ gap_end = vm_start_gap(vma); if (gap_end < low_limit) return -ENOMEM; if (gap_start <= high_limit && gap_end > gap_start && gap_end - gap_start >= length) goto found; /* Visit left subtree if it looks promising */ if (vma->vm_rb.rb_left) { struct vm_area_struct *left = rb_entry(vma->vm_rb.rb_left, struct vm_area_struct, vm_rb); if (left->rb_subtree_gap >= length) { vma = left; continue; } } /* Go back up the rbtree to find next candidate node */ while (true) { struct rb_node *prev = &vma->vm_rb; if (!rb_parent(prev)) return -ENOMEM; vma = rb_entry(rb_parent(prev), struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_right) { gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; goto check_current; } } } found: /* We found a suitable gap. Clip it with the original high_limit. */ if (gap_end > info->high_limit) gap_end = info->high_limit; found_highest: /* Compute highest gap address at the desired alignment */ gap_end -= info->length; gap_end -= (gap_end - info->align_offset) & info->align_mask; VM_BUG_ON(gap_end < info->low_limit); VM_BUG_ON(gap_end < gap_start); return gap_end; } /* * Search for an unmapped address range. * * We are looking for a range that: * - does not intersect with any VMA; * - is contained within the [low_limit, high_limit) interval; * - is at least the desired size. * - satisfies (begin_addr & align_mask) == (align_offset & align_mask) */ unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info) { unsigned long addr; if (info->flags & VM_UNMAPPED_AREA_TOPDOWN) addr = unmapped_area_topdown(info); else addr = unmapped_area(info); trace_vm_unmapped_area(addr, info); return addr; } /* Get an address range which is currently unmapped. * For shmat() with addr=0. * * Ugly calling convention alert: * Return value with the low bits set means error value, * ie * if (ret & ~PAGE_MASK) * error = ret; * * This function "knows" that -ENOMEM has the bits set. */ #ifndef HAVE_ARCH_UNMAPPED_AREA unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vm_unmapped_area_info info; const unsigned long mmap_end = arch_get_mmap_end(addr); if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.flags = 0; info.length = len; info.low_limit = mm->mmap_base; info.high_limit = mmap_end; info.align_mask = 0; info.align_offset = 0; return vm_unmapped_area(&info); } #endif /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): */ #ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct vm_area_struct *vma, *prev; struct mm_struct *mm = current->mm; struct vm_unmapped_area_info info; const unsigned long mmap_end = arch_get_mmap_end(addr); /* requested length too big for entire address space */ if (len > mmap_end - mmap_min_addr) return -ENOMEM; if (flags & MAP_FIXED) return addr; /* requesting a specific address */ if (addr) { addr = PAGE_ALIGN(addr); vma = find_vma_prev(mm, addr, &prev); if (mmap_end - len >= addr && addr >= mmap_min_addr && (!vma || addr + len <= vm_start_gap(vma)) && (!prev || addr >= vm_end_gap(prev))) return addr; } info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = max(PAGE_SIZE, mmap_min_addr); info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); info.align_mask = 0; info.align_offset = 0; addr = vm_unmapped_area(&info); /* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario * can happen with large stack limits and large mmap() * allocations. */ if (offset_in_page(addr)) { VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = TASK_UNMAPPED_BASE; info.high_limit = mmap_end; addr = vm_unmapped_area(&info); } return addr; } #endif unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); unsigned long error = arch_mmap_check(addr, len, flags); if (error) return error; /* Careful about overflows.. */ if (len > TASK_SIZE) return -ENOMEM; get_area = current->mm->get_unmapped_area; if (file) { if (file->f_op->get_unmapped_area) get_area = file->f_op->get_unmapped_area; } else if (flags & MAP_SHARED) { /* * mmap_region() will call shmem_zero_setup() to create a file, * so use shmem's get_unmapped_area in case it can be huge. * do_mmap() will clear pgoff, so match alignment. */ pgoff = 0; get_area = shmem_get_unmapped_area; } addr = get_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) return addr; if (addr > TASK_SIZE - len) return -ENOMEM; if (offset_in_page(addr)) return -EINVAL; error = security_mmap_addr(addr); return error ? error : addr; } EXPORT_SYMBOL(get_unmapped_area); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { struct rb_node *rb_node; struct vm_area_struct *vma; /* Check the cache first. */ vma = vmacache_find(mm, addr); if (likely(vma)) return vma; rb_node = mm->mm_rb.rb_node; while (rb_node) { struct vm_area_struct *tmp; tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb); if (tmp->vm_end > addr) { vma = tmp; if (tmp->vm_start <= addr) break; rb_node = rb_node->rb_left; } else rb_node = rb_node->rb_right; } if (vma) vmacache_update(addr, vma); return vma; } EXPORT_SYMBOL(find_vma); /* * Same as find_vma, but also return a pointer to the previous VMA in *pprev. */ struct vm_area_struct * find_vma_prev(struct mm_struct *mm, unsigned long addr, struct vm_area_struct **pprev) { struct vm_area_struct *vma; vma = find_vma(mm, addr); if (vma) { *pprev = vma->vm_prev; } else { struct rb_node *rb_node = rb_last(&mm->mm_rb); *pprev = rb_node ? rb_entry(rb_node, struct vm_area_struct, vm_rb) : NULL; } return vma; } /* * Verify that the stack growth is acceptable and * update accounting. This is shared with both the * grow-up and grow-down cases. */ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow) { struct mm_struct *mm = vma->vm_mm; unsigned long new_start; /* address space limit tests */ if (!may_expand_vm(mm, vma->vm_flags, grow)) return -ENOMEM; /* Stack limit test */ if (size > rlimit(RLIMIT_STACK)) return -ENOMEM; /* mlock limit tests */ if (vma->vm_flags & VM_LOCKED) { unsigned long locked; unsigned long limit; locked = mm->locked_vm + grow; limit = rlimit(RLIMIT_MEMLOCK); limit >>= PAGE_SHIFT; if (locked > limit && !capable(CAP_IPC_LOCK)) return -ENOMEM; } /* Check to ensure the stack will not grow into a hugetlb-only region */ new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start : vma->vm_end - size; if (is_hugepage_only_range(vma->vm_mm, new_start, size)) return -EFAULT; /* * Overcommit.. This must be the final test, as it will * update security statistics. */ if (security_vm_enough_memory_mm(mm, grow)) return -ENOMEM; return 0; } #if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64) /* * PA-RISC uses this for its stack; IA64 for its Register Backing Store. * vma is the last one with address > vma->vm_end. Have to extend vma. */ int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next; unsigned long gap_addr; int error = 0; if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; /* Guard against exceeding limits of the address space. */ address &= PAGE_MASK; if (address >= (TASK_SIZE & PAGE_MASK)) return -ENOMEM; address += PAGE_SIZE; /* Enforce stack_guard_gap */ gap_addr = address + stack_guard_gap; /* Guard against overflow */ if (gap_addr < address || gap_addr > TASK_SIZE) gap_addr = TASK_SIZE; next = vma->vm_next; if (next && next->vm_start < gap_addr && vma_is_accessible(next)) { if (!(next->vm_flags & VM_GROWSUP)) return -ENOMEM; /* Check that both stack segments have the same anon_vma? */ } /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_lock in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { unsigned long size, grow; size = address - vma->vm_start; grow = (address - vma->vm_end) >> PAGE_SHIFT; error = -ENOMEM; if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { /* * vma_gap_update() doesn't support concurrent * updates, but we only hold a shared mmap_lock * lock here, so we need to protect against * concurrent vma expansions. * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard * against concurrent vma expansions. */ spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_end = address; anon_vma_interval_tree_post_update_vma(vma); if (vma->vm_next) vma_gap_update(vma->vm_next); else mm->highest_vm_end = vm_end_gap(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; } #endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */ /* * vma is the first one with address < vma->vm_start. Have to extend vma. */ int expand_downwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *prev; int error = 0; address &= PAGE_MASK; if (address < mmap_min_addr) return -EPERM; /* Enforce stack_guard_gap */ prev = vma->vm_prev; /* Check that both stack segments have the same anon_vma? */ if (prev && !(prev->vm_flags & VM_GROWSDOWN) && vma_is_accessible(prev)) { if (address - prev->vm_end < stack_guard_gap) return -ENOMEM; } /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_lock in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { unsigned long size, grow; size = vma->vm_end - address; grow = (vma->vm_start - address) >> PAGE_SHIFT; error = -ENOMEM; if (grow <= vma->vm_pgoff) { error = acct_stack_growth(vma, size, grow); if (!error) { /* * vma_gap_update() doesn't support concurrent * updates, but we only hold a shared mmap_lock * lock here, so we need to protect against * concurrent vma expansions. * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard * against concurrent vma expansions. */ spin_lock(&mm->page_table_lock); if (vma->vm_flags & VM_LOCKED) mm->locked_vm += grow; vm_stat_account(mm, vma->vm_flags, grow); anon_vma_interval_tree_pre_update_vma(vma); vma->vm_start = address; vma->vm_pgoff -= grow; anon_vma_interval_tree_post_update_vma(vma); vma_gap_update(vma); spin_unlock(&mm->page_table_lock); perf_event_mmap(vma); } } } anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; } /* enforced gap between the expanding stack and other mappings. */ unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT; static int __init cmdline_parse_stack_guard_gap(char *p) { unsigned long val; char *endptr; val = simple_strtoul(p, &endptr, 10); if (!*endptr) stack_guard_gap = val << PAGE_SHIFT; return 1; } __setup("stack_guard_gap=", cmdline_parse_stack_guard_gap); #ifdef CONFIG_STACK_GROWSUP int expand_stack(struct vm_area_struct *vma, unsigned long address) { return expand_upwards(vma, address); } struct vm_area_struct * find_extend_vma(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma, *prev; addr &= PAGE_MASK; vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; /* don't alter vm_end if the coredump is running */ if (!prev || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); return prev; } #else int expand_stack(struct vm_area_struct *vma, unsigned long address) { return expand_downwards(vma, address); } struct vm_area_struct * find_extend_vma(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma; unsigned long start; addr &= PAGE_MASK; vma = find_vma(mm, addr); if (!vma) return NULL; if (vma->vm_start <= addr) return vma; if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; start = vma->vm_start; if (expand_stack(vma, addr)) return NULL; if (vma->vm_flags & VM_LOCKED) populate_vma_page_range(vma, addr, start, NULL); return vma; } #endif EXPORT_SYMBOL_GPL(find_extend_vma); /* * Ok - we have the memory areas we should free on the vma list, * so release them, and do the vma updates. * * Called with the mm semaphore held. */ static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma) { unsigned long nr_accounted = 0; /* Update high watermark before we lower total_vm */ update_hiwater_vm(mm); do { long nrpages = vma_pages(vma); if (vma->vm_flags & VM_ACCOUNT) nr_accounted += nrpages; vm_stat_account(mm, vma->vm_flags, -nrpages); vma = remove_vma(vma); } while (vma); vm_unacct_memory(nr_accounted); validate_mm(mm); } /* * Get rid of page table information in the indicated region. * * Called with the mm semaphore held. */ static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long start, unsigned long end) { struct vm_area_struct *next = vma_next(mm, prev); struct mmu_gather tlb; struct vm_area_struct *cur_vma; lru_add_drain(); tlb_gather_mmu(&tlb, mm, start, end); update_hiwater_rss(mm); unmap_vmas(&tlb, vma, start, end); /* * Ensure we have no stale TLB entries by the time this mapping is * removed from the rmap. * Note that we don't have to worry about nested flushes here because * we're holding the mm semaphore for removing the mapping - so any * concurrent flush in this region has to be coming through the rmap, * and we synchronize against that using the rmap lock. */ for (cur_vma = vma; cur_vma; cur_vma = cur_vma->vm_next) { if ((cur_vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) != 0) { tlb_flush_mmu(&tlb); break; } } free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, start, end); } /* * Create a list of vma's touched by the unmap, removing them from the mm's * vma list as we go.. */ static bool detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, unsigned long end) { struct vm_area_struct **insertion_point; struct vm_area_struct *tail_vma = NULL; insertion_point = (prev ? &prev->vm_next : &mm->mmap); vma->vm_prev = NULL; do { vma_rb_erase(vma, &mm->mm_rb); mm->map_count--; tail_vma = vma; vma = vma->vm_next; } while (vma && vma->vm_start < end); *insertion_point = vma; if (vma) { vma->vm_prev = prev; vma_gap_update(vma); } else mm->highest_vm_end = prev ? vm_end_gap(prev) : 0; tail_vma->vm_next = NULL; /* Kill the cache */ vmacache_invalidate(mm); /* * Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or * VM_GROWSUP VMA. Such VMAs can change their size under * down_read(mmap_lock) and collide with the VMA we are about to unmap. */ if (vma && (vma->vm_flags & VM_GROWSDOWN)) return false; if (prev && (prev->vm_flags & VM_GROWSUP)) return false; return true; } /* * __split_vma() bypasses sysctl_max_map_count checking. We use this where it * has already been checked or doesn't make sense to fail. */ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, int new_below) { struct vm_area_struct *new; int err; if (vma->vm_ops && vma->vm_ops->split) { err = vma->vm_ops->split(vma, addr); if (err) return err; } new = vm_area_dup(vma); if (!new) return -ENOMEM; if (new_below) new->vm_end = addr; else { new->vm_start = addr; new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT); } err = vma_dup_policy(vma, new); if (err) goto out_free_vma; err = anon_vma_clone(new, vma); if (err) goto out_free_mpol; if (new->vm_file) get_file(new->vm_file); if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); if (new_below) err = vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff + ((addr - new->vm_start) >> PAGE_SHIFT), new); else err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); /* Success. */ if (!err) return 0; /* Clean everything up if vma_adjust failed. */ vma_close(new); if (new->vm_file) fput(new->vm_file); unlink_anon_vmas(new); out_free_mpol: mpol_put(vma_policy(new)); out_free_vma: vm_area_free(new); return err; } /* * Split a vma into two pieces at address 'addr', a new vma is allocated * either for the first part or the tail. */ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, int new_below) { if (mm->map_count >= sysctl_max_map_count) return -ENOMEM; return __split_vma(mm, vma, addr, new_below); } /* Munmap is split into 2 main parts -- this part which finds * what needs doing, and the areas themselves, which do the * work. This now handles partial unmappings. * Jeremy Fitzhardinge <jeremy@goop.org> */ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool downgrade) { unsigned long end; struct vm_area_struct *vma, *prev, *last; if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE-start) return -EINVAL; len = PAGE_ALIGN(len); end = start + len; if (len == 0) return -EINVAL; /* * arch_unmap() might do unmaps itself. It must be called * and finish any rbtree manipulation before this code * runs and also starts to manipulate the rbtree. */ arch_unmap(mm, start, end); /* Find the first overlapping VMA */ vma = find_vma(mm, start); if (!vma) return 0; prev = vma->vm_prev; /* we have start < vma->vm_end */ /* if it doesn't overlap, we have nothing.. */ if (vma->vm_start >= end) return 0; /* * If we need to split any vma, do it now to save pain later. * * Note: mremap's move_vma VM_ACCOUNT handling assumes a partially * unmapped vm_area_struct will remain in use: so lower split_vma * places tmp vma above, and higher split_vma places tmp vma below. */ if (start > vma->vm_start) { int error; /* * Make sure that map_count on return from munmap() will * not exceed its limit; but let map_count go just above * its limit temporarily, to help free resources as expected. */ if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count) return -ENOMEM; error = __split_vma(mm, vma, start, 0); if (error) return error; prev = vma; } /* Does it split the last one? */ last = find_vma(mm, end); if (last && end > last->vm_start) { int error = __split_vma(mm, last, end, 1); if (error) return error; } vma = vma_next(mm, prev); if (unlikely(uf)) { /* * If userfaultfd_unmap_prep returns an error the vmas * will remain splitted, but userland will get a * highly unexpected error anyway. This is no * different than the case where the first of the two * __split_vma fails, but we don't undo the first * split, despite we could. This is unlikely enough * failure that it's not worth optimizing it for. */ int error = userfaultfd_unmap_prep(vma, start, end, uf); if (error) return error; } /* * unlock any mlock()ed ranges before detaching vmas */ if (mm->locked_vm) { struct vm_area_struct *tmp = vma; while (tmp && tmp->vm_start < end) { if (tmp->vm_flags & VM_LOCKED) { mm->locked_vm -= vma_pages(tmp); munlock_vma_pages_all(tmp); } tmp = tmp->vm_next; } } /* Detach vmas from rbtree */ if (!detach_vmas_to_be_unmapped(mm, vma, prev, end)) downgrade = false; if (downgrade) mmap_write_downgrade(mm); unmap_region(mm, vma, prev, start, end); /* Fix up all other VM information */ remove_vma_list(mm, vma); return downgrade ? 1 : 0; } int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf) { return __do_munmap(mm, start, len, uf, false); } unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf) { unsigned long ret; bool writable_file_mapping = false; /* Allow architectures to sanity-check the vm_flags. */ if (!arch_validate_flags(vm_flags)) return -EINVAL; /* Map writable and ensure this isn't a sealed memfd. */ if (file && is_shared_maywrite(vm_flags)) { int error = mapping_map_writable(file->f_mapping); if (error) return error; writable_file_mapping = true; } ret = __mmap_region(file, addr, len, vm_flags, pgoff, uf); /* Clear our write mapping regardless of error. */ if (writable_file_mapping) mapping_unmap_writable(file->f_mapping); validate_mm(current->mm); return ret; } static int __vm_munmap(unsigned long start, size_t len, bool downgrade) { int ret; struct mm_struct *mm = current->mm; LIST_HEAD(uf); if (mmap_write_lock_killable(mm)) return -EINTR; ret = __do_munmap(mm, start, len, &uf, downgrade); /* * Returning 1 indicates mmap_lock is downgraded. * But 1 is not legal return value of vm_munmap() and munmap(), reset * it to 0 before return. */ if (ret == 1) { mmap_read_unlock(mm); ret = 0; } else mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); return ret; } int vm_munmap(unsigned long start, size_t len) { return __vm_munmap(start, len, false); } EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { addr = untagged_addr(addr); profile_munmap(addr); return __vm_munmap(addr, len, true); } /* * Emulation of deprecated remap_file_pages() syscall. */ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long populate = 0; unsigned long ret = -EINVAL; struct file *file; pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. See Documentation/vm/remap_file_pages.rst.\n", current->comm, current->pid); if (prot) return ret; start = start & PAGE_MASK; size = size & PAGE_MASK; if (start + size <= start) return ret; /* Does pgoff wrap? */ if (pgoff + (size >> PAGE_SHIFT) < pgoff) return ret; if (mmap_write_lock_killable(mm)) return -EINTR; vma = find_vma(mm, start); if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; if (start < vma->vm_start) goto out; if (start + size > vma->vm_end) { struct vm_area_struct *next; for (next = vma->vm_next; next; next = next->vm_next) { /* hole between vmas ? */ if (next->vm_start != next->vm_prev->vm_end) goto out; if (next->vm_file != vma->vm_file) goto out; if (next->vm_flags != vma->vm_flags) goto out; if (start + size <= next->vm_end) break; } if (!next) goto out; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) { struct vm_area_struct *tmp; flags |= MAP_LOCKED; /* drop PG_Mlocked flag for over-mapped range */ for (tmp = vma; tmp->vm_start >= start + size; tmp = tmp->vm_next) { /* * Split pmd and munlock page on the border * of the range. */ vma_adjust_trans_huge(tmp, start, start + size, 0); munlock_vma_pages_range(tmp, max(tmp->vm_start, start), min(tmp->vm_end, start + size)); } } file = get_file(vma->vm_file); ret = do_mmap(vma->vm_file, start, size, prot, flags, pgoff, &populate, NULL); fput(file); out: mmap_write_unlock(mm); if (populate) mm_populate(ret, populate); if (!IS_ERR_VALUE(ret)) ret = 0; return ret; } /* * this is really a simplified "do_mmap". it only handles * anonymous maps. eventually we may be able to do some * brk-specific accounting here. */ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long flags, struct list_head *uf) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct rb_node **rb_link, *rb_parent; pgoff_t pgoff = addr >> PAGE_SHIFT; int error; unsigned long mapped_addr; /* Until we need other flags, refuse anything except VM_EXEC. */ if ((flags & (~VM_EXEC)) != 0) return -EINVAL; flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); if (IS_ERR_VALUE(mapped_addr)) return mapped_addr; error = mlock_future_check(mm, mm->def_flags, len); if (error) return error; /* Clear old maps, set up prev, rb_link, rb_parent, and uf */ if (munmap_vma_range(mm, addr, len, &prev, &rb_link, &rb_parent, uf)) return -ENOMEM; /* Check against address space limits *after* clearing old maps... */ if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT)) return -ENOMEM; if (mm->map_count > sysctl_max_map_count) return -ENOMEM; if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) return -ENOMEM; /* Can we just expand an old private anonymous mapping? */ vma = vma_merge(mm, prev, addr, addr + len, flags, NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX); if (vma) goto out; /* * create a vma struct for an anonymous mapping */ vma = vm_area_alloc(mm); if (!vma) { vm_unacct_memory(len >> PAGE_SHIFT); return -ENOMEM; } vma_set_anonymous(vma); vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = pgoff; vma->vm_flags = flags; vma->vm_page_prot = vm_get_page_prot(flags); vma_link(mm, vma, prev, rb_link, rb_parent); out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; mm->data_vm += len >> PAGE_SHIFT; if (flags & VM_LOCKED) mm->locked_vm += (len >> PAGE_SHIFT); vma->vm_flags |= VM_SOFTDIRTY; return 0; } int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) { struct mm_struct *mm = current->mm; unsigned long len; int ret; bool populate; LIST_HEAD(uf); len = PAGE_ALIGN(request); if (len < request) return -ENOMEM; if (!len) return 0; if (mmap_write_lock_killable(mm)) return -EINTR; ret = do_brk_flags(addr, len, flags, &uf); populate = ((mm->def_flags & VM_LOCKED) != 0); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate && !ret) mm_populate(addr, len); return ret; } EXPORT_SYMBOL(vm_brk_flags); int vm_brk(unsigned long addr, unsigned long len) { return vm_brk_flags(addr, len, 0); } EXPORT_SYMBOL(vm_brk); /* Release all mmaps. */ void exit_mmap(struct mm_struct *mm) { struct mmu_gather tlb; struct vm_area_struct *vma; unsigned long nr_accounted = 0; /* mm's last user has gone, and its about to be pulled down */ mmu_notifier_release(mm); if (unlikely(mm_is_oom_victim(mm))) { /* * Manually reap the mm to free as much memory as possible. * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard * this mm from further consideration. Taking mm->mmap_lock for * write after setting MMF_OOM_SKIP will guarantee that the oom * reaper will not run on this mm again after mmap_lock is * dropped. * * Nothing can be holding mm->mmap_lock here and the above call * to mmu_notifier_release(mm) ensures mmu notifier callbacks in * __oom_reap_task_mm() will not block. * * This needs to be done before calling munlock_vma_pages_all(), * which clears VM_LOCKED, otherwise the oom reaper cannot * reliably test it. */ (void)__oom_reap_task_mm(mm); set_bit(MMF_OOM_SKIP, &mm->flags); mmap_write_lock(mm); mmap_write_unlock(mm); } if (mm->locked_vm) { vma = mm->mmap; while (vma) { if (vma->vm_flags & VM_LOCKED) munlock_vma_pages_all(vma); vma = vma->vm_next; } } arch_exit_mmap(mm); vma = mm->mmap; if (!vma) /* Can happen if dup_mmap() received an OOM */ return; lru_add_drain(); flush_cache_mm(mm); tlb_gather_mmu(&tlb, mm, 0, -1); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use -1 here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, vma, 0, -1); free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, 0, -1); /* * Walk the list again, actually closing and freeing it, * with preemption enabled, without holding any MM locks. */ while (vma) { if (vma->vm_flags & VM_ACCOUNT) nr_accounted += vma_pages(vma); vma = remove_vma(vma); cond_resched(); } vm_unacct_memory(nr_accounted); } /* Insert vm structure into process list sorted by address * and into the inode's i_mmap tree. If vm_file is non-NULL * then i_mmap_rwsem is taken here. */ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { struct vm_area_struct *prev; struct rb_node **rb_link, *rb_parent; if (find_vma_links(mm, vma->vm_start, vma->vm_end, &prev, &rb_link, &rb_parent)) return -ENOMEM; if ((vma->vm_flags & VM_ACCOUNT) && security_vm_enough_memory_mm(mm, vma_pages(vma))) return -ENOMEM; /* * The vm_pgoff of a purely anonymous vma should be irrelevant * until its first write fault, when page's anon_vma and index * are set. But now set the vm_pgoff it will almost certainly * end up with (unless mremap moves it elsewhere before that * first wfault), so /proc/pid/maps tells a consistent story. * * By setting it to reflect the virtual start address of the * vma, merges and splits can happen in a seamless way, just * using the existing file pgoff checks and manipulations. * Similarly in do_mmap and in do_brk_flags. */ if (vma_is_anonymous(vma)) { BUG_ON(vma->anon_vma); vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT; } vma_link(mm, vma, prev, rb_link, rb_parent); return 0; } /* * Copy the vma structure to a new location in the same mm, * prior to moving page table entries, to effect an mremap move. */ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, unsigned long addr, unsigned long len, pgoff_t pgoff, bool *need_rmap_locks) { struct vm_area_struct *vma = *vmap; unsigned long vma_start = vma->vm_start; struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *new_vma, *prev; struct rb_node **rb_link, *rb_parent; bool faulted_in_anon_vma = true; /* * If anonymous vma has not yet been faulted, update new pgoff * to match new location, to increase its chance of merging. */ if (unlikely(vma_is_anonymous(vma) && !vma->anon_vma)) { pgoff = addr >> PAGE_SHIFT; faulted_in_anon_vma = false; } if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) return NULL; /* should never get here */ new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx); if (new_vma) { /* * Source vma may have been merged into new_vma */ if (unlikely(vma_start >= new_vma->vm_start && vma_start < new_vma->vm_end)) { /* * The only way we can get a vma_merge with * self during an mremap is if the vma hasn't * been faulted in yet and we were allowed to * reset the dst vma->vm_pgoff to the * destination address of the mremap to allow * the merge to happen. mremap must change the * vm_pgoff linearity between src and dst vmas * (in turn preventing a vma_merge) to be * safe. It is only safe to keep the vm_pgoff * linear if there are no pages mapped yet. */ VM_BUG_ON_VMA(faulted_in_anon_vma, new_vma); *vmap = vma = new_vma; } *need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff); } else { new_vma = vm_area_dup(vma); if (!new_vma) goto out; new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; if (vma_dup_policy(vma, new_vma)) goto out_free_vma; if (anon_vma_clone(new_vma, vma)) goto out_free_mempol; if (new_vma->vm_file) get_file(new_vma->vm_file); if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); vma_link(mm, new_vma, prev, rb_link, rb_parent); *need_rmap_locks = false; } return new_vma; out_free_mempol: mpol_put(vma_policy(new_vma)); out_free_vma: vm_area_free(new_vma); out: return NULL; } /* * Return true if the calling process may expand its vm space by the passed * number of pages */ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) { if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) return false; if (is_data_mapping(flags) && mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { /* Workaround for Valgrind */ if (rlimit(RLIMIT_DATA) == 0 && mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT) return true; pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits%s.\n", current->comm, current->pid, (mm->data_vm + npages) << PAGE_SHIFT, rlimit(RLIMIT_DATA), ignore_rlimit_data ? "" : " or use boot option ignore_rlimit_data"); if (!ignore_rlimit_data) return false; } return true; } void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) { mm->total_vm += npages; if (is_exec_mapping(flags)) mm->exec_vm += npages; else if (is_stack_mapping(flags)) mm->stack_vm += npages; else if (is_data_mapping(flags)) mm->data_vm += npages; } static vm_fault_t special_mapping_fault(struct vm_fault *vmf); /* * Having a close hook prevents vma merging regardless of flags. */ static void special_mapping_close(struct vm_area_struct *vma) { } static const char *special_mapping_name(struct vm_area_struct *vma) { return ((struct vm_special_mapping *)vma->vm_private_data)->name; } static int special_mapping_mremap(struct vm_area_struct *new_vma) { struct vm_special_mapping *sm = new_vma->vm_private_data; if (WARN_ON_ONCE(current->mm != new_vma->vm_mm)) return -EFAULT; if (sm->mremap) return sm->mremap(sm, new_vma); return 0; } static const struct vm_operations_struct special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, .mremap = special_mapping_mremap, .name = special_mapping_name, /* vDSO code relies that VVAR can't be accessed remotely */ .access = NULL, }; static const struct vm_operations_struct legacy_special_mapping_vmops = { .close = special_mapping_close, .fault = special_mapping_fault, }; static vm_fault_t special_mapping_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pgoff_t pgoff; struct page **pages; if (vma->vm_ops == &legacy_special_mapping_vmops) { pages = vma->vm_private_data; } else { struct vm_special_mapping *sm = vma->vm_private_data; if (sm->fault) return sm->fault(sm, vmf->vma, vmf); pages = sm->pages; } for (pgoff = vmf->pgoff; pgoff && *pages; ++pages) pgoff--; if (*pages) { struct page *page = *pages; get_page(page); vmf->page = page; return 0; } return VM_FAULT_SIGBUS; } static struct vm_area_struct *__install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, void *priv, const struct vm_operations_struct *ops) { int ret; struct vm_area_struct *vma; vma = vm_area_alloc(mm); if (unlikely(vma == NULL)) return ERR_PTR(-ENOMEM); vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND | VM_SOFTDIRTY; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); vma->vm_ops = ops; vma->vm_private_data = priv; ret = insert_vm_struct(mm, vma); if (ret) goto out; vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT); perf_event_mmap(vma); return vma; out: vm_area_free(vma); return ERR_PTR(ret); } bool vma_is_special_mapping(const struct vm_area_struct *vma, const struct vm_special_mapping *sm) { return vma->vm_private_data == sm && (vma->vm_ops == &special_mapping_vmops || vma->vm_ops == &legacy_special_mapping_vmops); } /* * Called with mm->mmap_lock held for writing. * Insert a new vma covering the given region, with the given flags. * Its pages are supplied by the given array of struct page *. * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated. * The region past the last page supplied will always produce SIGBUS. * The array pointer and the pages it points to are assumed to stay alive * for as long as this mapping might exist. */ struct vm_area_struct *_install_special_mapping( struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, const struct vm_special_mapping *spec) { return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec, &special_mapping_vmops); } int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long vm_flags, struct page **pages) { struct vm_area_struct *vma = __install_special_mapping( mm, addr, len, vm_flags, (void *)pages, &legacy_special_mapping_vmops); return PTR_ERR_OR_ZERO(vma); } static DEFINE_MUTEX(mm_all_locks_mutex); static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma) { if (!test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change from under us * because we hold the mm_all_locks_mutex. */ down_write_nest_lock(&anon_vma->root->rwsem, &mm->mmap_lock); /* * We can safely modify head.next after taking the * anon_vma->root->rwsem. If some other vma in this mm shares * the same anon_vma we won't take it again. * * No need of atomic instructions here, head.next * can't change from under us thanks to the * anon_vma->root->rwsem. */ if (__test_and_set_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); } } static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) { if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change from under us because * we hold the mm_all_locks_mutex. * * Operations on ->flags have to be atomic because * even if AS_MM_ALL_LOCKS is stable thanks to the * mm_all_locks_mutex, there may be other cpus * changing other bitflags in parallel to us. */ if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_lock); } } /* * This operation locks against the VM for all pte/vma/mm related * operations that could ever happen on a certain mm. This includes * vmtruncate, try_to_unmap, and all page faults. * * The caller must take the mmap_lock in write mode before calling * mm_take_all_locks(). The caller isn't allowed to release the * mmap_lock until mm_drop_all_locks() returns. * * mmap_lock in write mode is required in order to block all operations * that could modify pagetables and free pages without need of * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row * or it would deadlock. * * The LSB in anon_vma->rb_root.rb_node and the AS_MM_ALL_LOCKS bitflag in * mapping->flags avoid to take the same lock twice, if more than one * vma in this mm is backed by the same anon_vma or address_space. * * We take locks in following order, accordingly to comment at beginning * of mm/rmap.c: * - all hugetlbfs_i_mmap_rwsem_key locks (aka mapping->i_mmap_rwsem for * hugetlb mapping); * - all i_mmap_rwsem locks; * - all anon_vma->rwseml * * We can take all locks within these types randomly because the VM code * doesn't nest them and we protected from parallel mm_take_all_locks() by * mm_all_locks_mutex. * * mm_take_all_locks() and mm_drop_all_locks are expensive operations * that may have to take thousand of locks. * * mm_take_all_locks() can fail if it's interrupted by signals. */ int mm_take_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; BUG_ON(mmap_read_trylock(mm)); mutex_lock(&mm_all_locks_mutex); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } for (vma = mm->mmap; vma; vma = vma->vm_next) { if (signal_pending(current)) goto out_unlock; if (vma->vm_file && vma->vm_file->f_mapping && !is_vm_hugetlb_page(vma)) vm_lock_mapping(mm, vma->vm_file->f_mapping); } for (vma = mm->mmap; vma; vma = vma->vm_next) { if (signal_pending(current)) goto out_unlock; if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_lock_anon_vma(mm, avc->anon_vma); } return 0; out_unlock: mm_drop_all_locks(mm); return -EINTR; } static void vm_unlock_anon_vma(struct anon_vma *anon_vma) { if (test_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) { /* * The LSB of head.next can't change to 0 from under * us because we hold the mm_all_locks_mutex. * * We must however clear the bitflag before unlocking * the vma so the users using the anon_vma->rb_root will * never see our bitflag. * * No need of atomic instructions here, head.next * can't change from under us until we release the * anon_vma->root->rwsem. */ if (!__test_and_clear_bit(0, (unsigned long *) &anon_vma->root->rb_root.rb_root.rb_node)) BUG(); anon_vma_unlock_write(anon_vma); } } static void vm_unlock_mapping(struct address_space *mapping) { if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) { /* * AS_MM_ALL_LOCKS can't change to 0 from under us * because we hold the mm_all_locks_mutex. */ i_mmap_unlock_write(mapping); if (!test_and_clear_bit(AS_MM_ALL_LOCKS, &mapping->flags)) BUG(); } } /* * The mmap_lock cannot be released by the caller until * mm_drop_all_locks() returns. */ void mm_drop_all_locks(struct mm_struct *mm) { struct vm_area_struct *vma; struct anon_vma_chain *avc; BUG_ON(mmap_read_trylock(mm)); BUG_ON(!mutex_is_locked(&mm_all_locks_mutex)); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma) list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) vm_unlock_anon_vma(avc->anon_vma); if (vma->vm_file && vma->vm_file->f_mapping) vm_unlock_mapping(vma->vm_file->f_mapping); } mutex_unlock(&mm_all_locks_mutex); } /* * initialise the percpu counter for VM */ void __init mmap_init(void) { int ret; ret = percpu_counter_init(&vm_committed_as, 0, GFP_KERNEL); VM_BUG_ON(ret); } /* * Initialise sysctl_user_reserve_kbytes. * * This is intended to prevent a user from starting a single memory hogging * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER * mode. * * The default value is min(3% of free memory, 128MB) * 128MB is enough to recover with sshd/login, bash, and top/kill. */ static int init_user_reserve(void) { unsigned long free_kbytes; free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); return 0; } subsys_initcall(init_user_reserve); /* * Initialise sysctl_admin_reserve_kbytes. * * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin * to log in and kill a memory hogging process. * * Systems with more than 256MB will reserve 8MB, enough to recover * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will * only reserve 3% of free pages by default. */ static int init_admin_reserve(void) { unsigned long free_kbytes; free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); return 0; } subsys_initcall(init_admin_reserve); /* * Reinititalise user and admin reserves if memory is added or removed. * * The default user reserve max is 128MB, and the default max for the * admin reserve is 8MB. These are usually, but not always, enough to * enable recovery from a memory hogging process using login/sshd, a shell, * and tools like top. It may make sense to increase or even disable the * reserve depending on the existence of swap or variations in the recovery * tools. So, the admin may have changed them. * * If memory is added and the reserves have been eliminated or increased above * the default max, then we'll trust the admin. * * If memory is removed and there isn't enough free memory, then we * need to reset the reserves. * * Otherwise keep the reserve set by the admin. */ static int reserve_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) { unsigned long tmp, free_kbytes; switch (action) { case MEM_ONLINE: /* Default max is 128MB. Leave alone if modified by operator. */ tmp = sysctl_user_reserve_kbytes; if (0 < tmp && tmp < (1UL << 17)) init_user_reserve(); /* Default max is 8MB. Leave alone if modified by operator. */ tmp = sysctl_admin_reserve_kbytes; if (0 < tmp && tmp < (1UL << 13)) init_admin_reserve(); break; case MEM_OFFLINE: free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); if (sysctl_user_reserve_kbytes > free_kbytes) { init_user_reserve(); pr_info("vm.user_reserve_kbytes reset to %lu\n", sysctl_user_reserve_kbytes); } if (sysctl_admin_reserve_kbytes > free_kbytes) { init_admin_reserve(); pr_info("vm.admin_reserve_kbytes reset to %lu\n", sysctl_admin_reserve_kbytes); } break; default: break; } return NOTIFY_OK; } static struct notifier_block reserve_mem_nb = { .notifier_call = reserve_mem_notifier, }; static int __meminit init_reserve_notifier(void) { if (register_hotmemory_notifier(&reserve_mem_nb)) pr_err("Failed registering memory add/remove notifier for admin reserve\n"); return 0; } subsys_initcall(init_reserve_notifier); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/truncate.c - code for taking down pages from address_spaces * * Copyright (C) 2002, Linus Torvalds * * 10Sep2002 Andrew Morton * Initial version. */ #include <linux/kernel.h> #include <linux/backing-dev.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/pagevec.h> #include <linux/task_io_accounting_ops.h> #include <linux/buffer_head.h> /* grr. try_to_release_page, do_invalidatepage */ #include <linux/shmem_fs.h> #include <linux/cleancache.h> #include <linux/rmap.h> #include "internal.h" /* * Regular page slots are stabilized by the page lock even without the tree * itself locked. These unlocked entries need verification under the tree * lock. */ static inline void __clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { XA_STATE(xas, &mapping->i_pages, index); xas_set_update(&xas, workingset_update_node); if (xas_load(&xas) != entry) return; xas_store(&xas, NULL); mapping->nrexceptional--; } static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { xa_lock_irq(&mapping->i_pages); __clear_shadow_entry(mapping, index, entry); xa_unlock_irq(&mapping->i_pages); } /* * Unconditionally remove exceptional entries. Usually called from truncate * path. Note that the pagevec may be altered by this function by removing * exceptional entries similar to what pagevec_remove_exceptionals does. */ static void truncate_exceptional_pvec_entries(struct address_space *mapping, struct pagevec *pvec, pgoff_t *indices, pgoff_t end) { int i, j; bool dax, lock; /* Handled by shmem itself */ if (shmem_mapping(mapping)) return; for (j = 0; j < pagevec_count(pvec); j++) if (xa_is_value(pvec->pages[j])) break; if (j == pagevec_count(pvec)) return; dax = dax_mapping(mapping); lock = !dax && indices[j] < end; if (lock) xa_lock_irq(&mapping->i_pages); for (i = j; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; pgoff_t index = indices[i]; if (!xa_is_value(page)) { pvec->pages[j++] = page; continue; } if (index >= end) continue; if (unlikely(dax)) { dax_delete_mapping_entry(mapping, index); continue; } __clear_shadow_entry(mapping, index, page); } if (lock) xa_unlock_irq(&mapping->i_pages); pvec->nr = j; } /* * Invalidate exceptional entry if easily possible. This handles exceptional * entries for invalidate_inode_pages(). */ static int invalidate_exceptional_entry(struct address_space *mapping, pgoff_t index, void *entry) { /* Handled by shmem itself, or for DAX we do nothing. */ if (shmem_mapping(mapping) || dax_mapping(mapping)) return 1; clear_shadow_entry(mapping, index, entry); return 1; } /* * Invalidate exceptional entry if clean. This handles exceptional entries for * invalidate_inode_pages2() so for DAX it evicts only clean entries. */ static int invalidate_exceptional_entry2(struct address_space *mapping, pgoff_t index, void *entry) { /* Handled by shmem itself */ if (shmem_mapping(mapping)) return 1; if (dax_mapping(mapping)) return dax_invalidate_mapping_entry_sync(mapping, index); clear_shadow_entry(mapping, index, entry); return 1; } /** * do_invalidatepage - invalidate part or all of a page * @page: the page which is affected * @offset: start of the range to invalidate * @length: length of the range to invalidate * * do_invalidatepage() is called when all or part of the page has become * invalidated by a truncate operation. * * do_invalidatepage() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { void (*invalidatepage)(struct page *, unsigned int, unsigned int); invalidatepage = page->mapping->a_ops->invalidatepage; #ifdef CONFIG_BLOCK if (!invalidatepage) invalidatepage = block_invalidatepage; #endif if (invalidatepage) (*invalidatepage)(page, offset, length); } /* * If truncate cannot remove the fs-private metadata from the page, the page * becomes orphaned. It will be left on the LRU and may even be mapped into * user pagetables if we're racing with filemap_fault(). * * We need to bail out if page->mapping is no longer equal to the original * mapping. This happens a) when the VM reclaimed the page while we waited on * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ static void truncate_cleanup_page(struct page *page) { if (page_mapped(page)) unmap_mapping_page(page); if (page_has_private(page)) do_invalidatepage(page, 0, thp_size(page)); /* * Some filesystems seem to re-dirty the page even after * the VM has canceled the dirty bit (eg ext3 journaling). * Hence dirty accounting check is placed after invalidation. */ cancel_dirty_page(page); ClearPageMappedToDisk(page); } /* * This is for invalidate_mapping_pages(). That function can be called at * any time, and is not supposed to throw away dirty pages. But pages can * be marked dirty at any time too, so use remove_mapping which safely * discards clean, unused pages. * * Returns non-zero if the page was successfully invalidated. */ static int invalidate_complete_page(struct address_space *mapping, struct page *page) { int ret; if (page->mapping != mapping) return 0; if (page_has_private(page) && !try_to_release_page(page, 0)) return 0; ret = remove_mapping(mapping, page); return ret; } int truncate_inode_page(struct address_space *mapping, struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); if (page->mapping != mapping) return -EIO; truncate_cleanup_page(page); delete_from_page_cache(page); return 0; } /* * Used to get rid of pages on hardware memory corruption. */ int generic_error_remove_page(struct address_space *mapping, struct page *page) { if (!mapping) return -EINVAL; /* * Only punch for normal data pages for now. * Handling other types like directories would need more auditing. */ if (!S_ISREG(mapping->host->i_mode)) return -EIO; return truncate_inode_page(mapping, page); } EXPORT_SYMBOL(generic_error_remove_page); /* * Safely invalidate one page from its pagecache mapping. * It only drops clean, unused pages. The page must be locked. * * Returns 1 if the page is successfully invalidated, otherwise 0. */ int invalidate_inode_page(struct page *page) { struct address_space *mapping = page_mapping(page); if (!mapping) return 0; if (PageDirty(page) || PageWriteback(page)) return 0; if (page_mapped(page)) return 0; return invalidate_complete_page(mapping, page); } /** * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate * @lstart: offset from which to truncate * @lend: offset to which to truncate (inclusive) * * Truncate the page cache, removing the pages that are between * specified offsets (and zeroing out partial pages * if lstart or lend + 1 is not page aligned). * * Truncate takes two passes - the first pass is nonblocking. It will not * block on page locks and it will not block on writeback. The second pass * will wait. This is to prevent as much IO as possible in the affected region. * The first pass will remove most pages, so the search cost of the second pass * is low. * * We pass down the cache-hot hint to the page freeing code. Even if the * mapping is large, it is probably the case that the final pages are the most * recently touched, and freeing happens in ascending file offset order. * * Note that since ->invalidatepage() accepts range to invalidate * truncate_inode_pages_range is able to handle cases where lend + 1 is not * page aligned properly. */ void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, loff_t lend) { pgoff_t start; /* inclusive */ pgoff_t end; /* exclusive */ unsigned int partial_start; /* inclusive */ unsigned int partial_end; /* exclusive */ struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; if (mapping->nrpages == 0 && mapping->nrexceptional == 0) goto out; /* Offsets within partial pages */ partial_start = lstart & (PAGE_SIZE - 1); partial_end = (lend + 1) & (PAGE_SIZE - 1); /* * 'start' and 'end' always covers the range of pages to be fully * truncated. Partial pages are covered with 'partial_start' at the * start of the range and 'partial_end' at the end of the range. * Note that 'end' is exclusive while 'lend' is inclusive. */ start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; if (lend == -1) /* * lend == -1 indicates end-of-file so we have to set 'end' * to the highest possible pgoff_t and since the type is * unsigned we're using -1. */ end = -1; else end = (lend + 1) >> PAGE_SHIFT; pagevec_init(&pvec); index = start; while (index < end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { /* * Pagevec array has exceptional entries and we may also fail * to lock some pages. So we store pages that can be deleted * in a new pagevec. */ struct pagevec locked_pvec; pagevec_init(&locked_pvec); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (index >= end) break; if (xa_is_value(page)) continue; if (!trylock_page(page)) continue; WARN_ON(page_to_index(page) != index); if (PageWriteback(page)) { unlock_page(page); continue; } if (page->mapping != mapping) { unlock_page(page); continue; } pagevec_add(&locked_pvec, page); } for (i = 0; i < pagevec_count(&locked_pvec); i++) truncate_cleanup_page(locked_pvec.pages[i]); delete_from_page_cache_batch(mapping, &locked_pvec); for (i = 0; i < pagevec_count(&locked_pvec); i++) unlock_page(locked_pvec.pages[i]); truncate_exceptional_pvec_entries(mapping, &pvec, indices, end); pagevec_release(&pvec); cond_resched(); index++; } if (partial_start) { struct page *page = find_lock_page(mapping, start - 1); if (page) { unsigned int top = PAGE_SIZE; if (start > end) { /* Truncation within a single page */ top = partial_end; partial_end = 0; } wait_on_page_writeback(page); zero_user_segment(page, partial_start, top); cleancache_invalidate_page(mapping, page); if (page_has_private(page)) do_invalidatepage(page, partial_start, top - partial_start); unlock_page(page); put_page(page); } } if (partial_end) { struct page *page = find_lock_page(mapping, end); if (page) { wait_on_page_writeback(page); zero_user_segment(page, 0, partial_end); cleancache_invalidate_page(mapping, page); if (page_has_private(page)) do_invalidatepage(page, 0, partial_end); unlock_page(page); put_page(page); } } /* * If the truncation happened within a single page no pages * will be released, just zeroed, so we can bail out now. */ if (start >= end) goto out; index = start; for ( ; ; ) { cond_resched(); if (!pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { /* If all gone from start onwards, we're done */ if (index == start) break; /* Otherwise restart to make sure all gone */ index = start; continue; } if (index == start && indices[0] >= end) { /* All gone out of hole to be punched, we're done */ pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); break; } for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (index >= end) { /* Restart punch to make sure all gone */ index = start - 1; break; } if (xa_is_value(page)) continue; lock_page(page); WARN_ON(page_to_index(page) != index); wait_on_page_writeback(page); truncate_inode_page(mapping, page); unlock_page(page); } truncate_exceptional_pvec_entries(mapping, &pvec, indices, end); pagevec_release(&pvec); index++; } out: cleancache_invalidate_inode(mapping); } EXPORT_SYMBOL(truncate_inode_pages_range); /** * truncate_inode_pages - truncate *all* the pages from an offset * @mapping: mapping to truncate * @lstart: offset from which to truncate * * Called under (and serialised by) inode->i_mutex. * * Note: When this function returns, there can be a page in the process of * deletion (inside __delete_from_page_cache()) in the specified range. Thus * mapping->nrpages can be non-zero when this function returns even after * truncation of the whole mapping. */ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) { truncate_inode_pages_range(mapping, lstart, (loff_t)-1); } EXPORT_SYMBOL(truncate_inode_pages); /** * truncate_inode_pages_final - truncate *all* pages before inode dies * @mapping: mapping to truncate * * Called under (and serialized by) inode->i_mutex. * * Filesystems have to use this in the .evict_inode path to inform the * VM that this is the final truncate and the inode is going away. */ void truncate_inode_pages_final(struct address_space *mapping) { unsigned long nrexceptional; unsigned long nrpages; /* * Page reclaim can not participate in regular inode lifetime * management (can't call iput()) and thus can race with the * inode teardown. Tell it when the address space is exiting, * so that it does not install eviction information after the * final truncate has begun. */ mapping_set_exiting(mapping); /* * When reclaim installs eviction entries, it increases * nrexceptional first, then decreases nrpages. Make sure we see * this in the right order or we might miss an entry. */ nrpages = mapping->nrpages; smp_rmb(); nrexceptional = mapping->nrexceptional; if (nrpages || nrexceptional) { /* * As truncation uses a lockless tree lookup, cycle * the tree lock to make sure any ongoing tree * modification that does not see AS_EXITING is * completed before starting the final truncate. */ xa_lock_irq(&mapping->i_pages); xa_unlock_irq(&mapping->i_pages); } /* * Cleancache needs notification even if there are no pages or shadow * entries. */ truncate_inode_pages(mapping, 0); } EXPORT_SYMBOL(truncate_inode_pages_final); static unsigned long __invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_pagevec) { pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index = start; unsigned long ret; unsigned long count = 0; int i; pagevec_init(&pvec); while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, indices)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (index > end) break; if (xa_is_value(page)) { invalidate_exceptional_entry(mapping, index, page); continue; } if (!trylock_page(page)) continue; WARN_ON(page_to_index(page) != index); /* Middle of THP: skip */ if (PageTransTail(page)) { unlock_page(page); continue; } else if (PageTransHuge(page)) { index += HPAGE_PMD_NR - 1; i += HPAGE_PMD_NR - 1; /* * 'end' is in the middle of THP. Don't * invalidate the page as the part outside of * 'end' could be still useful. */ if (index > end) { unlock_page(page); continue; } /* Take a pin outside pagevec */ get_page(page); /* * Drop extra pins before trying to invalidate * the huge page. */ pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); } ret = invalidate_inode_page(page); unlock_page(page); /* * Invalidation is a hint that the page is no longer * of interest and try to speed up its reclaim. */ if (!ret) { deactivate_file_page(page); /* It is likely on the pagevec of a remote CPU */ if (nr_pagevec) (*nr_pagevec)++; } if (PageTransHuge(page)) put_page(page); count += ret; } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); cond_resched(); index++; } return count; } /** * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode * @mapping: the address_space which holds the pages to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * * This function only removes the unlocked pages, if you want to * remove all the pages of one inode, you must call truncate_inode_pages. * * invalidate_mapping_pages() will not block on IO activity. It will not * invalidate pages which are dirty, locked, under writeback or mapped into * pagetables. * * Return: the number of the pages that were invalidated */ unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { return __invalidate_mapping_pages(mapping, start, end, NULL); } EXPORT_SYMBOL(invalidate_mapping_pages); /** * This helper is similar with the above one, except that it accounts for pages * that are likely on a pagevec and count them in @nr_pagevec, which will used by * the caller. */ void invalidate_mapping_pagevec(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_pagevec) { __invalidate_mapping_pages(mapping, start, end, nr_pagevec); } /* * This is like invalidate_complete_page(), except it ignores the page's * refcount. We do this because invalidate_inode_pages2() needs stronger * invalidation guarantees, and cannot afford to leave pages behind because * shrink_page_list() has a temp ref on them, or because they're transiently * sitting in the lru_cache_add() pagevecs. */ static int invalidate_complete_page2(struct address_space *mapping, struct page *page) { unsigned long flags; if (page->mapping != mapping) return 0; if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return 0; xa_lock_irqsave(&mapping->i_pages, flags); if (PageDirty(page)) goto failed; BUG_ON(page_has_private(page)); __delete_from_page_cache(page, NULL); xa_unlock_irqrestore(&mapping->i_pages, flags); if (mapping->a_ops->freepage) mapping->a_ops->freepage(page); put_page(page); /* pagecache ref */ return 1; failed: xa_unlock_irqrestore(&mapping->i_pages, flags); return 0; } static int do_launder_page(struct address_space *mapping, struct page *page) { if (!PageDirty(page)) return 0; if (page->mapping != mapping || mapping->a_ops->launder_page == NULL) return 0; return mapping->a_ops->launder_page(page); } /** * invalidate_inode_pages2_range - remove range of pages from an address_space * @mapping: the address_space * @start: the page offset 'from' which to invalidate * @end: the page offset 'to' which to invalidate (inclusive) * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index; int i; int ret = 0; int ret2 = 0; int did_range_unmap = 0; if (mapping->nrpages == 0 && mapping->nrexceptional == 0) goto out; pagevec_init(&pvec); index = start; while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, indices)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (index > end) break; if (xa_is_value(page)) { if (!invalidate_exceptional_entry2(mapping, index, page)) ret = -EBUSY; continue; } if (!did_range_unmap && page_mapped(page)) { /* * If page is mapped, before taking its lock, * zap the rest of the file in one hit. */ unmap_mapping_pages(mapping, index, (1 + end - index), false); did_range_unmap = 1; } lock_page(page); WARN_ON(page_to_index(page) != index); if (page->mapping != mapping) { unlock_page(page); continue; } wait_on_page_writeback(page); if (page_mapped(page)) unmap_mapping_page(page); BUG_ON(page_mapped(page)); ret2 = do_launder_page(mapping, page); if (ret2 == 0) { if (!invalidate_complete_page2(mapping, page)) ret2 = -EBUSY; } if (ret2 < 0) ret = ret2; unlock_page(page); } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); cond_resched(); index++; } /* * For DAX we invalidate page tables after invalidating page cache. We * could invalidate page tables while invalidating each entry however * that would be expensive. And doing range unmapping before doesn't * work as we have no cheap way to find whether page cache entry didn't * get remapped later. */ if (dax_mapping(mapping)) { unmap_mapping_pages(mapping, start, end - start + 1, false); } out: cleancache_invalidate_inode(mapping); return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); /** * invalidate_inode_pages2 - remove all pages from an address_space * @mapping: the address_space * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2(struct address_space *mapping) { return invalidate_inode_pages2_range(mapping, 0, -1); } EXPORT_SYMBOL_GPL(invalidate_inode_pages2); /** * truncate_pagecache - unmap and remove pagecache that has been truncated * @inode: inode * @newsize: new file size * * inode's new i_size must already be written before truncate_pagecache * is called. * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache(struct inode *inode, loff_t newsize) { struct address_space *mapping = inode->i_mapping; loff_t holebegin = round_up(newsize, PAGE_SIZE); /* * unmap_mapping_range is called twice, first simply for * efficiency so that truncate_inode_pages does fewer * single-page unmaps. However after this first call, and * before truncate_inode_pages finishes, it is possible for * private pages to be COWed, which remain after * truncate_inode_pages finishes, hence the second * unmap_mapping_range call must be made for correctness. */ unmap_mapping_range(mapping, holebegin, 0, 1); truncate_inode_pages(mapping, newsize); unmap_mapping_range(mapping, holebegin, 0, 1); } EXPORT_SYMBOL(truncate_pagecache); /** * truncate_setsize - update inode and pagecache for a new file size * @inode: inode * @newsize: new file size * * truncate_setsize updates i_size and performs pagecache truncation (if * necessary) to @newsize. It will be typically be called from the filesystem's * setattr function when ATTR_SIZE is passed in. * * Must be called with a lock serializing truncates and writes (generally * i_mutex but e.g. xfs uses a different lock) and before all filesystem * specific block truncation has been performed. */ void truncate_setsize(struct inode *inode, loff_t newsize) { loff_t oldsize = inode->i_size; i_size_write(inode, newsize); if (newsize > oldsize) pagecache_isize_extended(inode, oldsize, newsize); truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); /** * pagecache_isize_extended - update pagecache after extension of i_size * @inode: inode for which i_size was extended * @from: original inode size * @to: new inode size * * Handle extension of inode size either caused by extending truncate or by * write starting after current i_size. We mark the page straddling current * i_size RO so that page_mkwrite() is called on the nearest write access to * the page. This way filesystem can be sure that page_mkwrite() is called on * the page before user writes to the page via mmap after the i_size has been * changed. * * The function must be called after i_size is updated so that page fault * coming after we unlock the page will already see the new i_size. * The function must be called while we still hold i_mutex - this not only * makes sure i_size is stable but also that userspace cannot observe new * i_size value before we are prepared to store mmap writes at new inode size. */ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) { int bsize = i_blocksize(inode); loff_t rounded_from; struct page *page; pgoff_t index; WARN_ON(to > inode->i_size); if (from >= to || bsize == PAGE_SIZE) return; /* Page straddling @from will not have any hole block created? */ rounded_from = round_up(from, bsize); if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1))) return; index = from >> PAGE_SHIFT; page = find_lock_page(inode->i_mapping, index); /* Page not cached? Nothing to do */ if (!page) return; /* * See clear_page_dirty_for_io() for details why set_page_dirty() * is needed. */ if (page_mkclean(page)) set_page_dirty(page); unlock_page(page); put_page(page); } EXPORT_SYMBOL(pagecache_isize_extended); /** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode * @lstart: offset of beginning of hole * @lend: offset of last byte of hole * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) { struct address_space *mapping = inode->i_mapping; loff_t unmap_start = round_up(lstart, PAGE_SIZE); loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1; /* * This rounding is currently just for example: unmap_mapping_range * expands its hole outwards, whereas we want it to contract the hole * inwards. However, existing callers of truncate_pagecache_range are * doing their own page rounding first. Note that unmap_mapping_range * allows holelen 0 for all, and we allow lend -1 for end of file. */ /* * Unlike in truncate_pagecache, unmap_mapping_range is called only * once (before truncating pagecache), and without "even_cows" flag: * hole-punching should not remove private COWed pages from the hole. */ if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); truncate_inode_pages_range(mapping, lstart, lend); } EXPORT_SYMBOL(truncate_pagecache_range); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H #include <linux/mmdebug.h> #include <linux/mmzone.h> #include <linux/stddef.h> #include <linux/linkage.h> #include <linux/topology.h> struct vm_area_struct; /* * In case of changes, please don't forget to update * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c */ /* Plain integer GFP bitmasks. Do not use this directly. */ #define ___GFP_DMA 0x01u #define ___GFP_HIGHMEM 0x02u #define ___GFP_DMA32 0x04u #define ___GFP_MOVABLE 0x08u #define ___GFP_RECLAIMABLE 0x10u #define ___GFP_HIGH 0x20u #define ___GFP_IO 0x40u #define ___GFP_FS 0x80u #define ___GFP_ZERO 0x100u #define ___GFP_ATOMIC 0x200u #define ___GFP_DIRECT_RECLAIM 0x400u #define ___GFP_KSWAPD_RECLAIM 0x800u #define ___GFP_WRITE 0x1000u #define ___GFP_NOWARN 0x2000u #define ___GFP_RETRY_MAYFAIL 0x4000u #define ___GFP_NOFAIL 0x8000u #define ___GFP_NORETRY 0x10000u #define ___GFP_MEMALLOC 0x20000u #define ___GFP_COMP 0x40000u #define ___GFP_NOMEMALLOC 0x80000u #define ___GFP_HARDWALL 0x100000u #define ___GFP_THISNODE 0x200000u #define ___GFP_ACCOUNT 0x400000u #ifdef CONFIG_LOCKDEP #define ___GFP_NOLOCKDEP 0x800000u #else #define ___GFP_NOLOCKDEP 0 #endif /* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* * Physical address zone modifiers (see linux/mmzone.h - low four bits) * * Do not put any conditional on these. If necessary modify the definitions * without the underscores and use them consistently. The definitions here may * be used in bit comparisons. */ #define __GFP_DMA ((__force gfp_t)___GFP_DMA) #define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM) #define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32) #define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */ #define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) /** * DOC: Page mobility and placement hints * * Page mobility and placement hints * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * These flags provide hints about how mobile the page is. Pages with similar * mobility are placed within the same pageblocks to minimise problems due * to external fragmentation. * * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be * moved by page migration during memory compaction or can be reclaimed. * * %__GFP_RECLAIMABLE is used for slab allocations that specify * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers. * * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible, * these pages will be spread between local zones to avoid all the dirty * pages being in one zone (fair zone allocation policy). * * %__GFP_HARDWALL enforces the cpuset memory allocation policy. * * %__GFP_THISNODE forces the allocation to be satisfied from the requested * node with no fallbacks or placement policy enforcements. * * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) #define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) /** * DOC: Watermark modifiers * * Watermark modifiers -- controls access to emergency reserves * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * %__GFP_HIGH indicates that the caller is high-priority and that granting * the request is necessary before the system can make forward progress. * For example, creating an IO context to clean pages. * * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is * high priority. Users are typically interrupt handlers. This may be * used in conjunction with %__GFP_HIGH * * %__GFP_MEMALLOC allows access to all memory. This should only be used when * the caller guarantees the allocation will allow more memory to be freed * very shortly e.g. process exiting or swapping. Users either should * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). * Users of this flag have to be extremely careful to not deplete the reserve * completely and implement a throttling mechanism which controls the * consumption of the reserve based on the amount of freed memory. * Usage of a pre-allocated pool (e.g. mempool) should be always considered * before using this flag. * * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. * This takes precedence over the %__GFP_MEMALLOC flag if both are set. */ #define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) #define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) #define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) #define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /** * DOC: Reclaim modifiers * * Reclaim modifiers * ~~~~~~~~~~~~~~~~~ * Please note that all the following flags are only applicable to sleepable * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them). * * %__GFP_IO can start physical IO. * * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the * allocator recursing into the filesystem which might already be holding * locks. * * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim. * This flag can be cleared to avoid unnecessary delays when a fallback * option is available. * * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when * the low watermark is reached and have it reclaim pages until the high * watermark is reached. A caller may wish to clear this flag when fallback * options are available and the reclaim is likely to disrupt the system. The * canonical example is THP allocation where a fallback is cheap but * reclaim/compaction may cause indirect stalls. * * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. * * The default allocator behavior depends on the request size. We have a concept * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER). * !costly allocations are too essential to fail so they are implicitly * non-failing by default (with some exceptions like OOM victims might fail so * the caller still has to check for failures) while costly requests try to be * not disruptive and back off even without invoking the OOM killer. * The following three modifiers might be used to override some of these * implicit rules * * %__GFP_NORETRY: The VM implementation will try only very lightweight * memory direct reclaim to get some memory under memory pressure (thus * it can sleep). It will avoid disruptive actions like OOM killer. The * caller must handle the failure which is quite likely to happen under * heavy memory pressure. The flag is suitable when failure can easily be * handled at small cost, such as reduced throughput * * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim * procedures that have previously failed if there is some indication * that progress has been made else where. It can wait for other * tasks to attempt high level approaches to freeing memory such as * compaction (which removes fragmentation) and page-out. * There is still a definite limit to the number of retries, but it is * a larger limit than with %__GFP_NORETRY. * Allocations with this flag may fail, but only when there is * genuinely little unused memory. While these allocations do not * directly trigger the OOM killer, their failure indicates that * the system is likely to need to use the OOM killer soon. The * caller must handle failure, but can reasonably do so by failing * a higher-level request, or completing it only in a much less * efficient manner. * If the allocation does fail, and the caller is in a position to * free some non-essential memory, doing so could benefit the system * as a whole. * * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller * cannot handle allocation failures. The allocation could block * indefinitely but will never return with failure. Testing for * failure is pointless. * New users should be evaluated carefully (and the flag should be * used only when there is no reasonable failure policy) but it is * definitely preferable to use the flag rather than opencode endless * loop around allocator. * Using this flag for costly allocations is _highly_ discouraged. */ #define __GFP_IO ((__force gfp_t)___GFP_IO) #define __GFP_FS ((__force gfp_t)___GFP_FS) #define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ #define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ #define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) #define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) #define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) #define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) /** * DOC: Action modifiers * * Action modifiers * ~~~~~~~~~~~~~~~~ * * %__GFP_NOWARN suppresses allocation failure reports. * * %__GFP_COMP address compound page metadata. * * %__GFP_ZERO returns a zeroed page on success. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ #define __GFP_BITS_SHIFT (23 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** * DOC: Useful GFP flag combinations * * Useful GFP flag combinations * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Useful GFP flag combinations that are commonly used. It is recommended * that subsystems start with one of these combinations and then set/clear * %__GFP_FOO flags as necessary. * * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower * watermark is applied to allow access to "atomic reserves". * The current implementation doesn't support NMI and few other strict * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT. * * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. * * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is * accounted to kmemcg. * * %GFP_NOWAIT is for kernel allocations that should not stall for direct * reclaim, start physical IO or use any filesystem callback. * * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages * that do not require the starting of any physical IO. * Please try to avoid using this flag directly and instead use * memalloc_noio_{save,restore} to mark the whole scope which cannot * perform any IO with a short explanation why. All allocation requests * will inherit GFP_NOIO implicitly. * * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. * Please try to avoid using this flag directly and instead use * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't * recurse into the FS layer with a short explanation why. All allocation * requests will inherit GFP_NOFS implicitly. * * %GFP_USER is for userspace allocations that also need to be directly * accessibly by the kernel or hardware. It is typically used by hardware * for buffers that are mapped to userspace (e.g. graphics) that hardware * still must DMA to. cpuset limits are enforced for these allocations. * * %GFP_DMA exists for historical reasons and should be avoided where possible. * The flags indicates that the caller requires that the lowest zone be * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but * it would require careful auditing as some users really require it and * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the * lowest zone as a type of emergency reserve. * * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit * address. * * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, * do not need to be directly accessible by the kernel but that cannot * move once in use. An example may be a hardware allocation that maps * data directly into userspace but has no addressing limitations. * * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not * need direct access to but can use kmap() when access is required. They * are expected to be movable via page reclaim or page migration. Typically, * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE. * * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They * are compound allocations that will generally fail quickly if memory is not * available and will not wake kswapd/kcompactd on failure. The _LIGHT * version does not attempt reclaim/compaction at all and is by default used * in page fault path, while the non-light is used by khugepaged. */ #define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) #define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) #define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) #define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) #define GFP_NOIO (__GFP_RECLAIM) #define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) #define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) #define GFP_DMA __GFP_DMA #define GFP_DMA32 __GFP_DMA32 #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) #define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE) #define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) #define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 static inline int gfp_migratetype(const gfp_t gfp_flags) { VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK); BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE); BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE); if (unlikely(page_group_by_mobility_disabled)) return MIGRATE_UNMOVABLE; /* Group based on mobility */ return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT; } #undef GFP_MOVABLE_MASK #undef GFP_MOVABLE_SHIFT static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } /** * gfpflags_normal_context - is gfp_flags a normal sleepable context? * @gfp_flags: gfp_flags to test * * Test whether @gfp_flags indicates that the allocation is from the * %current context and allowed to sleep. * * An allocation being allowed to block doesn't mean it owns the %current * context. When direct reclaim path tries to allocate memory, the * allocation context is nested inside whatever %current was doing at the * time of the original allocation. The nested allocation may be allowed * to block but modifying anything %current owns can corrupt the outer * context's expectations. * * %true result from this function indicates that the allocation context * can sleep and use anything that's associated with %current. */ static inline bool gfpflags_normal_context(const gfp_t gfp_flags) { return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) == __GFP_DIRECT_RECLAIM; } #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else #define OPT_ZONE_HIGHMEM ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA #define OPT_ZONE_DMA ZONE_DMA #else #define OPT_ZONE_DMA ZONE_NORMAL #endif #ifdef CONFIG_ZONE_DMA32 #define OPT_ZONE_DMA32 ZONE_DMA32 #else #define OPT_ZONE_DMA32 ZONE_NORMAL #endif /* * GFP_ZONE_TABLE is a word size bitstring that is used for looking up the * zone to use given the lowest 4 bits of gfp_t. Entries are GFP_ZONES_SHIFT * bits long and there are 16 of them to cover all possible combinations of * __GFP_DMA, __GFP_DMA32, __GFP_MOVABLE and __GFP_HIGHMEM. * * The zone fallback order is MOVABLE=>HIGHMEM=>NORMAL=>DMA32=>DMA. * But GFP_MOVABLE is not only a zone specifier but also an allocation * policy. Therefore __GFP_MOVABLE plus another zone selector is valid. * Only 1 bit of the lowest 3 bits (DMA,DMA32,HIGHMEM) can be set to "1". * * bit result * ================= * 0x0 => NORMAL * 0x1 => DMA or NORMAL * 0x2 => HIGHMEM or NORMAL * 0x3 => BAD (DMA+HIGHMEM) * 0x4 => DMA32 or NORMAL * 0x5 => BAD (DMA+DMA32) * 0x6 => BAD (HIGHMEM+DMA32) * 0x7 => BAD (HIGHMEM+DMA32+DMA) * 0x8 => NORMAL (MOVABLE+0) * 0x9 => DMA or NORMAL (MOVABLE+DMA) * 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too) * 0xb => BAD (MOVABLE+HIGHMEM+DMA) * 0xc => DMA32 or NORMAL (MOVABLE+DMA32) * 0xd => BAD (MOVABLE+DMA32+DMA) * 0xe => BAD (MOVABLE+DMA32+HIGHMEM) * 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA) * * GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms. */ #if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4 /* ZONE_DEVICE is not a valid GFP zone specifier */ #define GFP_ZONES_SHIFT 2 #else #define GFP_ZONES_SHIFT ZONES_SHIFT #endif #if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG #error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer #endif #define GFP_ZONE_TABLE ( \ (ZONE_NORMAL << 0 * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << ___GFP_DMA * GFP_ZONES_SHIFT) \ | (OPT_ZONE_HIGHMEM << ___GFP_HIGHMEM * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA32 << ___GFP_DMA32 * GFP_ZONES_SHIFT) \ | (ZONE_NORMAL << ___GFP_MOVABLE * GFP_ZONES_SHIFT) \ | (OPT_ZONE_DMA << (___GFP_MOVABLE | ___GFP_DMA) * GFP_ZONES_SHIFT) \ | (ZONE_MOVABLE << (___GFP_MOVABLE | ___GFP_HIGHMEM) * GFP_ZONES_SHIFT)\ | (OPT_ZONE_DMA32 << (___GFP_MOVABLE | ___GFP_DMA32) * GFP_ZONES_SHIFT)\ ) /* * GFP_ZONE_BAD is a bitmap for all combinations of __GFP_DMA, __GFP_DMA32 * __GFP_HIGHMEM and __GFP_MOVABLE that are not permitted. One flag per * entry starting with bit 0. Bit is set if the combination is not * allowed. */ #define GFP_ZONE_BAD ( \ 1 << (___GFP_DMA | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32) \ | 1 << (___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_DMA | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_HIGHMEM | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_HIGHMEM) \ | 1 << (___GFP_MOVABLE | ___GFP_DMA32 | ___GFP_DMA | ___GFP_HIGHMEM) \ ) static inline enum zone_type gfp_zone(gfp_t flags) { enum zone_type z; int bit = (__force int) (flags & GFP_ZONEMASK); z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) & ((1 << GFP_ZONES_SHIFT) - 1); VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1); return z; } /* * There is only one page-allocator function, and two main namespaces to * it. The alloc_page*() variants return 'struct page *' and as such * can allocate highmem pages, the *get*page*() variants return * virtual kernel addresses to the allocated page(s). */ static inline int gfp_zonelist(gfp_t flags) { #ifdef CONFIG_NUMA if (unlikely(flags & __GFP_THISNODE)) return ZONELIST_NOFALLBACK; #endif return ZONELIST_FALLBACK; } /* * We get the zone list from the current node and the gfp_mask. * This zone list contains a maximum of MAXNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * * For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets * optimized to &contig_page_data at compile-time. */ static inline struct zonelist *node_zonelist(int nid, gfp_t flags) { return NODE_DATA(nid)->node_zonelists + gfp_zonelist(flags); } #ifndef HAVE_ARCH_FREE_PAGE static inline void arch_free_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE static inline int arch_make_page_accessible(struct page *page) { return 0; } #endif struct page * __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, nodemask_t *nodemask); static inline struct page * __alloc_pages(gfp_t gfp_mask, unsigned int order, int preferred_nid) { return __alloc_pages_nodemask(gfp_mask, order, preferred_nid, NULL); } /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). */ static inline struct page * __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid)); return __alloc_pages(gfp_mask, order, nid); } /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); return __alloc_pages_node(nid, gfp_mask, order); } #ifdef CONFIG_NUMA extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order); static inline struct page * alloc_pages(gfp_t gfp_mask, unsigned int order) { return alloc_pages_current(gfp_mask, order); } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, int node, bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) #else static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { return alloc_pages_node(numa_node_id(), gfp_mask, order); } #define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); void *alloc_pages_exact(size_t size, gfp_t gfp_mask); void free_pages_exact(void *virt, size_t size); void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) #define __get_dma_pages(gfp_mask, order) \ __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); extern void free_unref_page(struct page *page); extern void free_unref_page_list(struct list_head *list); struct page_frag_cache; extern void __page_frag_cache_drain(struct page *page, unsigned int count); extern void *page_frag_alloc(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask); extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) void page_alloc_init(void); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); void page_alloc_init_late(void); /* * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what * GFP flags are used before interrupts are enabled. Once interrupts are * enabled, it is set to __GFP_BITS_MASK while the system is running. During * hibernation, it is used by PM to avoid I/O during memory allocation while * devices are suspended. */ extern gfp_t gfp_allowed_mask; /* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); extern void pm_restrict_gfp_mask(void); extern void pm_restore_gfp_mask(void); #ifdef CONFIG_PM_SLEEP extern bool pm_suspended_storage(void); #else static inline bool pm_suspended_storage(void) { return false; } #endif /* CONFIG_PM_SLEEP */ /* * Check if the gfp flags allow compaction - GFP_NOIO is a really * tricky context because the migration might require IO. */ static inline bool gfp_compaction_allowed(gfp_t gfp_mask) { return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO); } #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, int nid, nodemask_t *nodemask); #endif void free_contig_range(unsigned long pfn, unsigned int nr_pages); #ifdef CONFIG_CMA /* CMA stuff */ extern void init_cma_reserved_pageblock(struct page *page); #endif #endif /* __LINUX_GFP_H */ |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 | /* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel <riel@conectiva.com.br> * Released under the General Public License (GPL). * * Simple, low overhead reverse mapping scheme. * Please try to keep this thing as modular as possible. * * Provides methods for unmapping each kind of mapped page: * the anon methods track anonymous pages, and * the file methods track pages belonging to an inode. * * Original design by Rik van Riel <riel@conectiva.com.br> 2001 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004 * Contributions by Hugh Dickins 2003, 2004 */ /* * Lock ordering in mm: * * inode->i_mutex (while writing or truncating, not reading or faulting) * mm->mmap_lock * page->flags PG_locked (lock_page) * (see huegtlbfs below) * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share) * mapping->i_mmap_rwsem * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * anon_vma->rwsem * mm->page_table_lock or pte_lock * pgdat->lru_lock (in mark_page_accessed, isolate_lru_page) * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) * mem_cgroup_{begin,end}_page_stat (memcg->move_lock) * i_pages lock (widely used) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * i_pages lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mutex (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock * * * hugetlbfs PageHuge() pages take locks in this order: * mapping->i_mmap_rwsem * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * page->flags PG_locked (lock_page) */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> #include <asm/tlbflush.h> #include <trace/events/tlb.h> #include "internal.h" static struct kmem_cache *anon_vma_cachep; static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { struct anon_vma *anon_vma; anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); anon_vma->num_children = 0; anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. */ anon_vma->root = anon_vma; } return anon_vma; } static inline void anon_vma_free(struct anon_vma *anon_vma) { VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* * Synchronize against page_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by * down_read_trylock() from page_lock_anon_vma_read(). This orders: * * page_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() * * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } static void anon_vma_chain_link(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { avc->vma = vma; avc->anon_vma = anon_vma; list_add(&avc->same_vma, &vma->anon_vma_chain); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); } /** * __anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, which * is handled inline by anon_vma_prepare(). But if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in page_lock_anon_vma_read() * and that may actually touch the spinlock even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. * * This must be called with the mmap_lock held for reading. */ int __anon_vma_prepare(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *anon_vma, *allocated; struct anon_vma_chain *avc; might_sleep(); avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); return 0; out_enomem_free_avc: anon_vma_chain_free(avc); out_enomem: return -ENOMEM; } /* * This is a useful helper function for locking the anon_vma root as * we traverse the vma->anon_vma_chain, looping over anon_vma's that * have the same vma. * * Such anon_vma's should have the same root, so you'd expect to see * just a single mutex_lock for the whole traversal. */ static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma) { struct anon_vma *new_root = anon_vma->root; if (new_root != root) { if (WARN_ON_ONCE(root)) up_write(&root->rwsem); root = new_root; down_write(&root->rwsem); } return root; } static inline void unlock_anon_vma_root(struct anon_vma *root) { if (root) up_write(&root->rwsem); } /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. * * anon_vma_clone() is called by __vma_split(), __split_vma(), copy_vma() and * anon_vma_fork(). The first three want an exact copy of src, while the last * one, anon_vma_fork(), may try to reuse an existing anon_vma to prevent * endless growth of anon_vma. Since dst->anon_vma is set to NULL before call, * we can identify this case by checking (!dst->anon_vma && src->anon_vma). * * If (!dst->anon_vma && src->anon_vma) is true, this function tries to find * and reuse existing anon_vma which has no vmas and only one child anon_vma. * This prevents degradation of anon_vma hierarchy to endless linear chain in * case of constantly forking task. On the other hand, an anon_vma with more * than one child isn't reused even if there was no alive vma, thus rmap * walker has a good chance of avoiding scanning the whole hierarchy when it * searches where page is mapped. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { struct anon_vma_chain *avc, *pavc; struct anon_vma *root = NULL; list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { struct anon_vma *anon_vma; avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!avc)) { unlock_anon_vma_root(root); root = NULL; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto enomem_failure; } anon_vma = pavc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_chain_link(dst, avc, anon_vma); /* * Reuse existing anon_vma if it has no vma and only one * anon_vma child. * * Root anon_vma is never reused: * it has self-parent reference and at least one child. */ if (!dst->anon_vma && src->anon_vma && anon_vma->num_children < 2 && anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma; } if (dst->anon_vma) dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root); return 0; enomem_failure: /* * dst->anon_vma is dropped here otherwise its degree can be incorrectly * decremented in unlink_anon_vmas(). * We can safely do this because callers of anon_vma_clone() don't care * about dst->anon_vma if anon_vma_clone() failed. */ dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; } /* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; int error; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ vma->anon_vma = NULL; /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ error = anon_vma_clone(vma, pvma); if (error) return error; /* An existing anon_vma has been reused, all done then. */ if (vma->anon_vma) return 0; /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; anon_vma->num_active_vmas++; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; /* * The root anon_vma's spinlock is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; out_error_free_anon_vma: put_anon_vma(anon_vma); out_error: unlink_anon_vmas(vma); return -ENOMEM; } void unlink_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; struct anon_vma *root = NULL; /* * Unlink each anon_vma chained to the VMA. This list is ordered * from newest to oldest, ensuring the root anon_vma gets freed last. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); /* * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { anon_vma->parent->num_children--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } if (vma->anon_vma) vma->anon_vma->num_active_vmas--; unlock_anon_vma_root(root); /* * Iterate the list once more, it now only contains empty and unlinked * anon_vmas, destroy them. Could not do before due to __put_anon_vma() * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; VM_WARN_ON(anon_vma->num_children); VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } } static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); anon_vma->rb_root = RB_ROOT_CACHED; } void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC|SLAB_ACCOUNT); } /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against page_remove_rmap() * the best this function can do is return a locked anon_vma that might * have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe page_mapped() [ hence all those page_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from * page_remove_rmap() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. */ struct anon_vma *page_get_anon_vma(struct page *page) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } /* * If this page is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!page_mapped(page)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; } /* * Similar to page_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with page_get_anon_vma() and then block on the mutex. */ struct anon_vma *page_lock_anon_vma_read(struct page *page) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * If the page is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ if (!page_mapped(page)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!page_mapped(page)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); anon_vma_lock_read(anon_vma); if (atomic_dec_and_test(&anon_vma->refcount)) { /* * Oops, we held the last refcount, release the lock * and bail -- can't simply use put_anon_vma() because * we'll deadlock on the anon_vma_lock_write() recursion. */ anon_vma_unlock_read(anon_vma); __put_anon_vma(anon_vma); anon_vma = NULL; } return anon_vma; out: rcu_read_unlock(); return anon_vma; } void page_unlock_anon_vma_read(struct anon_vma *anon_vma) { anon_vma_unlock_read(anon_vma); } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */ void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (!tlb_ubc->flush_required) return; arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; } /* Flush iff there are potentially writable TLB entries that can race with IO */ void try_to_unmap_flush_dirty(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); } static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); tlb_ubc->flush_required = true; /* * Ensure compiler does not re-order the setting of tlb_flush_batched * before the PTE is cleared. */ barrier(); mm->tlb_flush_batched = true; /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() * before the page is queued for IO. */ if (writable) tlb_ubc->writable = true; } /* * Returns true if the TLB flush should be deferred to the end of a batch of * unmap operations to reduce IPIs. */ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { bool should_defer = false; if (!(flags & TTU_BATCH_FLUSH)) return false; /* If remote CPUs need to be flushed then defer batch the flush */ if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids) should_defer = true; put_cpu(); return should_defer; } /* * Reclaim unmaps pages under the PTL but do not flush the TLB prior to * releasing the PTL if TLB flushes are batched. It's possible for a parallel * operation such as mprotect or munmap to race between reclaim unmapping * the page and flushing the page. If this race occurs, it potentially allows * access to data via a stale TLB entry. Tracking all mm's that have TLB * batching in flight would be expensive during reclaim so instead track * whether TLB batching occurred in the past and if so then do a flush here * if required. This will cost one additional flush per reclaim cycle paid * by the first operation at risk such as mprotect and mumap. * * This must be called under the PTL so that an access to tlb_flush_batched * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise * via the PTL. */ void flush_tlb_batched_pending(struct mm_struct *mm) { if (data_race(mm->tlb_flush_batched)) { flush_tlb_mm(mm); /* * Do not allow the compiler to re-order the clearing of * tlb_flush_batched before the tlb is flushed. */ barrier(); mm->tlb_flush_batched = false; } } #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { } static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /* * At what user virtual address is page expected in vma? * Caller should check the page is actually part of the vma. */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { if (PageAnon(page)) { struct anon_vma *page__anon_vma = page_anon_vma(page); /* * Note: swapoff's unuse_vma() is more efficient with this * check, and needs it to match anon_vma when KSM is active. */ if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; } else if (!vma->vm_file) { return -EFAULT; } else if (vma->vm_file->f_mapping != compound_head(page)->mapping) { return -EFAULT; } return vma_address(page, vma); } pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pmd_t pmde; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); /* * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at() * without holding anon_vma lock for write. So when looking for a * genuine pmde (in which to find pte), test present and !THP together. */ pmde = *pmd; barrier(); if (!pmd_present(pmde) || pmd_trans_huge(pmde)) pmd = NULL; out: return pmd; } struct page_referenced_arg { int mapcount; int referenced; unsigned long vm_flags; struct mem_cgroup *memcg; }; /* * arg: page_referenced_arg will be passed */ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct page_referenced_arg *pra = arg; struct page_vma_mapped_walk pvmw = { .page = page, .vma = vma, .address = address, }; int referenced = 0; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; if (vma->vm_flags & VM_LOCKED) { page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } if (pvmw.pte) { if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) { /* * Don't treat a reference through * a sequentially read mapping as such. * If the page has been used in another mapping, * we will catch it; if this other mapping is * already gone, the unmap path will have set * PG_referenced or activated the page. */ if (likely(!(vma->vm_flags & VM_SEQ_READ))) referenced++; } } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) referenced++; } else { /* unexpected pmd-mapped page? */ WARN_ON_ONCE(1); } pra->mapcount--; } if (referenced) clear_page_idle(page); if (test_and_clear_page_young(page)) referenced++; if (referenced) { pra->referenced++; pra->vm_flags |= vma->vm_flags; } if (!pra->mapcount) return false; /* To break the loop */ return true; } static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg) { struct page_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; if (!mm_match_cgroup(vma->vm_mm, memcg)) return true; return false; } /** * page_referenced - test if the page was referenced * @page: the page to test * @is_locked: caller holds lock on the page * @memcg: target memory cgroup * @vm_flags: collect encountered vma->vm_flags who actually referenced the page * * Quick test_and_clear_referenced for all mappings to a page, * returns the number of ptes which referenced the page. */ int page_referenced(struct page *page, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { int we_locked = 0; struct page_referenced_arg pra = { .mapcount = total_mapcount(page), .memcg = memcg, }; struct rmap_walk_control rwc = { .rmap_one = page_referenced_one, .arg = (void *)&pra, .anon_lock = page_lock_anon_vma_read, }; *vm_flags = 0; if (!pra.mapcount) return 0; if (!page_rmapping(page)) return 0; if (!is_locked && (!PageAnon(page) || PageKsm(page))) { we_locked = trylock_page(page); if (!we_locked) return 1; } /* * If we are reclaiming on behalf of a cgroup, skip * counting on behalf of references from different * cgroups */ if (memcg) { rwc.invalid_vma = invalid_page_referenced_vma; } rmap_walk(page, &rwc); *vm_flags = pra.vm_flags; if (we_locked) unlock_page(page); return pra.referenced; } static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct page_vma_mapped_walk pvmw = { .page = page, .vma = vma, .address = address, .flags = PVMW_SYNC, }; struct mmu_notifier_range range; int *cleaned = arg; /* * We have to assume the worse case ie pmd for invalidation. Note that * the page can not be free from this function. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma, vma->vm_mm, address, vma_address_end(page, vma)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { int ret = 0; address = pvmw.address; if (pvmw.pte) { pte_t entry; pte_t *pte = pvmw.pte; if (!pte_dirty(*pte) && !pte_write(*pte)) continue; flush_cache_page(vma, address, pte_pfn(*pte)); entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(vma->vm_mm, address, pte, entry); ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pmd_t *pmd = pvmw.pmd; pmd_t entry; if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) continue; flush_cache_page(vma, address, page_to_pfn(page)); entry = pmdp_invalidate(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); set_pmd_at(vma->vm_mm, address, pmd, entry); ret = 1; #else /* unexpected pmd-mapped page? */ WARN_ON_ONCE(1); #endif } /* * No need to call mmu_notifier_invalidate_range() as we are * downgrading page table protection not changing it to point * to a new page. * * See Documentation/vm/mmu_notifier.rst */ if (ret) (*cleaned)++; } mmu_notifier_invalidate_range_end(&range); return true; } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { if (vma->vm_flags & VM_SHARED) return false; return true; } int page_mkclean(struct page *page) { int cleaned = 0; struct address_space *mapping; struct rmap_walk_control rwc = { .arg = (void *)&cleaned, .rmap_one = page_mkclean_one, .invalid_vma = invalid_mkclean_vma, }; BUG_ON(!PageLocked(page)); if (!page_mapped(page)) return 0; mapping = page_mapping(page); if (!mapping) return 0; rmap_walk(page, &rwc); return cleaned; } EXPORT_SYMBOL_GPL(page_mkclean); /** * page_move_anon_rmap - move a page to our anon_vma * @page: the page to move to our anon_vma * @vma: the vma the page belongs to * * When a page belongs exclusively to one process after a COW event, * that page can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling * processes. */ void page_move_anon_rmap(struct page *page, struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; page = compound_head(page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_VMA(!anon_vma, vma); anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; /* * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written * simultaneously, so a concurrent reader (eg page_referenced()'s * PageAnon()) will not see one without the other. */ WRITE_ONCE(page->mapping, (struct address_space *) anon_vma); } /** * __page_set_anon_rmap - set up new anonymous rmap * @page: Page or Hugepage to add to rmap * @vma: VM area to add page to. * @address: User virtual address of the mapping * @exclusive: the page is exclusively owned by the current process */ static void __page_set_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, int exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); if (PageAnon(page)) return; /* * If the page isn't exclusively mapped into this vma, * we must use the _oldest_ possible anon_vma for the * page mapping! */ if (!exclusive) anon_vma = anon_vma->root; anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON; page->mapping = (struct address_space *) anon_vma; page->index = linear_page_index(vma, address); } /** * __page_check_anon_rmap - sanity check anonymous rmap addition * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ static void __page_check_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { /* * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. * * We have exclusion against page_add_anon_rmap because the caller * always holds the page locked, except if called from page_dup_rmap, * in which case the page is already known to be setup. * * We have exclusion against page_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked * over the call to page_add_new_anon_rmap. */ VM_BUG_ON_PAGE(page_anon_vma(page)->root != vma->anon_vma->root, page); VM_BUG_ON_PAGE(page_to_pgoff(page) != linear_page_index(vma, address), page); } /** * page_add_anon_rmap - add pte mapping to an anonymous page * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @compound: charge the page as compound or small page * * The caller needs to hold the pte lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that PageAnon is not being upgraded racily to PageKsm * (but PageKsm is never downgraded to PageAnon). */ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, bool compound) { do_page_add_anon_rmap(page, vma, address, compound ? RMAP_COMPOUND : 0); } /* * Special version of the above for do_swap_page, which often runs * into pages that are exclusively owned by the current process. * Everybody else should continue to use page_add_anon_rmap above. */ void do_page_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, int flags) { bool compound = flags & RMAP_COMPOUND; bool first; if (unlikely(PageKsm(page))) lock_page_memcg(page); else VM_BUG_ON_PAGE(!PageLocked(page), page); if (compound) { atomic_t *mapcount; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageTransHuge(page), page); mapcount = compound_mapcount_ptr(page); first = atomic_inc_and_test(mapcount); } else { first = atomic_inc_and_test(&page->_mapcount); } if (first) { int nr = compound ? thp_nr_pages(page) : 1; /* * We use the irq-unsafe __{inc|mod}_zone_page_stat because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption * disabled. */ if (compound) __inc_lruvec_page_state(page, NR_ANON_THPS); __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); } if (unlikely(PageKsm(page))) { unlock_page_memcg(page); return; } /* address might be in next vma when migration races vma_adjust */ if (first) __page_set_anon_rmap(page, vma, address, flags & RMAP_EXCLUSIVE); else __page_check_anon_rmap(page, vma, address); } /** * page_add_new_anon_rmap - add pte mapping to a new anonymous page * @page: the page to add the mapping to * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @compound: charge the page as compound or small page * * Same as page_add_anon_rmap but must only be called on *new* pages. * This means the inc-and-test can be bypassed. * Page does not have to be locked. */ void page_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address, bool compound) { int nr = compound ? thp_nr_pages(page) : 1; VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); __SetPageSwapBacked(page); if (compound) { VM_BUG_ON_PAGE(!PageTransHuge(page), page); /* increment count (starts at -1) */ atomic_set(compound_mapcount_ptr(page), 0); if (hpage_pincount_available(page)) atomic_set(compound_pincount_ptr(page), 0); __inc_lruvec_page_state(page, NR_ANON_THPS); } else { /* Anon THP always mapped first with PMD */ VM_BUG_ON_PAGE(PageTransCompound(page), page); /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); } __mod_lruvec_page_state(page, NR_ANON_MAPPED, nr); __page_set_anon_rmap(page, vma, address, 1); } /** * page_add_file_rmap - add pte mapping to a file page * @page: the page to add the mapping to * @compound: charge the page as compound or small page * * The caller needs to hold the pte lock. */ void page_add_file_rmap(struct page *page, bool compound) { int i, nr = 1; VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page); lock_page_memcg(page); if (compound && PageTransHuge(page)) { for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { if (atomic_inc_and_test(&page[i]._mapcount)) nr++; } if (!atomic_inc_and_test(compound_mapcount_ptr(page))) goto out; if (PageSwapBacked(page)) __inc_node_page_state(page, NR_SHMEM_PMDMAPPED); else __inc_node_page_state(page, NR_FILE_PMDMAPPED); } else { if (PageTransCompound(page) && page_mapping(page)) { VM_WARN_ON_ONCE(!PageLocked(page)); SetPageDoubleMap(compound_head(page)); if (PageMlocked(page)) clear_page_mlock(compound_head(page)); } if (!atomic_inc_and_test(&page->_mapcount)) goto out; } __mod_lruvec_page_state(page, NR_FILE_MAPPED, nr); out: unlock_page_memcg(page); } static void page_remove_file_rmap(struct page *page, bool compound) { int i, nr = 1; VM_BUG_ON_PAGE(compound && !PageHead(page), page); /* Hugepages are not counted in NR_FILE_MAPPED for now. */ if (unlikely(PageHuge(page))) { /* hugetlb pages are always mapped with pmds */ atomic_dec(compound_mapcount_ptr(page)); return; } /* page still mapped by someone else? */ if (compound && PageTransHuge(page)) { for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { if (atomic_add_negative(-1, &page[i]._mapcount)) nr++; } if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) return; if (PageSwapBacked(page)) __dec_node_page_state(page, NR_SHMEM_PMDMAPPED); else __dec_node_page_state(page, NR_FILE_PMDMAPPED); } else { if (!atomic_add_negative(-1, &page->_mapcount)) return; } /* * We use the irq-unsafe __{inc|mod}_lruvec_page_state because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption disabled. */ __mod_lruvec_page_state(page, NR_FILE_MAPPED, -nr); if (unlikely(PageMlocked(page))) clear_page_mlock(page); } static void page_remove_anon_compound_rmap(struct page *page) { int i, nr; if (!atomic_add_negative(-1, compound_mapcount_ptr(page))) return; /* Hugepages are not counted in NR_ANON_PAGES for now. */ if (unlikely(PageHuge(page))) return; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return; __dec_lruvec_page_state(page, NR_ANON_THPS); if (TestClearPageDoubleMap(page)) { /* * Subpages can be mapped with PTEs too. Check how many of * them are still mapped. */ for (i = 0, nr = 0; i < thp_nr_pages(page); i++) { if (atomic_add_negative(-1, &page[i]._mapcount)) nr++; } /* * Queue the page for deferred split if at least one small * page of the compound page is unmapped, but at least one * small page is still mapped. */ if (nr && nr < thp_nr_pages(page)) deferred_split_huge_page(page); } else { nr = thp_nr_pages(page); } if (unlikely(PageMlocked(page))) clear_page_mlock(page); if (nr) __mod_lruvec_page_state(page, NR_ANON_MAPPED, -nr); } /** * page_remove_rmap - take down pte mapping from a page * @page: page to remove mapping from * @compound: uncharge the page as compound or small page * * The caller needs to hold the pte lock. */ void page_remove_rmap(struct page *page, bool compound) { lock_page_memcg(page); if (!PageAnon(page)) { page_remove_file_rmap(page, compound); goto out; } if (compound) { page_remove_anon_compound_rmap(page); goto out; } /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) goto out; /* * We use the irq-unsafe __{inc|mod}_zone_page_stat because * these counters are not modified in interrupt context, and * pte lock(a spinlock) is held, which implies preemption disabled. */ __dec_lruvec_page_state(page, NR_ANON_MAPPED); if (unlikely(PageMlocked(page))) clear_page_mlock(page); if (PageTransCompound(page)) deferred_split_huge_page(compound_head(page)); /* * It would be tidy to reset the PageAnon mapping here, * but that might overwrite a racing page_add_anon_rmap * which increments mapcount after us but sets mapping * before us: so leave the reset to free_unref_page, * and remember that it's only reliable while mapped. * Leaving it set also helps swapoff to reinstate ptes * faster for those pages still in swapcache. */ out: unlock_page_memcg(page); } /* * @arg: enum ttu_flags will be passed to this argument */ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; struct page_vma_mapped_walk pvmw = { .page = page, .vma = vma, .address = address, }; pte_t pteval; struct page *subpage; bool ret = true; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and page_remove_rmap(), * try_to_unmap() may return false when it is about to become true, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* munlock has nothing to gain from examining un-locked vmas */ if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) return true; if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && is_zone_device_page(page) && !is_device_private_page(page)) return true; if (flags & TTU_SPLIT_HUGE_PMD) { split_huge_pmd_address(vma, address, flags & TTU_SPLIT_FREEZE, page); } /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ range.end = PageKsm(page) ? address + PAGE_SIZE : vma_address_end(page, vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, address, range.end); if (PageHuge(page)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION /* PMD-mapped THP migration entry */ if (!pvmw.pte && (flags & TTU_MIGRATION)) { VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page); set_pmd_migration_entry(&pvmw, page); continue; } #endif /* * If the page is mlock()d, we cannot swap it out. * If it's recently referenced (perhaps page_referenced * skipped over this mm) then we should reactivate it. */ if (!(flags & TTU_IGNORE_MLOCK)) { if (vma->vm_flags & VM_LOCKED) { /* PTE-mapped THP are never mlocked */ if (!PageTransCompound(page)) { /* * Holding pte lock, we do *not* need * mmap_lock here */ mlock_vma_page(page); } ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (flags & TTU_MUNLOCK) continue; } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_PAGE(!pvmw.pte, page); subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); address = pvmw.address; if (PageHuge(page) && !PageAnon(page)) { /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. */ VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { /* * huge_pmd_unshare unmapped an entire PMD * page. There is no way of knowing exactly * which PMDs may be cached for this mm, so * we must flush them all. start/end were * already adjusted above to cover this range. */ flush_cache_range(vma, range.start, range.end); flush_tlb_range(vma, range.start, range.end); mmu_notifier_invalidate_range(mm, range.start, range.end); /* * The ref count of the PMD page was dropped * which is part of the way map counting * is done for shared PMDs. Return 'true' * here. When there is no other sharing, * huge_pmd_unshare returns false and we will * unmap the actual page and drop map count * to zero. */ page_vma_mapped_walk_done(&pvmw); break; } } if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && is_zone_device_page(page)) { swp_entry_t entry; pte_t swp_pte; pteval = ptep_get_and_clear(mm, pvmw.address, pvmw.pte); /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ entry = make_migration_entry(page, 0); swp_pte = swp_entry_to_pte(entry); /* * pteval maps a zone device page and is therefore * a swap pte. */ if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. * * The assignment to subpage above was computed from a * swap PTE which results in an invalid pointer. * Since only PAGE_SIZE pages can currently be * migrated, just set it to page. This will need to be * changed when hugepage migrations to device private * memory are supported. */ subpage = page; goto discard; } /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the page. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } /* Move the dirty bit to the page. Now the pte is gone. */ if (pte_dirty(pteval)) set_page_dirty(page); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (PageHuge(page)) { hugetlb_count_sub(compound_nr(page), mm); set_huge_swap_pte_at(mm, address, pvmw.pte, pteval, vma_mmu_pagesize(vma)); } else { dec_mm_counter(mm, mm_counter(page)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(page)); /* We have to invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); } else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE))) { swp_entry_t entry; pte_t swp_pte; if (arch_unmap_one(mm, vma, address, pteval) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ entry = make_migration_entry(subpage, pte_write(pteval)); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, address, pvmw.pte, swp_pte); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(subpage) }; pte_t swp_pte; /* * Store the swap location in the pte. * See handle_pte_fault() ... */ if (unlikely(PageSwapBacked(page) != PageSwapCache(page))) { WARN_ON_ONCE(1); ret = false; /* We have to invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); page_vma_mapped_walk_done(&pvmw); break; } /* MADV_FREE page check */ if (!PageSwapBacked(page)) { int ref_count, map_count; /* * Synchronize with gup_pte_range(): * - clear PTE; barrier; read refcount * - inc refcount; barrier; read PTE */ smp_mb(); ref_count = page_ref_count(page); map_count = page_mapcount(page); /* * Order reads for page refcount and dirty flag * (see comments in __remove_mapping()). */ smp_rmb(); /* * The only page refs must be one from isolation * plus the rmap(s) (dropped by discard:). */ if (ref_count == 1 + map_count && !PageDirty(page)) { /* Invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); dec_mm_counter(mm, MM_ANONPAGES); goto discard; } /* * If the page was redirtied, it cannot be * discarded. Remap the page to page table. */ set_pte_at(mm, address, pvmw.pte, pteval); SetPageSwapBacked(page); ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (swap_duplicate(entry) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (arch_unmap_one(mm, vma, address, pteval) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); set_pte_at(mm, address, pvmw.pte, swp_pte); /* Invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); } else { /* * This is a locked file-backed page, thus it cannot * be removed from the page cache and replaced by a new * page before mmu_notifier_invalidate_range_end, so no * concurrent thread might update its page table to * point at new page while a device still is using this * page. * * See Documentation/vm/mmu_notifier.rst */ dec_mm_counter(mm, mm_counter_file(page)); } discard: /* * No need to call mmu_notifier_invalidate_range() it has be * done above for all cases requiring it to happen under page * table lock before mmu_notifier_invalidate_range_end() * * See Documentation/vm/mmu_notifier.rst */ page_remove_rmap(subpage, PageHuge(page)); put_page(page); } mmu_notifier_invalidate_range_end(&range); return ret; } static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) { return vma_is_temporary_stack(vma); } static int page_not_mapped(struct page *page) { return !page_mapped(page); } /** * try_to_unmap - try to remove all page table mappings to a page * @page: the page to get unmapped * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * page, used in the pageout path. Caller must hold the page lock. * * If unmap is successful, return true. Otherwise, false. */ bool try_to_unmap(struct page *page, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, }; /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the * page tables leading to a race where migration cannot * find the migration ptes. Rather than increasing the * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ if ((flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE)) && !PageKsm(page) && PageAnon(page)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(page, &rwc); else rmap_walk(page, &rwc); /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and page_remove_rmap(), * try_to_unmap() may return false when it is about to become true, * if page table locking is skipped: use TTU_SYNC to wait for that. */ return !page_mapcount(page); } /** * try_to_munlock - try to munlock a page * @page: the page to be munlocked * * Called from munlock code. Checks all of the VMAs mapping the page * to make sure nobody else has this page mlocked. The page will be * returned with PG_mlocked cleared if no other vmas have it mlocked. */ void try_to_munlock(struct page *page) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)TTU_MUNLOCK, .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, }; VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page); VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page); rmap_walk(page, &rwc); } void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); } static struct anon_vma *rmap_walk_anon_lock(struct page *page, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) return rwc->anon_lock(page); /* * Note: remove_migration_ptes() cannot use page_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages * are holding mmap_lock. Users without mmap_lock are required to * take a reference count to prevent the anon_vma disappearing */ anon_vma = page_anon_vma(page); if (!anon_vma) return NULL; anon_vma_lock_read(anon_vma); return anon_vma; } /* * rmap_walk_anon - do something to anonymous page using the object-based * rmap method * @page: the page to be handled * @rwc: control variable according to each walk type * * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the anon_vma struct it points to. * * When called from try_to_munlock(), the mmap_lock of the mm containing the vma * where the page was found will be held for write. So, we won't recheck * vm_flags for that VMA. That should be OK, because that vma shouldn't be * LOCKED. */ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; if (locked) { anon_vma = page_anon_vma(page); /* anon_vma disappear under us? */ VM_BUG_ON_PAGE(!anon_vma, page); } else { anon_vma = rmap_walk_anon_lock(page, rwc); } if (!anon_vma) return; pgoff_start = page_to_pgoff(page); pgoff_end = pgoff_start + thp_nr_pages(page) - 1; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(page, vma, address, rwc->arg)) break; if (rwc->done && rwc->done(page)) break; } if (!locked) anon_vma_unlock_read(anon_vma); } /* * rmap_walk_file - do something to file page using the object-based rmap method * @page: the page to be handled * @rwc: control variable according to each walk type * * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the address_space struct it points to. * * When called from try_to_munlock(), the mmap_lock of the mm containing the vma * where the page was found will be held for write. So, we won't recheck * vm_flags for that VMA. That should be OK, because that vma shouldn't be * LOCKED. */ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, bool locked) { struct address_space *mapping = page_mapping(page); pgoff_t pgoff_start, pgoff_end; struct vm_area_struct *vma; /* * The page lock not only makes sure that page->mapping cannot * suddenly be NULLified by truncation, it makes sure that the * structure at mapping cannot be freed and reused yet, * so we can safely take mapping->i_mmap_rwsem. */ VM_BUG_ON_PAGE(!PageLocked(page), page); if (!mapping) return; pgoff_start = page_to_pgoff(page); pgoff_end = pgoff_start + thp_nr_pages(page) - 1; if (!locked) i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(page, vma); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(page, vma, address, rwc->arg)) goto done; if (rwc->done && rwc->done(page)) goto done; } done: if (!locked) i_mmap_unlock_read(mapping); } void rmap_walk(struct page *page, struct rmap_walk_control *rwc) { if (unlikely(PageKsm(page))) rmap_walk_ksm(page, rwc); else if (PageAnon(page)) rmap_walk_anon(page, rwc, false); else rmap_walk_file(page, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ void rmap_walk_locked(struct page *page, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_PAGE(PageKsm(page), page); if (PageAnon(page)) rmap_walk_anon(page, rwc, true); else rmap_walk_file(page, rwc, true); } #ifdef CONFIG_HUGETLB_PAGE /* * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. */ void hugepage_add_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { struct anon_vma *anon_vma = vma->anon_vma; int first; BUG_ON(!PageLocked(page)); BUG_ON(!anon_vma); /* address might be in next vma when migration races vma_adjust */ first = atomic_inc_and_test(compound_mapcount_ptr(page)); if (first) __page_set_anon_rmap(page, vma, address, 0); } void hugepage_add_new_anon_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address) { BUG_ON(address < vma->vm_start || address >= vma->vm_end); atomic_set(compound_mapcount_ptr(page), 0); if (hpage_pincount_available(page)) atomic_set(compound_pincount_ptr(page), 0); __page_set_anon_rmap(page, vma, address, 1); } #endif /* CONFIG_HUGETLB_PAGE */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_PGTABLE_INVERT_H #define _ASM_PGTABLE_INVERT_H 1 #ifndef __ASSEMBLY__ /* * A clear pte value is special, and doesn't get inverted. * * Note that even users that only pass a pgprot_t (rather * than a full pte) won't trigger the special zero case, * because even PAGE_NONE has _PAGE_PROTNONE | _PAGE_ACCESSED * set. So the all zero case really is limited to just the * cleared page table entry case. */ static inline bool __pte_needs_invert(u64 val) { return val && !(val & _PAGE_PRESENT); } /* Get a mask to xor with the page table entry to get the correct pfn. */ static inline u64 protnone_mask(u64 val) { return __pte_needs_invert(val) ? ~0ull : 0; } static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask) { /* * When a PTE transitions from NONE to !NONE or vice-versa * invert the PFN part to stop speculation. * pte_pfn undoes this when needed. */ if (__pte_needs_invert(oldval) != __pte_needs_invert(val)) val = (val & ~mask) | (~val & mask); return val; } #endif /* __ASSEMBLY__ */ #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/linux/eventpoll.h ( Efficient event polling implementation ) * Copyright (C) 2001,...,2006 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #ifndef _LINUX_EVENTPOLL_H #define _LINUX_EVENTPOLL_H #include <uapi/linux/eventpoll.h> #include <uapi/linux/kcmp.h> /* Forward declarations to avoid compiler errors */ struct file; #ifdef CONFIG_EPOLL #ifdef CONFIG_KCMP struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); #endif /* Used to initialize the epoll bits inside the "struct file" */ static inline void eventpoll_init_file(struct file *file) { INIT_LIST_HEAD(&file->f_ep_links); INIT_LIST_HEAD(&file->f_tfile_llink); } /* Used to release the epoll bits inside the "struct file" */ void eventpoll_release_file(struct file *file); /* * This is called from inside fs/file_table.c:__fput() to unlink files * from the eventpoll interface. We need to have this facility to cleanup * correctly files that are closed without being removed from the eventpoll * interface. */ static inline void eventpoll_release(struct file *file) { /* * Fast check to avoid the get/release of the semaphore. Since * we're doing this outside the semaphore lock, it might return * false negatives, but we don't care. It'll help in 99.99% of cases * to avoid the semaphore lock. False positives simply cannot happen * because the file in on the way to be removed and nobody ( but * eventpoll ) has still a reference to this file. */ if (likely(list_empty(&file->f_ep_links))) return; /* * The file is being closed while it is still linked to an epoll * descriptor. We need to handle this by correctly unlinking it * from its containers. */ eventpoll_release_file(file); } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock); /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ static inline int ep_op_has_event(int op) { return op != EPOLL_CTL_DEL; } #else static inline void eventpoll_init_file(struct file *file) {} static inline void eventpoll_release(struct file *file) {} #endif #endif /* #ifndef _LINUX_EVENTPOLL_H */ |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_STRING_H_ #define _LINUX_STRING_H_ #include <linux/compiler.h> /* for inline */ #include <linux/types.h> /* for size_t */ #include <linux/stddef.h> /* for NULL */ #include <stdarg.h> #include <uapi/linux/string.h> extern char *strndup_user(const char __user *, long); extern void *memdup_user(const void __user *, size_t); extern void *vmemdup_user(const void __user *, size_t); extern void *memdup_user_nul(const void __user *, size_t); /* * Include machine specific inline routines */ #include <asm/string.h> #ifndef __HAVE_ARCH_STRCPY extern char * strcpy(char *,const char *); #endif #ifndef __HAVE_ARCH_STRNCPY extern char * strncpy(char *,const char *, __kernel_size_t); #endif #ifndef __HAVE_ARCH_STRLCPY size_t strlcpy(char *, const char *, size_t); #endif #ifndef __HAVE_ARCH_STRSCPY ssize_t strscpy(char *, const char *, size_t); #endif /* Wraps calls to strscpy()/memset(), no arch specific code required */ ssize_t strscpy_pad(char *dest, const char *src, size_t count); #ifndef __HAVE_ARCH_STRCAT extern char * strcat(char *, const char *); #endif #ifndef __HAVE_ARCH_STRNCAT extern char * strncat(char *, const char *, __kernel_size_t); #endif #ifndef __HAVE_ARCH_STRLCAT extern size_t strlcat(char *, const char *, __kernel_size_t); #endif #ifndef __HAVE_ARCH_STRCMP extern int strcmp(const char *,const char *); #endif #ifndef __HAVE_ARCH_STRNCMP extern int strncmp(const char *,const char *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_STRCASECMP extern int strcasecmp(const char *s1, const char *s2); #endif #ifndef __HAVE_ARCH_STRNCASECMP extern int strncasecmp(const char *s1, const char *s2, size_t n); #endif #ifndef __HAVE_ARCH_STRCHR extern char * strchr(const char *,int); #endif #ifndef __HAVE_ARCH_STRCHRNUL extern char * strchrnul(const char *,int); #endif extern char * strnchrnul(const char *, size_t, int); #ifndef __HAVE_ARCH_STRNCHR extern char * strnchr(const char *, size_t, int); #endif #ifndef __HAVE_ARCH_STRRCHR extern char * strrchr(const char *,int); #endif extern char * __must_check skip_spaces(const char *); extern char *strim(char *); static inline __must_check char *strstrip(char *str) { return strim(str); } #ifndef __HAVE_ARCH_STRSTR extern char * strstr(const char *, const char *); #endif #ifndef __HAVE_ARCH_STRNSTR extern char * strnstr(const char *, const char *, size_t); #endif #ifndef __HAVE_ARCH_STRLEN extern __kernel_size_t strlen(const char *); #endif #ifndef __HAVE_ARCH_STRNLEN extern __kernel_size_t strnlen(const char *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_STRPBRK extern char * strpbrk(const char *,const char *); #endif #ifndef __HAVE_ARCH_STRSEP extern char * strsep(char **,const char *); #endif #ifndef __HAVE_ARCH_STRSPN extern __kernel_size_t strspn(const char *,const char *); #endif #ifndef __HAVE_ARCH_STRCSPN extern __kernel_size_t strcspn(const char *,const char *); #endif #ifndef __HAVE_ARCH_MEMSET extern void * memset(void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSET16 extern void *memset16(uint16_t *, uint16_t, __kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSET32 extern void *memset32(uint32_t *, uint32_t, __kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSET64 extern void *memset64(uint64_t *, uint64_t, __kernel_size_t); #endif static inline void *memset_l(unsigned long *p, unsigned long v, __kernel_size_t n) { if (BITS_PER_LONG == 32) return memset32((uint32_t *)p, v, n); else return memset64((uint64_t *)p, v, n); } static inline void *memset_p(void **p, void *v, __kernel_size_t n) { if (BITS_PER_LONG == 32) return memset32((uint32_t *)p, (uintptr_t)v, n); else return memset64((uint64_t *)p, (uintptr_t)v, n); } extern void **__memcat_p(void **a, void **b); #define memcat_p(a, b) ({ \ BUILD_BUG_ON_MSG(!__same_type(*(a), *(b)), \ "type mismatch in memcat_p()"); \ (typeof(*a) *)__memcat_p((void **)(a), (void **)(b)); \ }) #ifndef __HAVE_ARCH_MEMCPY extern void * memcpy(void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMMOVE extern void * memmove(void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMSCAN extern void * memscan(void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCMP extern int memcmp(const void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_BCMP extern int bcmp(const void *,const void *,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif #ifndef __HAVE_ARCH_MEMCPY_FLUSHCACHE static inline void memcpy_flushcache(void *dst, const void *src, size_t cnt) { memcpy(dst, src, cnt); } #endif void *memchr_inv(const void *s, int c, size_t n); char *strreplace(char *s, char old, char new); extern void kfree_const(const void *x); extern char *kstrdup(const char *s, gfp_t gfp) __malloc; extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp); extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); int match_string(const char * const *array, size_t n, const char *string); int __sysfs_match_string(const char * const *array, size_t n, const char *s); /** * sysfs_match_string - matches given string in an array * @_a: array of strings * @_s: string to match with * * Helper for __sysfs_match_string(). Calculates the size of @a automatically. */ #define sysfs_match_string(_a, _s) __sysfs_match_string(_a, ARRAY_SIZE(_a), _s) #ifdef CONFIG_BINARY_PRINTF int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args); int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf); int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4); #endif extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available); int ptr_to_hashval(const void *ptr, unsigned long *hashval_out); /** * strstarts - does @str start with @prefix? * @str: string to examine * @prefix: prefix to look for. */ static inline bool strstarts(const char *str, const char *prefix) { return strncmp(str, prefix, strlen(prefix)) == 0; } size_t memweight(const void *ptr, size_t bytes); /** * memzero_explicit - Fill a region of memory (e.g. sensitive * keying data) with 0s. * @s: Pointer to the start of the area. * @count: The size of the area. * * Note: usually using memset() is just fine (!), but in cases * where clearing out _local_ data at the end of a scope is * necessary, memzero_explicit() should be used instead in * order to prevent the compiler from optimising away zeroing. * * memzero_explicit() doesn't need an arch-specific version as * it just invokes the one of memset() implicitly. */ static inline void memzero_explicit(void *s, size_t count) { memset(s, 0, count); barrier_data(s); } /** * kbasename - return the last part of a pathname. * * @path: path to extract the filename from. */ static inline const char *kbasename(const char *path) { const char *tail = strrchr(path, '/'); return tail ? tail + 1 : path; } #define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) #define __RENAME(x) __asm__(#x) void fortify_panic(const char *name) __noreturn __cold; void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter"); void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter"); void __read_overflow3(void) __compiletime_error("detected read beyond size of object passed as 3rd parameter"); void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) #ifdef CONFIG_KASAN extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); #else #define __underlying_memchr __builtin_memchr #define __underlying_memcmp __builtin_memcmp #define __underlying_memcpy __builtin_memcpy #define __underlying_memmove __builtin_memmove #define __underlying_memset __builtin_memset #define __underlying_strcat __builtin_strcat #define __underlying_strcpy __builtin_strcpy #define __underlying_strlen __builtin_strlen #define __underlying_strncat __builtin_strncat #define __underlying_strncpy __builtin_strncpy #endif __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __write_overflow(); if (p_size < size) fortify_panic(__func__); return __underlying_strncpy(p, q, size); } __FORTIFY_INLINE char *strcat(char *p, const char *q) { size_t p_size = __builtin_object_size(p, 0); if (p_size == (size_t)-1) return __underlying_strcat(p, q); if (strlcat(p, q, p_size) >= p_size) fortify_panic(__func__); return p; } __FORTIFY_INLINE __kernel_size_t strlen(const char *p) { __kernel_size_t ret; size_t p_size = __builtin_object_size(p, 0); /* Work around gcc excess stack consumption issue */ if (p_size == (size_t)-1 || (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) fortify_panic(__func__); return ret; } extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); __FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) { size_t p_size = __builtin_object_size(p, 0); __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); if (p_size <= ret && maxlen != ret) fortify_panic(__func__); return ret; } /* defined after fortified strlen to reuse it */ extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) { size_t ret; size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) return __real_strlcpy(p, q, size); ret = strlen(q); if (size) { size_t len = (ret >= size) ? size - 1 : ret; if (__builtin_constant_p(len) && len >= p_size) __write_overflow(); if (len >= p_size) fortify_panic(__func__); __underlying_memcpy(p, q, len); p[len] = '\0'; } return ret; } /* defined after fortified strlen and strnlen to reuse them */ __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) { size_t p_len, copy_len; size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) return __underlying_strncat(p, q, count); p_len = strlen(p); copy_len = strnlen(q, count); if (p_size < p_len + copy_len + 1) fortify_panic(__func__); __underlying_memcpy(p + p_len, q, copy_len); p[p_len + copy_len] = '\0'; return p; } __FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __write_overflow(); if (p_size < size) fortify_panic(__func__); return __underlying_memset(p, c, size); } __FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (__builtin_constant_p(size)) { if (p_size < size) __write_overflow(); if (q_size < size) __read_overflow2(); } if (p_size < size || q_size < size) fortify_panic(__func__); return __underlying_memcpy(p, q, size); } __FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (__builtin_constant_p(size)) { if (p_size < size) __write_overflow(); if (q_size < size) __read_overflow2(); } if (p_size < size || q_size < size) fortify_panic(__func__); return __underlying_memmove(p, q, size); } extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); __FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __real_memscan(p, c, size); } __FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (__builtin_constant_p(size)) { if (p_size < size) __read_overflow(); if (q_size < size) __read_overflow2(); } if (p_size < size || q_size < size) fortify_panic(__func__); return __underlying_memcmp(p, q, size); } __FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __underlying_memchr(p, c, size); } void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); __FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __real_memchr_inv(p, c, size); } extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); __FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) { size_t p_size = __builtin_object_size(p, 0); if (__builtin_constant_p(size) && p_size < size) __read_overflow(); if (p_size < size) fortify_panic(__func__); return __real_kmemdup(p, size, gfp); } /* defined after fortified strlen and memcpy to reuse them */ __FORTIFY_INLINE char *strcpy(char *p, const char *q) { size_t p_size = __builtin_object_size(p, 0); size_t q_size = __builtin_object_size(q, 0); if (p_size == (size_t)-1 && q_size == (size_t)-1) return __underlying_strcpy(p, q); memcpy(p, q, strlen(q) + 1); return p; } /* Don't use these outside the FORITFY_SOURCE implementation */ #undef __underlying_memchr #undef __underlying_memcmp #undef __underlying_memcpy #undef __underlying_memmove #undef __underlying_memset #undef __underlying_strcat #undef __underlying_strcpy #undef __underlying_strlen #undef __underlying_strncat #undef __underlying_strncpy #endif /** * memcpy_and_pad - Copy one buffer to another with padding * @dest: Where to copy to * @dest_len: The destination buffer size * @src: Where to copy from * @count: The number of bytes to copy * @pad: Character to use for padding if space is left in destination. */ static inline void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, int pad) { if (dest_len > count) { memcpy(dest, src, count); memset(dest + count, pad, dest_len - count); } else memcpy(dest, src, dest_len); } /** * str_has_prefix - Test if a string has a given prefix * @str: The string to test * @prefix: The string to see if @str starts with * * A common way to test a prefix of a string is to do: * strncmp(str, prefix, sizeof(prefix) - 1) * * But this can lead to bugs due to typos, or if prefix is a pointer * and not a constant. Instead use str_has_prefix(). * * Returns: * * strlen(@prefix) if @str starts with @prefix * * 0 if @str does not start with @prefix */ static __always_inline size_t str_has_prefix(const char *str, const char *prefix) { size_t len = strlen(prefix); return strncmp(str, prefix, len) == 0 ? len : 0; } #endif /* _LINUX_STRING_H_ */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/spinlock.h> #include <linux/atomic.h> /* * This is an implementation of the notion of "decrement a * reference count, and return locked if it decremented to zero". * * NOTE NOTE NOTE! This is _not_ equivalent to * * if (atomic_dec_and_test(&atomic)) { * spin_lock(&lock); * return 1; * } * return 0; * * because the spin-lock and the decrement must be * "atomic". */ int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock(lock); if (atomic_dec_and_test(atomic)) return 1; spin_unlock(lock); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock); int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock_irqsave(lock, *flags); if (atomic_dec_and_test(atomic)) return 1; spin_unlock_irqrestore(lock, *flags); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave); |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/mm.h> #include <linux/bitops.h> #include <asm/word-at-a-time.h> /* * Do a strnlen, return length of string *with* final '\0'. * 'count' is the user-supplied count, while 'max' is the * address space maximum. * * Return 0 for exceptions (which includes hitting the address * space maximum), or 'count+1' if hitting the user-supplied * maximum count. * * NOTE! We can sometimes overshoot the user-supplied maximum * if it fits in a aligned 'long'. The caller needs to check * the return value against "> max". */ static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long align, res = 0; unsigned long c; /* * Do everything aligned. But that means that we * need to also expand the maximum.. */ align = (sizeof(unsigned long) - 1) & (unsigned long)src; src -= align; max += align; unsafe_get_user(c, (unsigned long __user *)src, efault); c |= aligned_byte_mask(align); for (;;) { unsigned long data; if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); return res + find_zero(data) + 1 - align; } res += sizeof(unsigned long); /* We already handled 'unsigned long' bytes. Did we do it all ? */ if (unlikely(max <= sizeof(unsigned long))) break; max -= sizeof(unsigned long); unsafe_get_user(c, (unsigned long __user *)(src+res), efault); } res -= align; /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, return the marker for "too long". */ if (res >= count) return count+1; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's 0. */ efault: return 0; } /** * strnlen_user: - Get the size of a user string INCLUDING final NUL. * @str: The string to measure. * @count: Maximum count (including NUL character) * * Context: User context only. This function may sleep if pagefaults are * enabled. * * Get the size of a NUL-terminated string in user space. * * Returns the size of the string INCLUDING the terminating NUL. * If the string is too long, returns a number larger than @count. User * has to check the return value against "> count". * On exception (or invalid count), returns 0. * * NOTE! You should basically never use this function. There is * almost never any valid case for using the length of a user space * string, since the string can be changed at any time by other * threads. Use "strncpy_from_user()" instead to get a stable copy * of the string. */ long strnlen_user(const char __user *str, long count) { unsigned long max_addr, src_addr; if (unlikely(count <= 0)) return 0; max_addr = user_addr_max(); src_addr = (unsigned long)untagged_addr(str); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; if (user_read_access_begin(str, max)) { retval = do_strnlen_user(str, count, max); user_read_access_end(); return retval; } } return 0; } EXPORT_SYMBOL(strnlen_user); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SPECIAL_INSNS_H #define _ASM_X86_SPECIAL_INSNS_H #ifdef __KERNEL__ #include <asm/nops.h> #include <asm/processor-flags.h> #include <linux/irqflags.h> #include <linux/jump_label.h> /* * The compiler should not reorder volatile asm statements with respect to each * other: they should execute in program order. However GCC 4.9.x and 5.x have * a bug (which was fixed in 8.1, 7.3 and 6.5) where they might reorder * volatile asm. The write functions are not affected since they have memory * clobbers preventing reordering. To prevent reads from being reordered with * respect to writes, use a dummy memory operand. */ #define __FORCE_ORDER "m"(*(unsigned int *)0x1000UL) void native_write_cr0(unsigned long val); static inline unsigned long native_read_cr0(void) { unsigned long val; asm volatile("mov %%cr0,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static __always_inline unsigned long native_read_cr2(void) { unsigned long val; asm volatile("mov %%cr2,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static __always_inline void native_write_cr2(unsigned long val) { asm volatile("mov %0,%%cr2": : "r" (val) : "memory"); } static inline unsigned long __native_read_cr3(void) { unsigned long val; asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER); return val; } static inline void native_write_cr3(unsigned long val) { asm volatile("mov %0,%%cr3": : "r" (val) : "memory"); } static inline unsigned long native_read_cr4(void) { unsigned long val; #ifdef CONFIG_X86_32 /* * This could fault if CR4 does not exist. Non-existent CR4 * is functionally equivalent to CR4 == 0. Keep it simple and pretend * that CR4 == 0 on CPUs that don't have CR4. */ asm volatile("1: mov %%cr4, %0\n" "2:\n" _ASM_EXTABLE(1b, 2b) : "=r" (val) : "0" (0), __FORCE_ORDER); #else /* CR4 always exists on x86_64. */ asm volatile("mov %%cr4,%0\n\t" : "=r" (val) : __FORCE_ORDER); #endif return val; } void native_write_cr4(unsigned long val); #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS static inline u32 rdpkru(void) { u32 ecx = 0; u32 edx, pkru; /* * "rdpkru" instruction. Places PKRU contents in to EAX, * clears EDX and requires that ecx=0. */ asm volatile(".byte 0x0f,0x01,0xee\n\t" : "=a" (pkru), "=d" (edx) : "c" (ecx)); return pkru; } static inline void wrpkru(u32 pkru) { u32 ecx = 0, edx = 0; /* * "wrpkru" instruction. Loads contents in EAX to PKRU, * requires that ecx = edx = 0. */ asm volatile(".byte 0x0f,0x01,0xef\n\t" : : "a" (pkru), "c"(ecx), "d"(edx)); } static inline void __write_pkru(u32 pkru) { /* * WRPKRU is relatively expensive compared to RDPKRU. * Avoid WRPKRU when it would not change the value. */ if (pkru == rdpkru()) return; wrpkru(pkru); } #else static inline u32 rdpkru(void) { return 0; } static inline void __write_pkru(u32 pkru) { } #endif static inline void native_wbinvd(void) { asm volatile("wbinvd": : :"memory"); } extern asmlinkage void asm_load_gs_index(unsigned int selector); static inline void native_load_gs_index(unsigned int selector) { unsigned long flags; local_irq_save(flags); asm_load_gs_index(selector); local_irq_restore(flags); } static inline unsigned long __read_cr4(void) { return native_read_cr4(); } #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else static inline unsigned long read_cr0(void) { return native_read_cr0(); } static inline void write_cr0(unsigned long x) { native_write_cr0(x); } static __always_inline unsigned long read_cr2(void) { return native_read_cr2(); } static __always_inline void write_cr2(unsigned long x) { native_write_cr2(x); } /* * Careful! CR3 contains more than just an address. You probably want * read_cr3_pa() instead. */ static inline unsigned long __read_cr3(void) { return __native_read_cr3(); } static inline void write_cr3(unsigned long x) { native_write_cr3(x); } static inline void __write_cr4(unsigned long x) { native_write_cr4(x); } static inline void wbinvd(void) { native_wbinvd(); } #ifdef CONFIG_X86_64 static inline void load_gs_index(unsigned int selector) { native_load_gs_index(selector); } #endif #endif /* CONFIG_PARAVIRT_XXL */ static inline void clflush(volatile void *__p) { asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); } static inline void clflushopt(volatile void *__p) { alternative_io(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0", ".byte 0x66; clflush %P0", X86_FEATURE_CLFLUSHOPT, "+m" (*(volatile char __force *)__p)); } static inline void clwb(volatile void *__p) { volatile struct { char x[64]; } *p = __p; asm volatile(ALTERNATIVE_2( ".byte " __stringify(NOP_DS_PREFIX) "; clflush (%[pax])", ".byte 0x66; clflush (%[pax])", /* clflushopt (%%rax) */ X86_FEATURE_CLFLUSHOPT, ".byte 0x66, 0x0f, 0xae, 0x30", /* clwb (%%rax) */ X86_FEATURE_CLWB) : [p] "+m" (*p) : [pax] "a" (p)); } #define nop() asm volatile ("nop") static __always_inline void serialize(void) { /* Instruction opcode for SERIALIZE; supported in binutils >= 2.35. */ asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory"); } /* The dst parameter must be 64-bytes aligned */ static inline void movdir64b(void *dst, const void *src) { const struct { char _[64]; } *__src = src; struct { char _[64]; } *__dst = dst; /* * MOVDIR64B %(rdx), rax. * * Both __src and __dst must be memory constraints in order to tell the * compiler that no other memory accesses should be reordered around * this one. * * Also, both must be supplied as lvalues because this tells * the compiler what the object is (its size) the instruction accesses. * I.e., not the pointers but what they point to, thus the deref'ing '*'. */ asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" : "+m" (*__dst) : "m" (*__src), "a" (__dst), "d" (__src)); } /** * enqcmds - Enqueue a command in supervisor (CPL0) mode * @dst: destination, in MMIO space (must be 512-bit aligned) * @src: 512 bits memory operand * * The ENQCMDS instruction allows software to write a 512-bit command to * a 512-bit-aligned special MMIO region that supports the instruction. * A return status is loaded into the ZF flag in the RFLAGS register. * ZF = 0 equates to success, and ZF = 1 indicates retry or error. * * This function issues the ENQCMDS instruction to submit data from * kernel space to MMIO space, in a unit of 512 bits. Order of data access * is not guaranteed, nor is a memory barrier performed afterwards. It * returns 0 on success and -EAGAIN on failure. * * Warning: Do not use this helper unless your driver has checked that the * ENQCMDS instruction is supported on the platform and the device accepts * ENQCMDS. */ static inline int enqcmds(void __iomem *dst, const void *src) { const struct { char _[64]; } *__src = src; struct { char _[64]; } __iomem *__dst = dst; bool zf; /* * ENQCMDS %(rdx), rax * * See movdir64b()'s comment on operand specification. */ asm volatile(".byte 0xf3, 0x0f, 0x38, 0xf8, 0x02, 0x66, 0x90" CC_SET(z) : CC_OUT(z) (zf), "+m" (*__dst) : "m" (*__src), "a" (__dst), "d" (__src)); /* Submission failure is indicated via EFLAGS.ZF=1 */ if (zf) return -EAGAIN; return 0; } #endif /* __KERNEL__ */ #endif /* _ASM_X86_SPECIAL_INSNS_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __FS_NOTIFY_FSNOTIFY_H_ #define __FS_NOTIFY_FSNOTIFY_H_ #include <linux/list.h> #include <linux/fsnotify.h> #include <linux/srcu.h> #include <linux/types.h> #include "../mount.h" static inline struct inode *fsnotify_conn_inode( struct fsnotify_mark_connector *conn) { return container_of(conn->obj, struct inode, i_fsnotify_marks); } static inline struct mount *fsnotify_conn_mount( struct fsnotify_mark_connector *conn) { return container_of(conn->obj, struct mount, mnt_fsnotify_marks); } static inline struct super_block *fsnotify_conn_sb( struct fsnotify_mark_connector *conn) { return container_of(conn->obj, struct super_block, s_fsnotify_marks); } static inline struct super_block *fsnotify_connector_sb( struct fsnotify_mark_connector *conn) { switch (conn->type) { case FSNOTIFY_OBJ_TYPE_INODE: return fsnotify_conn_inode(conn)->i_sb; case FSNOTIFY_OBJ_TYPE_VFSMOUNT: return fsnotify_conn_mount(conn)->mnt.mnt_sb; case FSNOTIFY_OBJ_TYPE_SB: return fsnotify_conn_sb(conn); default: return NULL; } } /* destroy all events sitting in this groups notification queue */ extern void fsnotify_flush_notify(struct fsnotify_group *group); /* protects reads of inode and vfsmount marks list */ extern struct srcu_struct fsnotify_mark_srcu; /* compare two groups for sorting of marks lists */ extern int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b); /* Destroy all marks attached to an object via connector */ extern void fsnotify_destroy_marks(fsnotify_connp_t *connp); /* run the list of all marks associated with inode and destroy them */ static inline void fsnotify_clear_marks_by_inode(struct inode *inode) { fsnotify_destroy_marks(&inode->i_fsnotify_marks); } /* run the list of all marks associated with vfsmount and destroy them */ static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt) { fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks); } /* run the list of all marks associated with sb and destroy them */ static inline void fsnotify_clear_marks_by_sb(struct super_block *sb) { fsnotify_destroy_marks(&sb->s_fsnotify_marks); } /* * update the dentry->d_flags of all of inode's children to indicate if inode cares * about events that happen to its children. */ extern void fsnotify_set_children_dentry_flags(struct inode *inode); extern struct kmem_cache *fsnotify_mark_connector_cachep; #endif /* __FS_NOTIFY_FSNOTIFY_H_ */ |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <dipankar@in.ibm.com> * * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) * * For detailed explanation of Read-Copy Update mechanism see - * http://lse.sourceforge.net/locking/rcupdate.html * */ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <asm/processor.h> #include <linux/cpumask.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define ulong2long(a) (*(long *)(&(a))) #define USHORT_CMP_GE(a, b) (USHRT_MAX / 2 >= (unsigned short)((a) - (b))) #define USHORT_CMP_LT(a, b) (USHRT_MAX / 2 < (unsigned short)((a) - (b))) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void rcu_barrier_tasks_rude(void); void synchronize_rcu(void); #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from * areas that don't even know about current. This gives the rcu_read_lock() * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() (current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TINY_RCU #define rcu_read_unlock_strict() do { } while (0) #else void rcu_read_unlock_strict(void); #endif static inline void __rcu_read_lock(void) { preempt_disable(); } static inline void __rcu_read_unlock(void) { preempt_enable(); rcu_read_unlock_strict(); } static inline int rcu_preempt_depth(void) { return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active __read_mostly; void rcu_sched_clock_irq(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); #ifdef CONFIG_TASKS_RCU_GENERIC void rcu_init_tasks_generic(void); #else static inline void rcu_init_tasks_generic(void) { } #endif #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #ifdef CONFIG_NO_HZ_FULL void rcu_user_enter(void); void rcu_user_exit(void); #else static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } #endif /* CONFIG_NO_HZ_FULL */ #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); void rcu_nocb_flush_deferred_wakeup(void); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /** * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers * @a: Code that RCU needs to pay attention to. * * RCU read-side critical sections are forbidden in the inner idle loop, * that is, between the rcu_idle_enter() and the rcu_idle_exit() -- RCU * will happily ignore any such read-side critical sections. However, * things like powertop need tracepoints in the inner idle loop. * * This macro provides the way out: RCU_NONIDLE(do_something_with_RCU()) * will tell RCU that it needs to pay attention, invoke its argument * (in this example, calling the do_something_with_RCU() function), * and then tell RCU to go back to ignoring this CPU. It is permissible * to nest RCU_NONIDLE() wrappers, but not indefinitely (but the limit is * on the order of a million or so, even on 32-bit systems). It is * not legal to block within RCU_NONIDLE(), nor is it permissible to * transfer control either into or out of RCU_NONIDLE()'s statement. */ #define RCU_NONIDLE(a) \ do { \ rcu_irq_enter_irqson(); \ do { a; } while (0); \ rcu_irq_exit_irqson(); \ } while (0) /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU_GENERIC # ifdef CONFIG_TASKS_RCU # define rcu_tasks_classic_qs(t, preempt) \ do { \ if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu # define synchronize_rcu_tasks synchronize_rcu # endif # ifdef CONFIG_TASKS_TRACE_RCU # define rcu_tasks_trace_qs(t) \ do { \ if (!likely(READ_ONCE((t)->trc_reader_checked)) && \ !unlikely(READ_ONCE((t)->trc_reader_nesting))) { \ smp_store_release(&(t)->trc_reader_checked, true); \ smp_mb(); /* Readers partitioned by store. */ \ } \ } while (0) # else # define rcu_tasks_trace_qs(t) do { } while (0) # endif #define rcu_tasks_qs(t, preempt) \ do { \ rcu_tasks_classic_qs((t), (preempt)); \ rcu_tasks_trace_qs((t)); \ } while (0) # ifdef CONFIG_TASKS_RUDE_RCU void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks_rude(void); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_stop(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_stop(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** * rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period? * * As an accident of implementation, an RCU Tasks Trace grace period also * acts as an RCU grace period. However, this could change at any time. * Code relying on this accident must call this function to verify that * this accident is still happening. * * You have been warned! */ static inline bool rcu_trace_implies_rcu_gp(void) { return true; } /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPTION kernels. */ #define cond_resched_tasks_rcu_qs() \ do { \ rcu_tasks_qs(current, false); \ cond_resched(); \ } while (0) /** * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states * @old_ts: jiffies at start of processing. * * This helper is for long-running softirq handlers, such as NAPI threads in * networking. The caller should initialize the variable passed in as @old_ts * at the beginning of the softirq handler. When invoked frequently, this macro * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will * provide both RCU and RCU-Tasks quiescent states. Note that this macro * modifies its old_ts argument. * * Because regions of code that have disabled softirq act as RCU read-side * critical sections, this macro should be invoked with softirq (and * preemption) enabled. * * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would * have more chance to invoke schedule() calls and provide necessary quiescent * states. As a contrast, calling cond_resched() only won't achieve the same * effect because cond_resched() does not provide RCU-Tasks quiescent states. */ #define rcu_softirq_qs_periodic(old_ts) \ do { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ time_after(jiffies, (old_ts) + HZ / 10)) { \ preempt_disable(); \ rcu_softirq_qs(); \ preempt_enable(); \ (old_ts) = jiffies; \ } \ } while (0) /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ #if defined(CONFIG_TREE_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif /* * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls * are needed for dynamic initialization and destruction of rcu_head * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for * dynamic initialization and destruction of statically allocated rcu_head * structures. However, rcu_head structures allocated dynamically in the * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head(struct rcu_head *head) { } static inline void destroy_rcu_head(struct rcu_head *head) { } static inline void init_rcu_head_on_stack(struct rcu_head *head) { } static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); } extern struct lockdep_map rcu_lock_map; extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) { return 1; } static inline int rcu_read_lock_bh_held(void) { return 1; } static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } static inline int rcu_read_lock_any_held(void) { return !preemptible(); } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU /** * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message * * This checks debug_lockdep_rcu_enabled() before checking (c) to * prevent early boot splats due to lockdep not yet being initialized, * and rechecks it after checking (c) to prevent false-positive splats * due to races with lockdep being disabled. See commit 3066820034b5dd * ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail. */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(".data.unlikely") __warned; \ if (debug_lockdep_rcu_enabled() && (c) && \ debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) #if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } #else /* #ifdef CONFIG_PROVE_RCU */ static inline void rcu_preempt_sleep_check(void) { } #endif /* #else #ifdef CONFIG_PROVE_RCU */ #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0) #define rcu_sleep_check() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple pointers markings to match different RCU implementations * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ #define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ /** * unrcu_pointer - mark a pointer as not being RCU protected * @p: pointer needing to lose its __rcu property * * Converts @p from an __rcu pointer to a __kernel pointer. * This allows an __rcu pointer to be used with xchg() and friends. */ #define unrcu_pointer(p) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)(p); \ rcu_check_sparse(p, __rcu); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_access_pointer(p, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_dereference_check(p, c, space) \ ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) #define rcu_dereference_raw(p) \ ({ \ /* Dependency order vs. p above. */ \ typeof(p) ________p1 = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. */ #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from * reordering the code that initializes the structure after the pointer * assignment. More importantly, this call documents which pointers * will be dereferenced by RCU read-side code. * * In some special cases, you may use RCU_INIT_POINTER() instead * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due * to the fact that it does not constrain either the CPU or the compiler. * That said, using RCU_INIT_POINTER() when you should have used * rcu_assign_pointer() is a very bad thing that results in * impossible-to-diagnose memory corruption. So please be careful. * See the RCU_INIT_POINTER() comment header for details. * * Note that rcu_assign_pointer() evaluates each of its arguments only * once, appearances notwithstanding. One of the "extra" evaluations * is in typeof() and the other visible only to sparse (__CHECKER__), * neither of which actually execute the argument. As with most cpp * macros, this execute-arguments-only-once property is important, so * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ #define rcu_assign_pointer(p, v) \ do { \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ else \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ } while (0) /** * rcu_replace_pointer() - replace an RCU pointer, returning its old value * @rcu_ptr: RCU pointer, whose old value is returned * @ptr: regular pointer * @c: the lockdep conditions under which the dereference will take place * * Perform a replacement, where @rcu_ptr is an RCU-annotated * pointer and @c is the lockdep argument that is passed to the * rcu_dereference_protected() call used to read that pointer. The old * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. */ #define rcu_replace_pointer(rcu_ptr, ptr, c) \ ({ \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ __tmp; \ }) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the * lockdep checks for being in an RCU read-side critical section. This is * useful when the value of this pointer is accessed, but the pointer is * not dereferenced, for example, when testing an RCU-protected pointer * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. * * It is also permissible to use rcu_access_pointer() when read-side * access to the pointer was removed at least one grace period ago, as * is the case in the context of the RCU callback that is freeing up * the data, or after a synchronize_rcu() returns. This can be useful * when tearing down multi-linked structures after a grace period * has elapsed. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the * dereference will take place are correct. Typically the conditions * indicate the various locking conditions that should be held at that * point. The check should return true if the conditions are satisfied. * An implicit check for being in an RCU read-side critical section * (rcu_read_lock()) is included. * * For example: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); * * Inserts memory barriers on architectures that require them * (currently only the Alpha), prevents the compiler from refetching * (and from merging fetches), and, more importantly, documents exactly * which pointers are protected by RCU and checks that the pointer is * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-bh counterpart to rcu_dereference_check(). */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \ __rcu) /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(). This is useful in cases where update-side locks * prevent the value of the pointer from changing. Please note that this * primitive does *not* prevent the compiler from repeating this reference * or combining it with other references, so it should not be used without * protection of appropriate locks. * * This function is only for update-side use. Using this function * when protected only by rcu_read_lock() will result in infrequent * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), (c), __rcu) /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * This is a simple wrapper around rcu_dereference_check(). */ #define rcu_dereference(p) rcu_dereference_check(p, 0) /** * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0) /** * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows:: * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); * if (long_lived) { * if (!atomic_inc_not_zero(p->refcnt)) * long_lived = false; * else * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); */ #define rcu_pointer_handoff(p) (p) /** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the * synchronize_rcu() is guaranteed to block until after all the other * CPUs exit their critical sections. Similarly, if call_rcu() is invoked * on one CPU while other CPUs are within RCU read-side critical * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU * callback is invoked. This is legal, because the RCU read-side critical * section that was running concurrently with the call_rcu() (and which * therefore might be referencing something that the corresponding RCU * callback would free up) has completed before the corresponding * RCU callback is invoked. * * RCU read-side critical sections may be nested. Any deferred actions * will be deferred until the outermost RCU read-side critical section * completes. * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU * read-side critical section that would block in a !PREEMPTION kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock() used illegally while idle"); } /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not * a bug -- this property is what provides RCU's performance benefits. * Of course, writers must coordinate with each other. The normal * spinlock primitives work well for this, but any other technique may be * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In most situations, rcu_read_unlock() is immune from deadlock. * However, in kernels built with CONFIG_RCU_BOOST, rcu_read_unlock() * is responsible for deboosting, which it does via rt_mutex_unlock(). * Unfortunately, this function acquires the scheduler's runqueue and * priority-inheritance spinlocks. This means that deadlock could result * if the caller of rcu_read_unlock() already holds one of these locks or * any lock that is ever acquired while holding them. * * That said, RCU readers are never priority boosted unless they were * preempted. Therefore, one way to avoid deadlock is to make sure * that preemption never happens within any RCU read-side critical * section whose outermost rcu_read_unlock() is called with one of * rt_mutex_unlock()'s locks held. Such preemption can be avoided in * a number of ways, for example, by invoking preempt_disable() before * critical section's outermost rcu_read_lock(). * * Given that the set of locks acquired by rt_mutex_unlock() might change * at any time, a somewhat more future-proofed approach is to make sure * that that preemption never happens within any RCU read-side critical * section whose outermost rcu_read_unlock() is called with irqs disabled. * This approach relies on the fact that rt_mutex_unlock() currently only * acquires irq-disabled locks. * * The second of these two approaches is best in most situations, * however, the first approach can also be useful, at least to those * developers willing to keep abreast of the set of locks acquired by * rt_mutex_unlock(). * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); __release(RCU); __rcu_read_unlock(); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent of rcu_read_lock(), but also disables softirqs. * Note that anything else that disables softirqs can also serve as * an RCU read-side critical section. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) { local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_bh() used illegally while idle"); } /** * rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ static inline void rcu_read_unlock_bh(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * This is equivalent of rcu_read_lock(), but disables preemption. * Read-side critical sections can also be introduced by anything else * that disables preemption, including local_irq_disable() and friends. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_sched() from process context if the matching * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) { preempt_disable_notrace(); __acquire(RCU_SCHED); } /** * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section * * See rcu_read_lock_sched() for more information. */ static inline void rcu_read_unlock_sched(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) { __release(RCU_SCHED); preempt_enable_notrace(); } /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to * readers either at compile time or via rcu_assign_pointer() *and* * * a. You have not made *any* reader-visible changes to * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to * other state where exact synchronization is not required.) * * Failure to follow these rules governing use of RCU_INIT_POINTER() will * result in impossible-to-diagnose memory corruption. As in the structures * will look OK in crash dumps, but any concurrent RCU readers might * see pre-initialized values of the referenced data structure. So * please be very careful how you use RCU_INIT_POINTER()!!! * * If you are creating an RCU-protected linked structure that is accessed * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) \ do { \ rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) /* * Does the specified offset indicate that the corresponding rcu_head * structure can be handled by kvfree_rcu()? */ #define __is_kvfree_rcu_offset(offset) ((offset) < 4096) /* * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain. */ #define __kvfree_rcu(head, offset) \ do { \ BUILD_BUG_ON(!__is_kvfree_rcu_offset(offset)); \ kvfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ } while (0) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * * The kfree_rcu() function handles this issue. Rather than encoding a * function address in the embedded rcu_head structure, kfree_rcu() instead * encodes the offset of the rcu_head structure within the base structure. * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in __kvfree_rcu(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * * Note that the allowable offset might decrease in the future, for example, * to allow something like kmem_cache_free_rcu(). * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ #define kfree_rcu(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) \ __kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ } while (0) /** * kvfree_rcu() - kvfree an object after a grace period. * * This macro consists of one or two arguments and it is * based on whether an object is head-less or not. If it * has a head then a semantic stays the same as it used * to be before: * * kvfree_rcu(ptr, rhf); * * where @ptr is a pointer to kvfree(), @rhf is the name * of the rcu_head structure within the type of @ptr. * * When it comes to head-less variant, only one argument * is passed and that is just a pointer which has to be * freed after a grace period. Therefore the semantic is * * kvfree_rcu(ptr); * * where @ptr is a pointer to kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() * annotation. Otherwise, please switch and embed the * rcu_head structure within the type of @ptr. */ #define kvfree_rcu(...) KVFREE_GET_MACRO(__VA_ARGS__, \ kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__) #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kfree_rcu_mightsleep(ptr) kvfree_rcu_mightsleep(ptr) #define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME #define kvfree_rcu_arg_2(ptr, rhf) kfree_rcu(ptr, rhf) #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ \ if (___p) \ kvfree_call_rcu(NULL, (rcu_callback_t) (___p)); \ } while (0) /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies * if the UNLOCK and LOCK are executed by the same CPU or if the * UNLOCK and LOCK operate on the same lock variable. */ #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE #define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ #else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #define smp_mb__after_unlock_lock() do { } while (0) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ /* Has the specified rcu_head structure been handed to call_rcu()? */ /** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * * If you intend to invoke rcu_head_after_call_rcu() to test whether a * given rcu_head structure has already been passed to call_rcu(), then * you must also invoke this rcu_head_init() function on it just after * allocating that structure. Calls to this function must not race with * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. */ static inline void rcu_head_init(struct rcu_head *rhp) { rhp->func = (rcu_callback_t)~0L; } /** * rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including * the case where @rhp has already been invoked after a grace period. * Calls to this function must not race with callback invocation. One way * to avoid such races is to enclose the call to rcu_head_after_call_rcu() * in an RCU read-side critical section that includes a read-side fetch * of the pointer to the structure containing @rhp. */ static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { rcu_callback_t func = READ_ONCE(rhp->func); if (func == f) return true; WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } /* kernel/ksysfs.c definitions */ extern int rcu_expedited; extern int rcu_normal; #endif /* __LINUX_RCUPDATE_H */ |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1994 Linus Torvalds * * Pentium III FXSR, SSE support * General FPU state handling cleanups * Gareth Hughes <gareth@valinux.com>, May 2000 * x86-64 work by Andi Kleen 2002 */ #ifndef _ASM_X86_FPU_INTERNAL_H #define _ASM_X86_FPU_INTERNAL_H #include <linux/compat.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/mm.h> #include <asm/user.h> #include <asm/fpu/api.h> #include <asm/fpu/xstate.h> #include <asm/fpu/xcr.h> #include <asm/cpufeature.h> #include <asm/trace/fpu.h> /* * High level FPU state handling functions: */ extern void fpu__prepare_read(struct fpu *fpu); extern void fpu__prepare_write(struct fpu *fpu); extern void fpu__save(struct fpu *fpu); extern int fpu__restore_sig(void __user *buf, int ia32_frame); extern void fpu__drop(struct fpu *fpu); extern int fpu__copy(struct task_struct *dst, struct task_struct *src); extern void fpu__clear_user_states(struct fpu *fpu); extern void fpu__clear_all(struct fpu *fpu); extern int fpu__exception_code(struct fpu *fpu, int trap_nr); /* * Boot time FPU initialization functions: */ extern void fpu__init_cpu(void); extern void fpu__init_system_xstate(void); extern void fpu__init_cpu_xstate(void); extern void fpu__init_system(void); extern void fpu__init_check_bugs(void); extern void fpu__resume_cpu(void); extern u64 fpu__get_supported_xfeatures_mask(void); /* * Debugging facility: */ #ifdef CONFIG_X86_DEBUG_FPU # define WARN_ON_FPU(x) WARN_ON_ONCE(x) #else # define WARN_ON_FPU(x) ({ (void)(x); 0; }) #endif /* * FPU related CPU feature flag helper routines: */ static __always_inline __pure bool use_xsaveopt(void) { return static_cpu_has(X86_FEATURE_XSAVEOPT); } static __always_inline __pure bool use_xsave(void) { return static_cpu_has(X86_FEATURE_XSAVE); } static __always_inline __pure bool use_fxsr(void) { return static_cpu_has(X86_FEATURE_FXSR); } /* * fpstate handling functions: */ extern union fpregs_state init_fpstate; extern void fpstate_init(union fpregs_state *state); #ifdef CONFIG_MATH_EMULATION extern void fpstate_init_soft(struct swregs_state *soft); #else static inline void fpstate_init_soft(struct swregs_state *soft) {} #endif static inline void fpstate_init_xstate(struct xregs_state *xsave) { /* * XRSTORS requires these bits set in xcomp_bv, or it will * trigger #GP: */ xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask_all; } static inline void fpstate_init_fxstate(struct fxregs_state *fx) { fx->cwd = 0x37f; fx->mxcsr = MXCSR_DEFAULT; } extern void fpstate_sanitize_xstate(struct fpu *fpu); /* Returns 0 or the negated trap number, which results in -EFAULT for #PF */ #define user_insn(insn, output, input...) \ ({ \ int err; \ \ might_fault(); \ \ asm volatile(ASM_STAC "\n" \ "1: " #insn "\n" \ "2: " ASM_CLAC "\n" \ ".section .fixup,\"ax\"\n" \ "3: negl %%eax\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE_FAULT(1b, 3b) \ : [err] "=a" (err), output \ : "0"(0), input); \ err; \ }) #define kernel_insn_err(insn, output, input...) \ ({ \ int err; \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: movl $-1,%[err]\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE(1b, 3b) \ : [err] "=r" (err), output \ : "0"(0), input); \ err; \ }) #define kernel_insn(insn, output, input...) \ asm volatile("1:" #insn "\n\t" \ "2:\n" \ _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \ : output : input) static inline int copy_fregs_to_user(struct fregs_state __user *fx) { return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); } static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); else return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); } static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_kernel_to_fxregs_err(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) return kernel_insn_err(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else return kernel_insn_err(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); else return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void copy_kernel_to_fregs(struct fregs_state *fx) { kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_kernel_to_fregs_err(struct fregs_state *fx) { return kernel_insn_err(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fregs(struct fregs_state __user *fx) { return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline void copy_fxregs_to_kernel(struct fpu *fpu) { if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave)); else asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); } static inline void fxsave(struct fxregs_state *fx) { if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (*fx)); else asm volatile("fxsaveq %[fx]" : [fx] "=m" (*fx)); } /* These macros all use (%edi)/(%rdi) as the single memory argument. */ #define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" #define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" #define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" #define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" #define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" /* * After this @err contains 0 on success or the negated trap number when * the operation raises an exception. For faults this results in -EFAULT. */ #define XSTATE_OP(op, st, lmask, hmask, err) \ asm volatile("1:" op "\n\t" \ "xor %[err], %[err]\n" \ "2:\n\t" \ ".pushsection .fixup,\"ax\"\n\t" \ "3: negl %%eax\n\t" \ "jmp 2b\n\t" \ ".popsection\n\t" \ _ASM_EXTABLE_FAULT(1b, 3b) \ : [err] "=a" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact * format and supervisor states in addition to modified optimization in * XSAVEOPT. * * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT * supports modified optimization which is not supported by XSAVE. * * We use XSAVE as a fallback. * * The 661 label is defined in the ALTERNATIVE* macros as the address of the * original instruction which gets replaced. We need to use it here as the * address of the instruction where we might get an exception at. */ #define XSTATE_XSAVE(st, lmask, hmask, err) \ asm volatile(ALTERNATIVE_2(XSAVE, \ XSAVEOPT, X86_FEATURE_XSAVEOPT, \ XSAVES, X86_FEATURE_XSAVES) \ "\n" \ "xor %[err], %[err]\n" \ "3:\n" \ ".pushsection .fixup,\"ax\"\n" \ "4: movl $-2, %[err]\n" \ "jmp 3b\n" \ ".popsection\n" \ _ASM_EXTABLE(661b, 4b) \ : [err] "=r" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact * XSAVE area format. */ #define XSTATE_XRESTORE(st, lmask, hmask) \ asm volatile(ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ "3:\n" \ _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\ : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * This function is called only during boot time when x86 caps are not set * up and alternative can not be used yet. */ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) { u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; int err; WARN_ON(system_state != SYSTEM_BOOTING); if (boot_cpu_has(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); /* * We should never fault when copying from a kernel buffer, and the FPU * state we set at boot time should be valid. */ WARN_ON_FPU(err); } /* * Save processor xstate to xsave area. */ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) { u64 mask = xfeatures_mask_all; u32 lmask = mask; u32 hmask = mask >> 32; int err; WARN_ON_FPU(!alternatives_patched); XSTATE_XSAVE(xstate, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); } /* * Restore processor xstate from xsave area. */ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; XSTATE_XRESTORE(xstate, lmask, hmask); } /* * Save xstate to user space xsave area. * * We don't use modified optimization because xrstor/xrstors might track * a different application. * * We don't use compacted format xsave area for * backward compatibility for old applications which don't understand * compacted format of xsave area. */ static inline int copy_xregs_to_user(struct xregs_state __user *buf) { u64 mask = xfeatures_mask_user(); u32 lmask = mask; u32 hmask = mask >> 32; int err; /* * Clear the xsave header first, so that reserved fields are * initialized to zero. */ err = __clear_user(&buf->header, sizeof(buf->header)); if (unlikely(err)) return -EFAULT; stac(); XSTATE_OP(XSAVE, buf, lmask, hmask, err); clac(); return err; } /* * Restore xstate from user space xsave area. */ static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask) { struct xregs_state *xstate = ((__force struct xregs_state *)buf); u32 lmask = mask; u32 hmask = mask >> 32; int err; stac(); XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); clac(); return err; } /* * Restore xstate from kernel space xsave area, return an error code instead of * an exception. */ static inline int copy_kernel_to_xregs_err(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; int err; if (static_cpu_has(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); return err; } extern int copy_fpregs_to_fpstate(struct fpu *fpu); static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) { if (use_xsave()) { copy_kernel_to_xregs(&fpstate->xsave, mask); } else { if (use_fxsr()) copy_kernel_to_fxregs(&fpstate->fxsave); else copy_kernel_to_fregs(&fpstate->fsave); } } static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) { /* * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is * pending. Clear the x87 state here by setting it to fixed values. * "m" is a random variable that should be in L1. */ if (unlikely(static_cpu_has_bug(X86_BUG_FXSAVE_LEAK))) { asm volatile( "fnclex\n\t" "emms\n\t" "fildl %P[addr]" /* set F?P to defined value */ : : [addr] "m" (fpstate)); } __copy_kernel_to_fpregs(fpstate, -1); } extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); /* * FPU context switch related helper methods: */ DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); /* * The in-register FPU state for an FPU context on a CPU is assumed to be * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx * matches the FPU. * * If the FPU register state is valid, the kernel can skip restoring the * FPU state from memory. * * Any code that clobbers the FPU registers or updates the in-memory * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * * Either one of these invalidation functions is enough. Invalidate * a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ static inline void __cpu_invalidate_fpregs_state(void) { __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) { fpu->last_cpu = -1; } static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } /* * These generally need preemption protection to work, * do try to avoid using these on their own: */ static inline void fpregs_deactivate(struct fpu *fpu) { this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } /* * Internal helper, do not use directly. Use switch_fpu_return() instead. */ static inline void __fpregs_load_activate(void) { struct fpu *fpu = ¤t->thread.fpu; int cpu = smp_processor_id(); if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) return; if (!fpregs_state_valid(fpu, cpu)) { copy_kernel_to_fpregs(&fpu->state); fpregs_activate(fpu); fpu->last_cpu = cpu; } clear_thread_flag(TIF_NEED_FPU_LOAD); } /* * FPU state switching for scheduling. * * This is a two-stage process: * * - switch_fpu_prepare() saves the old state. * This is done within the context of the old process. * * - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state * will get loaded on return to userspace, or when the kernel needs it. * * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers * are saved in the current thread's FPU register state. * * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not * hold current()'s FPU registers. It is required to load the * registers before returning to userland or using the content * otherwise. * * The FPU context is only stored/restored for a user task and * PF_KTHREAD is used to distinguish between kernel and user threads. */ static inline void switch_fpu_prepare(struct task_struct *prev, int cpu) { struct fpu *old_fpu = &prev->thread.fpu; if (static_cpu_has(X86_FEATURE_FPU) && !(prev->flags & PF_KTHREAD)) { if (!copy_fpregs_to_fpstate(old_fpu)) old_fpu->last_cpu = -1; else old_fpu->last_cpu = cpu; /* But leave fpu_fpregs_owner_ctx! */ trace_x86_fpu_regs_deactivated(old_fpu); } } /* * Misc helper functions: */ /* * Load PKRU from the FPU context if available. Delay loading of the * complete FPU state until the return to userland. */ static inline void switch_fpu_finish(struct task_struct *next) { u32 pkru_val = init_pkru_value; struct pkru_state *pk; struct fpu *next_fpu = &next->thread.fpu; if (!static_cpu_has(X86_FEATURE_FPU)) return; set_thread_flag(TIF_NEED_FPU_LOAD); if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* * PKRU state is switched eagerly because it needs to be valid before we * return to userland e.g. for a copy_to_user() operation. */ if (!(next->flags & PF_KTHREAD)) { /* * If the PKRU bit in xsave.header.xfeatures is not set, * then the PKRU component was in init state, which means * XRSTOR will set PKRU to 0. If the bit is not set then * get_xsave_addr() will return NULL because the PKRU value * in memory is not valid. This means pkru_val has to be * set to 0 and not to init_pkru_value. */ pk = get_xsave_addr(&next_fpu->state.xsave, XFEATURE_PKRU); pkru_val = pk ? pk->pkru : 0; } __write_pkru(pkru_val); } #endif /* _ASM_X86_FPU_INTERNAL_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 | /* SPDX-License-Identifier: GPL-2.0 */ #include <asm/processor.h> static inline int phys_addr_valid(resource_size_t addr) { #ifdef CONFIG_PHYS_ADDR_T_64BIT return !(addr >> boot_cpu_data.x86_phys_bits); #else return 1; #endif } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2020 ARM Ltd. */ #ifndef __ASM_VDSO_PROCESSOR_H #define __ASM_VDSO_PROCESSOR_H #ifndef __ASSEMBLY__ /* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ static __always_inline void rep_nop(void) { asm volatile("rep; nop" ::: "memory"); } static __always_inline void cpu_relax(void) { rep_nop(); } #endif /* __ASSEMBLY__ */ #endif /* __ASM_VDSO_PROCESSOR_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 | // SPDX-License-Identifier: GPL-2.0 #include <linux/memblock.h> #include <linux/mmdebug.h> #include <linux/export.h> #include <linux/mm.h> #include <asm/page.h> #include <linux/vmalloc.h> #include "physaddr.h" #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { x = y + phys_base; VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); } else { x = y + (__START_KERNEL_map - PAGE_OFFSET); /* carry flag will be set if starting x was >= PAGE_OFFSET */ VIRTUAL_BUG_ON((x > y) || !phys_addr_valid(x)); } return x; } EXPORT_SYMBOL(__phys_addr); unsigned long __phys_addr_symbol(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* only check upper bounds since lower bounds will trigger carry */ VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); return y + phys_base; } EXPORT_SYMBOL(__phys_addr_symbol); #endif bool __virt_addr_valid(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ if (unlikely(x > y)) { x = y + phys_base; if (y >= KERNEL_IMAGE_SIZE) return false; } else { x = y + (__START_KERNEL_map - PAGE_OFFSET); /* carry flag will be set if starting x was >= PAGE_OFFSET */ if ((x > y) || !phys_addr_valid(x)) return false; } return pfn_valid(x >> PAGE_SHIFT); } EXPORT_SYMBOL(__virt_addr_valid); #else #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { unsigned long phys_addr = x - PAGE_OFFSET; /* VMALLOC_* aren't constants */ VIRTUAL_BUG_ON(x < PAGE_OFFSET); VIRTUAL_BUG_ON(__vmalloc_start_set && is_vmalloc_addr((void *) x)); /* max_low_pfn is set early, but not _that_ early */ if (max_low_pfn) { VIRTUAL_BUG_ON((phys_addr >> PAGE_SHIFT) > max_low_pfn); BUG_ON(slow_virt_to_phys((void *)x) != phys_addr); } return phys_addr; } EXPORT_SYMBOL(__phys_addr); #endif bool __virt_addr_valid(unsigned long x) { if (x < PAGE_OFFSET) return false; if (__vmalloc_start_set && is_vmalloc_addr((void *) x)) return false; if (x >= FIXADDR_START) return false; return pfn_valid((x - PAGE_OFFSET) >> PAGE_SHIFT); } EXPORT_SYMBOL(__virt_addr_valid); #endif /* CONFIG_X86_64 */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk). * * (C) SGI 2006, Christoph Lameter * Cleaned up and restructured to ease the addition of alternative * implementations of SLAB allocators. * (C) Linux Foundation 2008-2013 * Unified interface for all slab allocators */ #ifndef _LINUX_SLAB_H #define _LINUX_SLAB_H #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/percpu-refcount.h> /* * Flags to pass to kmem_cache_create(). * The ones marked DEBUG are only valid if CONFIG_DEBUG_SLAB is set. */ /* DEBUG: Perform (expensive) checks on alloc/free */ #define SLAB_CONSISTENCY_CHECKS ((slab_flags_t __force)0x00000100U) /* DEBUG: Red zone objs in a cache */ #define SLAB_RED_ZONE ((slab_flags_t __force)0x00000400U) /* DEBUG: Poison objects */ #define SLAB_POISON ((slab_flags_t __force)0x00000800U) /* Align objs on cache lines */ #define SLAB_HWCACHE_ALIGN ((slab_flags_t __force)0x00002000U) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA ((slab_flags_t __force)0x00004000U) /* Use GFP_DMA32 memory */ #define SLAB_CACHE_DMA32 ((slab_flags_t __force)0x00008000U) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER ((slab_flags_t __force)0x00010000U) /* Panic if kmem_cache_create() fails */ #define SLAB_PANIC ((slab_flags_t __force)0x00040000U) /* * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS! * * This delays freeing the SLAB page by a grace period, it does _NOT_ * delay object freeing. This means that if you do kmem_cache_free() * that memory location is free to be reused at any time. Thus it may * be possible to see another object there in the same RCU grace period. * * This feature only ensures the memory location backing the object * stays valid, the trick to using this is relying on an independent * object validation pass. Something like: * * rcu_read_lock() * again: * obj = lockless_lookup(key); * if (obj) { * if (!try_get_ref(obj)) // might fail for free objects * goto again; * * if (obj->key != key) { // not the object we expected * put_ref(obj); * goto again; * } * } * rcu_read_unlock(); * * This is useful if we need to approach a kernel structure obliquely, * from its address obtained without the usual locking. We can lock * the structure to stabilize it and check it's still at the given address, * only if we can be sure that the memory has not been meanwhile reused * for some other kind of object (which our subsystem's lock might corrupt). * * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. * * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ /* Defer freeing slabs to RCU */ #define SLAB_TYPESAFE_BY_RCU ((slab_flags_t __force)0x00080000U) /* Spread some memory over cpuset */ #define SLAB_MEM_SPREAD ((slab_flags_t __force)0x00100000U) /* Trace allocations and frees */ #define SLAB_TRACE ((slab_flags_t __force)0x00200000U) /* Flag to prevent checks on free */ #ifdef CONFIG_DEBUG_OBJECTS # define SLAB_DEBUG_OBJECTS ((slab_flags_t __force)0x00400000U) #else # define SLAB_DEBUG_OBJECTS 0 #endif /* Avoid kmemleak tracing */ #define SLAB_NOLEAKTRACE ((slab_flags_t __force)0x00800000U) /* Fault injection mark */ #ifdef CONFIG_FAILSLAB # define SLAB_FAILSLAB ((slab_flags_t __force)0x02000000U) #else # define SLAB_FAILSLAB 0 #endif /* Account to memcg */ #ifdef CONFIG_MEMCG_KMEM # define SLAB_ACCOUNT ((slab_flags_t __force)0x04000000U) #else # define SLAB_ACCOUNT 0 #endif #ifdef CONFIG_KASAN #define SLAB_KASAN ((slab_flags_t __force)0x08000000U) #else #define SLAB_KASAN 0 #endif /* The following flags affect the page allocator grouping pages by mobility */ /* Objects are reclaimable */ #define SLAB_RECLAIM_ACCOUNT ((slab_flags_t __force)0x00020000U) #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ /* Slab deactivation flag */ #define SLAB_DEACTIVATED ((slab_flags_t __force)0x10000000U) /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault. * * ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can. * Both make kfree a no-op. */ #define ZERO_SIZE_PTR ((void *)16) #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) #include <linux/kasan.h> struct mem_cgroup; /* * struct kmem_cache related prototypes */ void __init kmem_cache_init(void); bool slab_is_available(void); extern bool usercopy_fallback; struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); struct kmem_cache *kmem_cache_create_usercopy(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); void kmem_cache_destroy(struct kmem_cache *); int kmem_cache_shrink(struct kmem_cache *); /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. * * The alignment of the struct determines object alignment. If you * f.e. add ____cacheline_aligned_in_smp to the struct declaration * then the objects will be properly aligned in SMP configurations. */ #define KMEM_CACHE(__struct, __flags) \ kmem_cache_create(#__struct, sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), NULL) /* * To whitelist a single field for copying to/from usercopy, use this * macro instead for KMEM_CACHE() above. */ #define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ kmem_cache_create_usercopy(#__struct, \ sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), \ offsetof(struct __struct, __field), \ sizeof_field(struct __struct, __field), NULL) /* * Common kmalloc functions provided by all allocators */ void * __must_check krealloc(const void *, size_t, gfp_t); void kfree(const void *); void kfree_sensitive(const void *); size_t __ksize(const void *); size_t ksize(const void *); #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR void __check_heap_object(const void *ptr, unsigned long n, struct page *page, bool to_user); #else static inline void __check_heap_object(const void *ptr, unsigned long n, struct page *page, bool to_user) { } #endif /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. * Setting ARCH_KMALLOC_MINALIGN in arch headers allows that. */ #if defined(ARCH_DMA_MINALIGN) && ARCH_DMA_MINALIGN > 8 #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN #define KMALLOC_MIN_SIZE ARCH_DMA_MINALIGN #define KMALLOC_SHIFT_LOW ilog2(ARCH_DMA_MINALIGN) #else #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #endif /* * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. * Intended for arches that get misalignment faults even for 64 bit integer * aligned buffers. */ #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif /* * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN * aligned pointers. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) #define __assume_page_alignment __assume_aligned(PAGE_SIZE) /* * Kmalloc array related definitions */ #ifdef CONFIG_SLAB /* * The largest kmalloc size supported by the SLAB allocators is * 32 megabyte (2^25) or the maximum allocatable page order if that is * less than 32 MB. * * WARNING: Its not easy to increase this value since the allocators have * to do various tricks to work around compiler limitations in order to * ensure proper constant folding. */ #define KMALLOC_SHIFT_HIGH ((MAX_ORDER + PAGE_SHIFT - 1) <= 25 ? \ (MAX_ORDER + PAGE_SHIFT - 1) : 25) #define KMALLOC_SHIFT_MAX KMALLOC_SHIFT_HIGH #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 #endif #endif #ifdef CONFIG_SLUB /* * SLUB directly allocates requests fitting in to an order-1 page * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif #endif #ifdef CONFIG_SLOB /* * SLOB passes all requests larger than one page to the page allocator. * No kmalloc array is necessary since objects of different sizes can * be allocated from the same page. */ #define KMALLOC_SHIFT_HIGH PAGE_SHIFT #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif #endif /* Maximum allocatable size */ #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) /* Maximum size for which we actually use a slab cache */ #define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH) /* Maximum order allocatable via the slab allocator */ #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT) /* * Kmalloc subsystem. */ #ifndef KMALLOC_MIN_SIZE #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif /* * This restriction comes from byte sized index implementation. * Page size is normally 2^12 bytes and, in this case, if we want to use * byte sized index which can represent 2^8 entries, the size of the object * should be equal or greater to 2^12 / 2^8 = 2^4 = 16. * If minimum size of kmalloc is less than 16, we use it as minimum object * size and give up to use byte sized index. */ #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) /* * Whenever changing this, take care of that kmalloc_type() and * create_kmalloc_caches() still work as intended. */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, KMALLOC_RECLAIM, #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif NR_KMALLOC_TYPES }; #ifndef CONFIG_SLOB extern struct kmem_cache * kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) { #ifdef CONFIG_ZONE_DMA /* * The most common case is KMALLOC_NORMAL, so test for it * with a single branch for both flags. */ if (likely((flags & (__GFP_DMA | __GFP_RECLAIMABLE)) == 0)) return KMALLOC_NORMAL; /* * At least one of the flags has to be set. If both are, __GFP_DMA * is more important. */ return flags & __GFP_DMA ? KMALLOC_DMA : KMALLOC_RECLAIM; #else return flags & __GFP_RECLAIMABLE ? KMALLOC_RECLAIM : KMALLOC_NORMAL; #endif } /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. * 0 = zero alloc * 1 = 65 .. 96 bytes * 2 = 129 .. 192 bytes * n = 2^(n-1)+1 .. 2^n */ static __always_inline unsigned int kmalloc_index(size_t size) { if (!size) return 0; if (size <= KMALLOC_MIN_SIZE) return KMALLOC_SHIFT_LOW; if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) return 1; if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) return 2; if (size <= 8) return 3; if (size <= 16) return 4; if (size <= 32) return 5; if (size <= 64) return 6; if (size <= 128) return 7; if (size <= 256) return 8; if (size <= 512) return 9; if (size <= 1024) return 10; if (size <= 2 * 1024) return 11; if (size <= 4 * 1024) return 12; if (size <= 8 * 1024) return 13; if (size <= 16 * 1024) return 14; if (size <= 32 * 1024) return 15; if (size <= 64 * 1024) return 16; if (size <= 128 * 1024) return 17; if (size <= 256 * 1024) return 18; if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; if (size <= 4 * 1024 * 1024) return 22; if (size <= 8 * 1024 * 1024) return 23; if (size <= 16 * 1024 * 1024) return 24; if (size <= 32 * 1024 * 1024) return 25; if (size <= 64 * 1024 * 1024) return 26; BUG(); /* Will never be reached. Needed because the compiler may complain */ return -1; } #endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment __malloc; void kmem_cache_free(struct kmem_cache *, void *); /* * Bulk allocation and freeing operations. These are accelerated in an * allocator specific way to avoid taking locks repeatedly or building * metadata structures unnecessarily. * * Note that interrupts must be enabled when calling these functions. */ void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); /* * Caller must not use kfree_bulk() on memory not originally allocated * by kmalloc(), because the SLOB allocator cannot handle this. */ static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc; #else static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) { return __kmalloc(size, flags); } static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) { return kmem_cache_alloc(s, flags); } #endif #ifdef CONFIG_TRACING extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment __malloc; #ifdef CONFIG_NUMA extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) __assume_slab_alignment __malloc; #else static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { return kmem_cache_alloc_trace(s, gfpflags, size); } #endif /* CONFIG_NUMA */ #else /* CONFIG_TRACING */ static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) { void *ret = kmem_cache_alloc(s, flags); ret = kasan_kmalloc(s, ret, size, flags); return ret; } static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { void *ret = kmem_cache_alloc_node(s, gfpflags, node); ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; } #endif /* CONFIG_TRACING */ extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; #ifdef CONFIG_TRACING extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; #else static __always_inline void * kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) { return kmalloc_order(size, flags, order); } #endif static __always_inline void *kmalloc_large(size_t size, gfp_t flags) { unsigned int order = get_order(size); return kmalloc_order_trace(size, flags, order); } /** * kmalloc - allocate memory * @size: how many bytes of memory are required. * @flags: the type of memory to allocate. * * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN * bytes. For @size of power of two bytes, the alignment is also guaranteed * to be at least to the size. * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` * * The recommended usage of the @flags is described at * :ref:`Documentation/core-api/memory-allocation.rst <memory_allocation>` * * Below is a brief outline of the most useful GFP flags * * %GFP_KERNEL * Allocate normal kernel ram. May sleep. * * %GFP_NOWAIT * Allocation will not sleep. * * %GFP_ATOMIC * Allocation will not sleep. May use emergency pools. * * %GFP_HIGHUSER * Allocate memory from high memory on behalf of user. * * Also it is possible to set different flags by OR'ing * in one or more of the following additional @flags: * * %__GFP_HIGH * This allocation has high priority and may use emergency pools. * * %__GFP_NOFAIL * Indicate that this allocation is in no way allowed to fail * (think twice before using). * * %__GFP_NORETRY * If memory is not immediately available, * then give up at once. * * %__GFP_NOWARN * If allocation fails, don't issue any warnings. * * %__GFP_RETRY_MAYFAIL * Try really hard to succeed the allocation but fail * eventually. */ static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { #ifndef CONFIG_SLOB unsigned int index; #endif if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); #ifndef CONFIG_SLOB index = kmalloc_index(size); if (!index) return ZERO_SIZE_PTR; return kmem_cache_alloc_trace( kmalloc_caches[kmalloc_type(flags)][index], flags, size); #endif } return __kmalloc(size, flags); } static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && size <= KMALLOC_MAX_CACHE_SIZE) { unsigned int i = kmalloc_index(size); if (!i) return ZERO_SIZE_PTR; return kmem_cache_alloc_node_trace( kmalloc_caches[kmalloc_type(flags)][i], flags, node, size); } #endif return __kmalloc_node(size, flags, node); } /** * kmalloc_array - allocate memory for an array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc(bytes, flags); return __kmalloc(bytes, flags); } /** * kcalloc - allocate memory for an array. The memory is set to zero. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) { return kmalloc_array(n, size, flags | __GFP_ZERO); } /* * kmalloc_track_caller is a special version of kmalloc that records the * calling function of the routine calling it for slab leak tracking instead * of just the calling function (confusing, eh?). * It's useful when the call to kmalloc comes from a widely-used standard * allocator where we care about the real place the memory allocation * request comes from. */ extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc_node(bytes, flags, node); return __kmalloc_node(bytes, flags, node); } static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) { return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); } #ifdef CONFIG_NUMA extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long); #define kmalloc_node_track_caller(size, flags, node) \ __kmalloc_node_track_caller(size, flags, node, \ _RET_IP_) #else /* CONFIG_NUMA */ #define kmalloc_node_track_caller(size, flags, node) \ kmalloc_track_caller(size, flags) #endif /* CONFIG_NUMA */ /* * Shortcuts */ static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags) { return kmem_cache_alloc(k, flags | __GFP_ZERO); } /** * kzalloc - allocate memory. The memory is set to zero. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ static inline void *kzalloc(size_t size, gfp_t flags) { return kmalloc(size, flags | __GFP_ZERO); } /** * kzalloc_node - allocate zeroed memory from a particular memory node. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). * @node: memory node from which to allocate */ static inline void *kzalloc_node(size_t size, gfp_t flags, int node) { return kmalloc_node(size, flags | __GFP_ZERO, node); } unsigned int kmem_cache_size(struct kmem_cache *s); void __init kmem_cache_init_late(void); #if defined(CONFIG_SMP) && defined(CONFIG_SLAB) int slab_prepare_cpu(unsigned int cpu); int slab_dead_cpu(unsigned int cpu); #else #define slab_prepare_cpu NULL #define slab_dead_cpu NULL #endif #endif /* _LINUX_SLAB_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 | // SPDX-License-Identifier: GPL-2.0 /* * Lockless hierarchical page accounting & limiting * * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner */ #include <linux/page_counter.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sched.h> #include <linux/bug.h> #include <asm/page.h> static void propagate_protected_usage(struct page_counter *c, unsigned long usage) { unsigned long protected, old_protected; unsigned long low, min; long delta; if (!c->parent) return; min = READ_ONCE(c->min); if (min || atomic_long_read(&c->min_usage)) { protected = min(usage, min); old_protected = atomic_long_xchg(&c->min_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_min_usage); } low = READ_ONCE(c->low); if (low || atomic_long_read(&c->low_usage)) { protected = min(usage, low); old_protected = atomic_long_xchg(&c->low_usage, protected); delta = protected - old_protected; if (delta) atomic_long_add(delta, &c->parent->children_low_usage); } } /** * page_counter_cancel - take pages out of the local counter * @counter: counter * @nr_pages: number of pages to cancel */ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages) { long new; new = atomic_long_sub_return(nr_pages, &counter->usage); propagate_protected_usage(counter, new); /* More uncharges than charges? */ WARN_ON_ONCE(new < 0); } /** * page_counter_charge - hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * * NOTE: This does not consider any configured counter limits. */ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) { long new; new = atomic_long_add_return(nr_pages, &c->usage); propagate_protected_usage(c, new); /* * This is indeed racy, but we can live with some * inaccuracy in the watermark. */ if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } } /** * page_counter_try_charge - try to hierarchically charge pages * @counter: counter * @nr_pages: number of pages to charge * @fail: points first counter to hit its limit, if any * * Returns %true on success, or %false and @fail if the counter or one * of its ancestors has hit its configured limit. */ bool page_counter_try_charge(struct page_counter *counter, unsigned long nr_pages, struct page_counter **fail) { struct page_counter *c; for (c = counter; c; c = c->parent) { long new; /* * Charge speculatively to avoid an expensive CAS. If * a bigger charge fails, it might falsely lock out a * racing smaller charge and send it into reclaim * early, but the error is limited to the difference * between the two sizes, which is less than 2M/4M in * case of a THP locking out a regular page charge. * * The atomic_long_add_return() implies a full memory * barrier between incrementing the count and reading * the limit. When racing with page_counter_set_max(), * we either see the new limit or the setter sees the * counter has changed and retries. */ new = atomic_long_add_return(nr_pages, &c->usage); if (new > c->max) { atomic_long_sub(nr_pages, &c->usage); propagate_protected_usage(c, new); /* * This is racy, but we can live with some * inaccuracy in the failcnt which is only used * to report stats. */ data_race(c->failcnt++); *fail = c; goto failed; } propagate_protected_usage(c, new); /* * Just like with failcnt, we can live with some * inaccuracy in the watermark. */ if (new > READ_ONCE(c->watermark)) WRITE_ONCE(c->watermark, new); } return true; failed: for (c = counter; c != *fail; c = c->parent) page_counter_cancel(c, nr_pages); return false; } /** * page_counter_uncharge - hierarchically uncharge pages * @counter: counter * @nr_pages: number of pages to uncharge */ void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; for (c = counter; c; c = c->parent) page_counter_cancel(c, nr_pages); } /** * page_counter_set_max - set the maximum number of pages allowed * @counter: counter * @nr_pages: limit to set * * Returns 0 on success, -EBUSY if the current number of pages on the * counter already exceeds the specified limit. * * The caller must serialize invocations on the same counter. */ int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages) { for (;;) { unsigned long old; long usage; /* * Update the limit while making sure that it's not * below the concurrently-changing counter value. * * The xchg implies two full memory barriers before * and after, so the read-swap-read is ordered and * ensures coherency with page_counter_try_charge(): * that function modifies the count before checking * the limit, so if it sees the old limit, we see the * modified counter and retry. */ usage = atomic_long_read(&counter->usage); if (usage > nr_pages) return -EBUSY; old = xchg(&counter->max, nr_pages); if (atomic_long_read(&counter->usage) <= usage) return 0; counter->max = old; cond_resched(); } } /** * page_counter_set_min - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->min, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_set_low - set the amount of protected memory * @counter: counter * @nr_pages: value to set * * The caller must serialize invocations on the same counter. */ void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages) { struct page_counter *c; WRITE_ONCE(counter->low, nr_pages); for (c = counter; c; c = c->parent) propagate_protected_usage(c, atomic_long_read(&c->usage)); } /** * page_counter_memparse - memparse() for page counter limits * @buf: string to parse * @max: string meaning maximum possible value * @nr_pages: returns the result in number of pages * * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be * limited to %PAGE_COUNTER_MAX. */ int page_counter_memparse(const char *buf, const char *max, unsigned long *nr_pages) { char *end; u64 bytes; if (!strcmp(buf, max)) { *nr_pages = PAGE_COUNTER_MAX; return 0; } bytes = memparse(buf, &end); if (*end != '\0') return -EINVAL; *nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX); return 0; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H #define ARCH_DEFAULT_PKEY 0 /* * If more than 16 keys are ever supported, a thorough audit * will be necessary to ensure that the types that store key * numbers and masks have sufficient capacity. */ #define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); static inline bool arch_pkeys_enabled(void) { return boot_cpu_has(X86_FEATURE_OSPKE); } /* * Try to dedicate one of the protection keys to be used as an * execute-only protection key. */ extern int __execute_only_pkey(struct mm_struct *mm); static inline int execute_only_pkey(struct mm_struct *mm) { if (!boot_cpu_has(X86_FEATURE_OSPKE)) return ARCH_DEFAULT_PKEY; return __execute_only_pkey(mm); } extern int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey); static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey) { if (!boot_cpu_has(X86_FEATURE_OSPKE)) return 0; return __arch_override_mprotect_pkey(vma, prot, pkey); } extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3) #define mm_pkey_allocation_map(mm) (mm->context.pkey_allocation_map) #define mm_set_pkey_allocated(mm, pkey) do { \ mm_pkey_allocation_map(mm) |= (1U << pkey); \ } while (0) #define mm_set_pkey_free(mm, pkey) do { \ mm_pkey_allocation_map(mm) &= ~(1U << pkey); \ } while (0) static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { /* * "Allocated" pkeys are those that have been returned * from pkey_alloc() or pkey 0 which is allocated * implicitly when the mm is created. */ if (pkey < 0) return false; if (pkey >= arch_max_pkey()) return false; /* * The exec-only pkey is set in the allocation map, but * is not available to any of the user interfaces like * mprotect_pkey(). */ if (pkey == mm->context.execute_only_pkey) return false; return mm_pkey_allocation_map(mm) & (1U << pkey); } /* * Returns a positive, 4-bit key on success, or -1 on failure. */ static inline int mm_pkey_alloc(struct mm_struct *mm) { /* * Note: this is the one and only place we make sure * that the pkey is valid as far as the hardware is * concerned. The rest of the kernel trusts that * only good, valid pkeys come out of here. */ u16 all_pkeys_mask = ((1U << arch_max_pkey()) - 1); int ret; /* * Are we out of pkeys? We must handle this specially * because ffz() behavior is undefined if there are no * zeros. */ if (mm_pkey_allocation_map(mm) == all_pkeys_mask) return -1; ret = ffz(mm_pkey_allocation_map(mm)); mm_set_pkey_allocated(mm, ret); return ret; } static inline int mm_pkey_free(struct mm_struct *mm, int pkey) { if (!mm_pkey_is_allocated(mm, pkey)) return -EINVAL; mm_set_pkey_free(mm, pkey); return 0; } extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); extern void copy_init_pkru_to_fpregs(void); static inline int vma_pkey(struct vm_area_struct *vma) { unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3; return (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT; } #endif /*_ASM_X86_PKEYS_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/file_table.c * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) */ #include <linux/string.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/init.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/eventpoll.h> #include <linux/rcupdate.h> #include <linux/mount.h> #include <linux/capability.h> #include <linux/cdev.h> #include <linux/fsnotify.h> #include <linux/sysctl.h> #include <linux/percpu_counter.h> #include <linux/percpu.h> #include <linux/task_work.h> #include <linux/ima.h> #include <linux/swap.h> #include <linux/atomic.h> #include "internal.h" /* sysctl tunables... */ struct files_stat_struct files_stat = { .max_files = NR_FILE }; /* SLAB cache for file structures */ static struct kmem_cache *filp_cachep __read_mostly; static struct percpu_counter nr_files __cacheline_aligned_in_smp; static void file_free_rcu(struct rcu_head *head) { struct file *f = container_of(head, struct file, f_u.fu_rcuhead); put_cred(f->f_cred); kmem_cache_free(filp_cachep, f); } static inline void file_free(struct file *f) { security_file_free(f); if (!(f->f_mode & FMODE_NOACCOUNT)) percpu_counter_dec(&nr_files); call_rcu(&f->f_u.fu_rcuhead, file_free_rcu); } /* * Return the total number of open files in the system */ static long get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } /* * Return the maximum number of open files in the system */ unsigned long get_max_files(void) { return files_stat.max_files; } EXPORT_SYMBOL_GPL(get_max_files); /* * Handle nr_files sysctl */ #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) int proc_nr_files(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #else int proc_nr_files(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } #endif static struct file *__alloc_file(int flags, const struct cred *cred) { struct file *f; int error; f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL); if (unlikely(!f)) return ERR_PTR(-ENOMEM); f->f_cred = get_cred(cred); error = security_file_alloc(f); if (unlikely(error)) { file_free_rcu(&f->f_u.fu_rcuhead); return ERR_PTR(error); } atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); spin_lock_init(&f->f_lock); mutex_init(&f->f_pos_lock); eventpoll_init_file(f); f->f_flags = flags; f->f_mode = OPEN_FMODE(flags); /* f->f_version: 0 */ return f; } /* Find an unused file structure and return a pointer to it. * Returns an error pointer if some error happend e.g. we over file * structures limit, run out of memory or operation is not permitted. * * Be very careful using this. You are responsible for * getting write access to any mount that you might assign * to this filp, if it is opened for write. If this is not * done, you will imbalance int the mount's writer count * and a warning at __fput() time. */ struct file *alloc_empty_file(int flags, const struct cred *cred) { static long old_max; struct file *f; /* * Privileged users can go above max_files */ if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) { /* * percpu_counters are inaccurate. Do an expensive check before * we go and fail. */ if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files) goto over; } f = __alloc_file(flags, cred); if (!IS_ERR(f)) percpu_counter_inc(&nr_files); return f; over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { pr_info("VFS: file-max limit %lu reached\n", get_max_files()); old_max = get_nr_files(); } return ERR_PTR(-ENFILE); } /* * Variant of alloc_empty_file() that doesn't check and modify nr_files. * * Should not be used unless there's a very good reason to do so. */ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred) { struct file *f = __alloc_file(flags, cred); if (!IS_ERR(f)) f->f_mode |= FMODE_NOACCOUNT; return f; } /** * alloc_file - allocate and initialize a 'struct file' * * @path: the (dentry, vfsmount) pair for the new file * @flags: O_... flags with which the new file will be opened * @fop: the 'struct file_operations' for the new file */ static struct file *alloc_file(const struct path *path, int flags, const struct file_operations *fop) { struct file *file; file = alloc_empty_file(flags, current_cred()); if (IS_ERR(file)) return file; file->f_path = *path; file->f_inode = path->dentry->d_inode; file->f_mapping = path->dentry->d_inode->i_mapping; file->f_wb_err = filemap_sample_wb_err(file->f_mapping); file->f_sb_err = file_sample_sb_err(file); if ((file->f_mode & FMODE_READ) && likely(fop->read || fop->read_iter)) file->f_mode |= FMODE_CAN_READ; if ((file->f_mode & FMODE_WRITE) && likely(fop->write || fop->write_iter)) file->f_mode |= FMODE_CAN_WRITE; file->f_mode |= FMODE_OPENED; file->f_op = fop; if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(path->dentry->d_inode); return file; } struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, const char *name, int flags, const struct file_operations *fops) { static const struct dentry_operations anon_ops = { .d_dname = simple_dname }; struct qstr this = QSTR_INIT(name, strlen(name)); struct path path; struct file *file; path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this); if (!path.dentry) return ERR_PTR(-ENOMEM); if (!mnt->mnt_sb->s_d_op) d_set_d_op(path.dentry, &anon_ops); path.mnt = mntget(mnt); d_instantiate(path.dentry, inode); file = alloc_file(&path, flags, fops); if (IS_ERR(file)) { ihold(inode); path_put(&path); } return file; } EXPORT_SYMBOL(alloc_file_pseudo); struct file *alloc_file_clone(struct file *base, int flags, const struct file_operations *fops) { struct file *f = alloc_file(&base->f_path, flags, fops); if (!IS_ERR(f)) { path_get(&f->f_path); f->f_mapping = base->f_mapping; } return f; } /* the real guts of fput() - releasing the last reference to file */ static void __fput(struct file *file) { struct dentry *dentry = file->f_path.dentry; struct vfsmount *mnt = file->f_path.mnt; struct inode *inode = file->f_inode; fmode_t mode = file->f_mode; if (unlikely(!(file->f_mode & FMODE_OPENED))) goto out; might_sleep(); fsnotify_close(file); /* * The function eventpoll_release() should be the first called * in the file cleanup chain. */ eventpoll_release(file); locks_remove_file(file); ima_file_free(file); if (unlikely(file->f_flags & FASYNC)) { if (file->f_op->fasync) file->f_op->fasync(-1, file, 0); } if (file->f_op->release) file->f_op->release(inode, file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL && !(mode & FMODE_PATH))) { cdev_put(inode->i_cdev); } fops_put(file->f_op); put_pid(file->f_owner.pid); if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_dec(inode); if (mode & FMODE_WRITER) { put_write_access(inode); __mnt_drop_write(mnt); } dput(dentry); if (unlikely(mode & FMODE_NEED_UNMOUNT)) dissolve_on_fput(mnt); mntput(mnt); out: file_free(file); } static LLIST_HEAD(delayed_fput_list); static void delayed_fput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_fput_list); struct file *f, *t; llist_for_each_entry_safe(f, t, node, f_u.fu_llist) __fput(f); } static void ____fput(struct callback_head *work) { __fput(container_of(work, struct file, f_u.fu_rcuhead)); } /* * If kernel thread really needs to have the final fput() it has done * to complete, call this. The only user right now is the boot - we * *do* need to make sure our writes to binaries on initramfs has * not left us with opened struct file waiting for __fput() - execve() * won't work without that. Please, don't add more callers without * very good reasons; in particular, never call that with locks * held and never call that from a thread that might need to do * some work on any kind of umount. */ void flush_delayed_fput(void) { delayed_fput(NULL); } EXPORT_SYMBOL_GPL(flush_delayed_fput); static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput); void fput_many(struct file *file, unsigned int refs) { if (atomic_long_sub_and_test(refs, &file->f_count)) { struct task_struct *task = current; if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) { init_task_work(&file->f_u.fu_rcuhead, ____fput); if (!task_work_add(task, &file->f_u.fu_rcuhead, TWA_RESUME)) return; /* * After this task has run exit_task_work(), * task_work_add() will fail. Fall through to delayed * fput to avoid leaking *file. */ } if (llist_add(&file->f_u.fu_llist, &delayed_fput_list)) schedule_delayed_work(&delayed_fput_work, 1); } } void fput(struct file *file) { fput_many(file, 1); } /* * synchronous analog of fput(); for kernel threads that might be needed * in some umount() (and thus can't use flush_delayed_fput() without * risking deadlocks), need to wait for completion of __fput() and know * for this specific struct file it won't involve anything that would * need them. Use only if you really need it - at the very least, * don't blindly convert fput() by kernel thread to that. */ void __fput_sync(struct file *file) { if (atomic_long_dec_and_test(&file->f_count)) { struct task_struct *task = current; BUG_ON(!(task->flags & PF_KTHREAD)); __fput(file); } } EXPORT_SYMBOL(fput); EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); percpu_counter_init(&nr_files, 0, GFP_KERNEL); } /* * One file with associated inode and dcache is very roughly 1K. Per default * do not use more than 10% of our memory for files. */ void __init files_maxfiles_init(void) { unsigned long n; unsigned long nr_pages = totalram_pages(); unsigned long memreserve = (nr_pages - nr_free_pages()) * 3/2; memreserve = min(memreserve, nr_pages - 1); n = ((nr_pages - memreserve) * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/backing-dev.h * * low-level device information and state which is propagated up through * to high-level code. */ #ifndef _LINUX_BACKING_DEV_H #define _LINUX_BACKING_DEV_H #include <linux/kernel.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/blkdev.h> #include <linux/device.h> #include <linux/writeback.h> #include <linux/blk-cgroup.h> #include <linux/backing-dev-defs.h> #include <linux/slab.h> static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); return bdi; } struct backing_dev_info *bdi_get_by_id(u64 id); void bdi_put(struct backing_dev_info *bdi); __printf(2, 3) int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...); __printf(2, 0) int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args); void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); struct backing_dev_info *bdi_alloc(int node_id); void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); void wb_wakeup_delayed(struct bdi_writeback *wb); void wb_wait_for_completion(struct wb_completion *done); extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; extern struct workqueue_struct *bdi_async_bio_wq; static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { return test_bit(WB_has_dirty_io, &wb->state); } static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) { /* * @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are * any dirty wbs. See wb_update_write_bandwidth(). */ return atomic_long_read(&bdi->tot_write_bandwidth); } static inline void __add_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item, s64 amount) { percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { __add_wb_stat(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { __add_wb_stat(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_read_positive(&wb->stat[item]); } static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_sum_positive(&wb->stat[item]); } extern void wb_writeout_inc(struct bdi_writeback *wb); /* * maximal error of a stat counter. */ static inline unsigned long wb_stat_error(void) { #ifdef CONFIG_SMP return nr_cpu_ids * WB_STAT_BATCH; #else return 1; #endif } int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio); int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); /* * Flags in backing_dev_info::capability * * BDI_CAP_WRITEBACK: Supports dirty page writeback, and dirty pages * should contribute to accounting * BDI_CAP_WRITEBACK_ACCT: Automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold */ #define BDI_CAP_WRITEBACK (1 << 0) #define BDI_CAP_WRITEBACK_ACCT (1 << 1) #define BDI_CAP_STRICTLIMIT (1 << 2) extern struct backing_dev_info noop_backing_dev_info; /** * writeback_in_progress - determine whether there is writeback in progress * @wb: bdi_writeback of interest * * Determine whether there is writeback waiting to be handled against a * bdi_writeback. */ static inline bool writeback_in_progress(struct bdi_writeback *wb) { return test_bit(WB_writeback_running, &wb->state); } static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) { struct super_block *sb; if (!inode) return &noop_backing_dev_info; sb = inode->i_sb; #ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) return I_BDEV(inode)->bd_bdi; #endif return sb->s_bdi; } static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) { return wb->congested & cong_bits; } long congestion_wait(int sync, long timeout); long wait_iff_congested(int sync, long timeout); static inline bool mapping_can_writeback(struct address_space *mapping) { return inode_to_bdi(mapping->host)->capabilities & BDI_CAP_WRITEBACK; } static inline int bdi_sched_wait(void *word) { schedule(); return 0; } #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css); struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); void wb_blkcg_offline(struct blkcg *blkcg); int inode_congested(struct inode *inode, int cong_bits); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode * @inode: inode of interest * * Cgroup writeback requires support from the filesystem. Also, both memcg and * iocg have to be on the default hierarchy. Test whether all conditions are * met. * * Note that the test result may change dynamically on the same inode * depending on how memcg and iocg are configured. */ static inline bool inode_cgwb_enabled(struct inode *inode) { struct backing_dev_info *bdi = inode_to_bdi(inode); return cgroup_subsys_on_dfl(memory_cgrp_subsys) && cgroup_subsys_on_dfl(io_cgrp_subsys) && (bdi->capabilities & BDI_CAP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } /** * wb_find_current - find wb for %current on a bdi * @bdi: bdi of interest * * Find the wb of @bdi which matches both the memcg and blkcg of %current. * Must be called under rcu_read_lock() which protects the returend wb. * NULL if not found. */ static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; memcg_css = task_css(current, memory_cgrp_id); if (!memcg_css->parent) return &bdi->wb; wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); /* * %current's blkcg equals the effective blkcg of its memcg. No * need to use the relatively expensive cgroup_get_e_css(). */ if (likely(wb && wb->blkcg_css == task_css(current, io_cgrp_id))) return wb; return NULL; } /** * wb_get_create_current - get or create wb for %current on a bdi * @bdi: bdi of interest * @gfp: allocation mask * * Equivalent to wb_get_create() on %current's memcg. This function is * called from a relatively hot path and optimizes the common cases using * wb_find_current(). */ static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { struct bdi_writeback *wb; rcu_read_lock(); wb = wb_find_current(bdi); if (wb && unlikely(!wb_tryget(wb))) wb = NULL; rcu_read_unlock(); if (unlikely(!wb)) { struct cgroup_subsys_state *memcg_css; memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, gfp); css_put(memcg_css); } return wb; } /** * inode_to_wb_is_valid - test whether an inode has a wb associated * @inode: inode of interest * * Returns %true if @inode has a wb associated. May be called without any * locking. */ static inline bool inode_to_wb_is_valid(struct inode *inode) { return inode->i_wb; } /** * inode_to_wb - determine the wb of an inode * @inode: inode of interest * * Returns the wb @inode is currently associated with. The caller must be * holding either @inode->i_lock, the i_pages lock, or the * associated wb's list_lock. */ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(debug_locks && (inode->i_sb->s_iflags & SB_I_CGROUPWB) && (!lockdep_is_held(&inode->i_lock) && !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) && !lockdep_is_held(&inode->i_wb->list_lock))); #endif return inode->i_wb; } /** * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction * @inode: target inode * @cookie: output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't * holding inode->i_lock, the i_pages lock or wb->list_lock. This * function determines the wb associated with @inode and ensures that the * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). * * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and * can't sleep during the transaction. IRQs may or may not be disabled on * return. */ static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { rcu_read_lock(); /* * Paired with store_release in inode_switch_wbs_work_fn() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; if (unlikely(cookie->locked)) xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); /* * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages * lock. inode_to_wb() will bark. Deref directly. */ return inode->i_wb; } /** * unlocked_inode_to_wb_end - end inode wb access transaction * @inode: target inode * @cookie: @cookie from unlocked_inode_to_wb_begin() */ static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { if (unlikely(cookie->locked)) xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags); rcu_read_unlock(); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool inode_cgwb_enabled(struct inode *inode) { return false; } static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { return &bdi->wb; } static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { return &bdi->wb; } static inline bool inode_to_wb_is_valid(struct inode *inode) { return true; } static inline struct bdi_writeback *inode_to_wb(struct inode *inode) { return &inode_to_bdi(inode)->wb; } static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { return inode_to_wb(inode); } static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { } static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } static inline void wb_blkcg_offline(struct blkcg *blkcg) { } static inline int inode_congested(struct inode *inode, int cong_bits) { return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); } #endif /* CONFIG_CGROUP_WRITEBACK */ static inline int inode_read_congested(struct inode *inode) { return inode_congested(inode, 1 << WB_sync_congested); } static inline int inode_write_congested(struct inode *inode) { return inode_congested(inode, 1 << WB_async_congested); } static inline int inode_rw_congested(struct inode *inode) { return inode_congested(inode, (1 << WB_sync_congested) | (1 << WB_async_congested)); } static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits) { return wb_congested(&bdi->wb, cong_bits); } static inline int bdi_read_congested(struct backing_dev_info *bdi) { return bdi_congested(bdi, 1 << WB_sync_congested); } static inline int bdi_write_congested(struct backing_dev_info *bdi) { return bdi_congested(bdi, 1 << WB_async_congested); } static inline int bdi_rw_congested(struct backing_dev_info *bdi) { return bdi_congested(bdi, (1 << WB_sync_congested) | (1 << WB_async_congested)); } const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM filemap #if !defined(_TRACE_FILEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FILEMAP_H #include <linux/types.h> #include <linux/tracepoint.h> #include <linux/mm.h> #include <linux/memcontrol.h> #include <linux/device.h> #include <linux/kdev_t.h> #include <linux/errseq.h> DECLARE_EVENT_CLASS(mm_filemap_op_page_cache, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field(unsigned long, pfn) __field(unsigned long, i_ino) __field(unsigned long, index) __field(dev_t, s_dev) ), TP_fast_assign( __entry->pfn = page_to_pfn(page); __entry->i_ino = page->mapping->host->i_ino; __entry->index = page->index; if (page->mapping->host->i_sb) __entry->s_dev = page->mapping->host->i_sb->s_dev; else __entry->s_dev = page->mapping->host->i_rdev; ), TP_printk("dev %d:%d ino %lx page=%p pfn=%lu ofs=%lu", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, pfn_to_page(__entry->pfn), __entry->pfn, __entry->index << PAGE_SHIFT) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_delete_from_page_cache, TP_PROTO(struct page *page), TP_ARGS(page) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_add_to_page_cache, TP_PROTO(struct page *page), TP_ARGS(page) ); TRACE_EVENT(filemap_set_wb_err, TP_PROTO(struct address_space *mapping, errseq_t eseq), TP_ARGS(mapping, eseq), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, errseq) ), TP_fast_assign( __entry->i_ino = mapping->host->i_ino; __entry->errseq = eseq; if (mapping->host->i_sb) __entry->s_dev = mapping->host->i_sb->s_dev; else __entry->s_dev = mapping->host->i_rdev; ), TP_printk("dev=%d:%d ino=0x%lx errseq=0x%x", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->errseq) ); TRACE_EVENT(file_check_and_advance_wb_err, TP_PROTO(struct file *file, errseq_t old), TP_ARGS(file, old), TP_STRUCT__entry( __field(struct file *, file) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, old) __field(errseq_t, new) ), TP_fast_assign( __entry->file = file; __entry->i_ino = file->f_mapping->host->i_ino; if (file->f_mapping->host->i_sb) __entry->s_dev = file->f_mapping->host->i_sb->s_dev; else __entry->s_dev = file->f_mapping->host->i_rdev; __entry->old = old; __entry->new = file->f_wb_err; ), TP_printk("file=%p dev=%d:%d ino=0x%lx old=0x%x new=0x%x", __entry->file, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->old, __entry->new) ); #endif /* _TRACE_FILEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_VSYSCALL_H #define _ASM_X86_VSYSCALL_H #include <linux/seqlock.h> #include <uapi/asm/vsyscall.h> #include <asm/page_types.h> #ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); extern void set_vsyscall_pgtable_user_bits(pgd_t *root); /* * Called on instruction fetch fault in vsyscall page. * Returns true if handled. */ extern bool emulate_vsyscall(unsigned long error_code, struct pt_regs *regs, unsigned long address); #else static inline void map_vsyscall(void) {} static inline bool emulate_vsyscall(unsigned long error_code, struct pt_regs *regs, unsigned long address) { return false; } #endif /* * The (legacy) vsyscall page is the long page in the kernel portion * of the address space that has user-accessible permissions. */ static inline bool is_vsyscall_vaddr(unsigned long vaddr) { return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); } #endif /* _ASM_X86_VSYSCALL_H */ |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/pagevec.h * * In many places it is efficient to batch an operation up against multiple * pages. A pagevec is a multipage container which is used for that. */ #ifndef _LINUX_PAGEVEC_H #define _LINUX_PAGEVEC_H #include <linux/xarray.h> /* 15 pointers + header align the pagevec structure to a power of two */ #define PAGEVEC_SIZE 15 struct page; struct address_space; struct pagevec { unsigned char nr; bool percpu_pvec_drained; struct page *pages[PAGEVEC_SIZE]; }; void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); unsigned pagevec_lookup_entries(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_entries, pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start, pgoff_t end); static inline unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start) { return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1); } unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag); unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned max_pages); static inline unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, xa_mark_t tag) { return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag); } static inline void pagevec_init(struct pagevec *pvec) { pvec->nr = 0; pvec->percpu_pvec_drained = false; } static inline void pagevec_reinit(struct pagevec *pvec) { pvec->nr = 0; } static inline unsigned pagevec_count(struct pagevec *pvec) { return pvec->nr; } static inline unsigned pagevec_space(struct pagevec *pvec) { return PAGEVEC_SIZE - pvec->nr; } /* * Add a page to a pagevec. Returns the number of slots still available. */ static inline unsigned pagevec_add(struct pagevec *pvec, struct page *page) { pvec->pages[pvec->nr++] = page; return pagevec_space(pvec); } static inline void pagevec_release(struct pagevec *pvec) { if (pagevec_count(pvec)) __pagevec_release(pvec); } #endif /* _LINUX_PAGEVEC_H */ |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/libfs.c * Library for filesystems writers. */ #include <linux/blkdev.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/mount.h> #include <linux/vfs.h> #include <linux/quotaops.h> #include <linux/mutex.h> #include <linux/namei.h> #include <linux/exportfs.h> #include <linux/writeback.h> #include <linux/buffer_head.h> /* sync_mapping_buffers */ #include <linux/fs_context.h> #include <linux/pseudo_fs.h> #include <linux/fsnotify.h> #include <linux/unicode.h> #include <linux/fscrypt.h> #include <linux/uaccess.h> #include "internal.h" int simple_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(inode, stat); stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9); return 0; } EXPORT_SYMBOL(simple_getattr); int simple_statfs(struct dentry *dentry, struct kstatfs *buf) { buf->f_type = dentry->d_sb->s_magic; buf->f_bsize = PAGE_SIZE; buf->f_namelen = NAME_MAX; return 0; } EXPORT_SYMBOL(simple_statfs); /* * Retaining negative dentries for an in-memory filesystem just wastes * memory and lookup time: arrange for them to be deleted immediately. */ int always_delete_dentry(const struct dentry *dentry) { return 1; } EXPORT_SYMBOL(always_delete_dentry); const struct dentry_operations simple_dentry_operations = { .d_delete = always_delete_dentry, }; EXPORT_SYMBOL(simple_dentry_operations); /* * Lookup the data. This is trivial - if the dentry didn't already * exist, we know it is negative. Set d_op to delete negative dentries. */ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); if (!dentry->d_sb->s_d_op) d_set_d_op(dentry, &simple_dentry_operations); d_add(dentry, NULL); return NULL; } EXPORT_SYMBOL(simple_lookup); int dcache_dir_open(struct inode *inode, struct file *file) { file->private_data = d_alloc_cursor(file->f_path.dentry); return file->private_data ? 0 : -ENOMEM; } EXPORT_SYMBOL(dcache_dir_open); int dcache_dir_close(struct inode *inode, struct file *file) { dput(file->private_data); return 0; } EXPORT_SYMBOL(dcache_dir_close); /* parent is locked at least shared */ /* * Returns an element of siblings' list. * We are looking for <count>th positive after <p>; if * found, dentry is grabbed and returned to caller. * If no such element exists, NULL is returned. */ static struct dentry *scan_positives(struct dentry *cursor, struct list_head *p, loff_t count, struct dentry *last) { struct dentry *dentry = cursor->d_parent, *found = NULL; spin_lock(&dentry->d_lock); while ((p = p->next) != &dentry->d_subdirs) { struct dentry *d = list_entry(p, struct dentry, d_child); // we must at least skip cursors, to avoid livelocks if (d->d_flags & DCACHE_DENTRY_CURSOR) continue; if (simple_positive(d) && !--count) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) found = dget_dlock(d); spin_unlock(&d->d_lock); if (likely(found)) break; count = 1; } if (need_resched()) { list_move(&cursor->d_child, p); p = &cursor->d_child; spin_unlock(&dentry->d_lock); cond_resched(); spin_lock(&dentry->d_lock); } } spin_unlock(&dentry->d_lock); dput(last); return found; } loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) { struct dentry *dentry = file->f_path.dentry; switch (whence) { case 1: offset += file->f_pos; fallthrough; case 0: if (offset >= 0) break; fallthrough; default: return -EINVAL; } if (offset != file->f_pos) { struct dentry *cursor = file->private_data; struct dentry *to = NULL; inode_lock_shared(dentry->d_inode); if (offset > 2) to = scan_positives(cursor, &dentry->d_subdirs, offset - 2, NULL); spin_lock(&dentry->d_lock); if (to) list_move(&cursor->d_child, &to->d_child); else list_del_init(&cursor->d_child); spin_unlock(&dentry->d_lock); dput(to); file->f_pos = offset; inode_unlock_shared(dentry->d_inode); } return offset; } EXPORT_SYMBOL(dcache_dir_lseek); /* Relationship between i_mode and the DT_xxx types */ static inline unsigned char dt_type(struct inode *inode) { return (inode->i_mode >> 12) & 15; } /* * Directory is locked and all positive dentries in it are safe, since * for ramfs-type trees they can't go away without unlink() or rmdir(), * both impossible due to the lock on directory. */ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; struct list_head *anchor = &dentry->d_subdirs; struct dentry *next = NULL; struct list_head *p; if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos == 2) p = anchor; else if (!list_empty(&cursor->d_child)) p = &cursor->d_child; else return 0; while ((next = scan_positives(cursor, p, 1, next)) != NULL) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, d_inode(next)->i_ino, dt_type(d_inode(next)))) break; ctx->pos++; p = &next->d_child; } spin_lock(&dentry->d_lock); if (next) list_move_tail(&cursor->d_child, &next->d_child); else list_del_init(&cursor->d_child); spin_unlock(&dentry->d_lock); dput(next); return 0; } EXPORT_SYMBOL(dcache_readdir); ssize_t generic_read_dir(struct file *filp, char __user *buf, size_t siz, loff_t *ppos) { return -EISDIR; } EXPORT_SYMBOL(generic_read_dir); const struct file_operations simple_dir_operations = { .open = dcache_dir_open, .release = dcache_dir_close, .llseek = dcache_dir_lseek, .read = generic_read_dir, .iterate_shared = dcache_readdir, .fsync = noop_fsync, }; EXPORT_SYMBOL(simple_dir_operations); const struct inode_operations simple_dir_inode_operations = { .lookup = simple_lookup, }; EXPORT_SYMBOL(simple_dir_inode_operations); static struct dentry *find_next_child(struct dentry *parent, struct dentry *prev) { struct dentry *child = NULL; struct list_head *p = prev ? &prev->d_child : &parent->d_subdirs; spin_lock(&parent->d_lock); while ((p = p->next) != &parent->d_subdirs) { struct dentry *d = container_of(p, struct dentry, d_child); if (simple_positive(d)) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) child = dget_dlock(d); spin_unlock(&d->d_lock); if (likely(child)) break; } } spin_unlock(&parent->d_lock); dput(prev); return child; } void simple_recursive_removal(struct dentry *dentry, void (*callback)(struct dentry *)) { struct dentry *this = dget(dentry); while (true) { struct dentry *victim = NULL, *child; struct inode *inode = this->d_inode; inode_lock_nested(inode, I_MUTEX_CHILD); if (d_is_dir(this)) inode->i_flags |= S_DEAD; while ((child = find_next_child(this, victim)) == NULL) { // kill and ascend // update metadata while it's still locked inode->i_ctime = current_time(inode); clear_nlink(inode); inode_unlock(inode); victim = this; this = this->d_parent; inode = this->d_inode; inode_lock_nested(inode, I_MUTEX_CHILD); if (simple_positive(victim)) { d_invalidate(victim); // avoid lost mounts if (d_is_dir(victim)) fsnotify_rmdir(inode, victim); else fsnotify_unlink(inode, victim); if (callback) callback(victim); dput(victim); // unpin it } if (victim == dentry) { inode->i_ctime = inode->i_mtime = current_time(inode); if (d_is_dir(dentry)) drop_nlink(inode); inode_unlock(inode); dput(dentry); return; } } inode_unlock(inode); this = child; } } EXPORT_SYMBOL(simple_recursive_removal); static const struct super_operations simple_super_operations = { .statfs = simple_statfs, }; static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc) { struct pseudo_fs_context *ctx = fc->fs_private; struct inode *root; s->s_maxbytes = MAX_LFS_FILESIZE; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = ctx->magic; s->s_op = ctx->ops ?: &simple_super_operations; s->s_xattr = ctx->xattr; s->s_time_gran = 1; root = new_inode(s); if (!root) return -ENOMEM; /* * since this is the first inode, make it number 1. New inodes created * after this must take care not to collide with it (by passing * max_reserved of 1 to iunique). */ root->i_ino = 1; root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR; root->i_atime = root->i_mtime = root->i_ctime = current_time(root); s->s_root = d_make_root(root); if (!s->s_root) return -ENOMEM; s->s_d_op = ctx->dops; return 0; } static int pseudo_fs_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, pseudo_fs_fill_super); } static void pseudo_fs_free(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations pseudo_fs_context_ops = { .free = pseudo_fs_free, .get_tree = pseudo_fs_get_tree, }; /* * Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that * will never be mountable) */ struct pseudo_fs_context *init_pseudo(struct fs_context *fc, unsigned long magic) { struct pseudo_fs_context *ctx; ctx = kzalloc(sizeof(struct pseudo_fs_context), GFP_KERNEL); if (likely(ctx)) { ctx->magic = magic; fc->fs_private = ctx; fc->ops = &pseudo_fs_context_ops; fc->sb_flags |= SB_NOUSER; fc->global = true; } return ctx; } EXPORT_SYMBOL(init_pseudo); int simple_open(struct inode *inode, struct file *file) { if (inode->i_private) file->private_data = inode->i_private; return 0; } EXPORT_SYMBOL(simple_open); int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode); inc_nlink(inode); ihold(inode); dget(dentry); d_instantiate(dentry, inode); return 0; } EXPORT_SYMBOL(simple_link); int simple_empty(struct dentry *dentry) { struct dentry *child; int ret = 0; spin_lock(&dentry->d_lock); list_for_each_entry(child, &dentry->d_subdirs, d_child) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { spin_unlock(&child->d_lock); goto out; } spin_unlock(&child->d_lock); } ret = 1; out: spin_unlock(&dentry->d_lock); return ret; } EXPORT_SYMBOL(simple_empty); int simple_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode); drop_nlink(inode); dput(dentry); return 0; } EXPORT_SYMBOL(simple_unlink); int simple_rmdir(struct inode *dir, struct dentry *dentry) { if (!simple_empty(dentry)) return -ENOTEMPTY; drop_nlink(d_inode(dentry)); simple_unlink(dir, dentry); drop_nlink(dir); return 0; } EXPORT_SYMBOL(simple_rmdir); int simple_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *inode = d_inode(old_dentry); int they_are_dirs = d_is_dir(old_dentry); if (flags & ~RENAME_NOREPLACE) return -EINVAL; if (!simple_empty(new_dentry)) return -ENOTEMPTY; if (d_really_is_positive(new_dentry)) { simple_unlink(new_dir, new_dentry); if (they_are_dirs) { drop_nlink(d_inode(new_dentry)); drop_nlink(old_dir); } } else if (they_are_dirs) { drop_nlink(old_dir); inc_nlink(new_dir); } old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime = new_dir->i_mtime = inode->i_ctime = current_time(old_dir); return 0; } EXPORT_SYMBOL(simple_rename); /** * simple_setattr - setattr for simple filesystem * @dentry: dentry * @iattr: iattr structure * * Returns 0 on success, -error on failure. * * simple_setattr is a simple ->setattr implementation without a proper * implementation of size changes. * * It can either be used for in-memory filesystems or special files * on simple regular filesystems. Anything that needs to change on-disk * or wire state on size changes needs its own setattr method. */ int simple_setattr(struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); int error; error = setattr_prepare(dentry, iattr); if (error) return error; if (iattr->ia_valid & ATTR_SIZE) truncate_setsize(inode, iattr->ia_size); setattr_copy(inode, iattr); mark_inode_dirty(inode); return 0; } EXPORT_SYMBOL(simple_setattr); int simple_readpage(struct file *file, struct page *page) { clear_highpage(page); flush_dcache_page(page); SetPageUptodate(page); unlock_page(page); return 0; } EXPORT_SYMBOL(simple_readpage); int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { struct page *page; pgoff_t index; index = pos >> PAGE_SHIFT; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; *pagep = page; if (!PageUptodate(page) && (len != PAGE_SIZE)) { unsigned from = pos & (PAGE_SIZE - 1); zero_user_segments(page, 0, from, from + len, PAGE_SIZE); } return 0; } EXPORT_SYMBOL(simple_write_begin); /** * simple_write_end - .write_end helper for non-block-device FSes * @file: See .write_end of address_space_operations * @mapping: " * @pos: " * @len: " * @copied: " * @page: " * @fsdata: " * * simple_write_end does the minimum needed for updating a page after writing is * done. It has the same API signature as the .write_end of * address_space_operations vector. So it can just be set onto .write_end for * FSes that don't need any other processing. i_mutex is assumed to be held. * Block based filesystems should use generic_write_end(). * NOTE: Even though i_size might get updated by this function, mark_inode_dirty * is not called, so a filesystem that actually does store data in .write_inode * should extend on what's done here with a call to mark_inode_dirty() in the * case that i_size has changed. * * Use *ONLY* with simple_readpage() */ int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = page->mapping->host; loff_t last_pos = pos + copied; /* zero the stale part of the page if we did a short copy */ if (!PageUptodate(page)) { if (copied < len) { unsigned from = pos & (PAGE_SIZE - 1); zero_user(page, from + copied, len - copied); } SetPageUptodate(page); } /* * No need to use i_size_read() here, the i_size * cannot change under us because we hold the i_mutex. */ if (last_pos > inode->i_size) i_size_write(inode, last_pos); set_page_dirty(page); unlock_page(page); put_page(page); return copied; } EXPORT_SYMBOL(simple_write_end); /* * the inodes created here are not hashed. If you use iunique to generate * unique inode values later for this filesystem, then you must take care * to pass it an appropriate max_reserved value to avoid collisions. */ int simple_fill_super(struct super_block *s, unsigned long magic, const struct tree_descr *files) { struct inode *inode; struct dentry *root; struct dentry *dentry; int i; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = magic; s->s_op = &simple_super_operations; s->s_time_gran = 1; inode = new_inode(s); if (!inode) return -ENOMEM; /* * because the root inode is 1, the files array must not contain an * entry at index 1 */ inode->i_ino = 1; inode->i_mode = S_IFDIR | 0755; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; set_nlink(inode, 2); root = d_make_root(inode); if (!root) return -ENOMEM; for (i = 0; !files->name || files->name[0]; i++, files++) { if (!files->name) continue; /* warn if it tries to conflict with the root inode */ if (unlikely(i == 1)) printk(KERN_WARNING "%s: %s passed in a files array" "with an index of 1!\n", __func__, s->s_type->name); dentry = d_alloc_name(root, files->name); if (!dentry) goto out; inode = new_inode(s); if (!inode) { dput(dentry); goto out; } inode->i_mode = S_IFREG | files->mode; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inode->i_fop = files->ops; inode->i_ino = i; d_add(dentry, inode); } s->s_root = root; return 0; out: d_genocide(root); shrink_dcache_parent(root); dput(root); return -ENOMEM; } EXPORT_SYMBOL(simple_fill_super); static DEFINE_SPINLOCK(pin_fs_lock); int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count) { struct vfsmount *mnt = NULL; spin_lock(&pin_fs_lock); if (unlikely(!*mount)) { spin_unlock(&pin_fs_lock); mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (IS_ERR(mnt)) return PTR_ERR(mnt); spin_lock(&pin_fs_lock); if (!*mount) *mount = mnt; } mntget(*mount); ++*count; spin_unlock(&pin_fs_lock); mntput(mnt); return 0; } EXPORT_SYMBOL(simple_pin_fs); void simple_release_fs(struct vfsmount **mount, int *count) { struct vfsmount *mnt; spin_lock(&pin_fs_lock); mnt = *mount; if (!--*count) *mount = NULL; spin_unlock(&pin_fs_lock); mntput(mnt); } EXPORT_SYMBOL(simple_release_fs); /** * simple_read_from_buffer - copy data from the buffer to user space * @to: the user space buffer to read to * @count: the maximum number of bytes to read * @ppos: the current position in the buffer * @from: the buffer to read from * @available: the size of the buffer * * The simple_read_from_buffer() function reads up to @count bytes from the * buffer @from at offset @ppos into the user space address starting at @to. * * On success, the number of bytes read is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available) { loff_t pos = *ppos; size_t ret; if (pos < 0) return -EINVAL; if (pos >= available || !count) return 0; if (count > available - pos) count = available - pos; ret = copy_to_user(to, from + pos, count); if (ret == count) return -EFAULT; count -= ret; *ppos = pos + count; return count; } EXPORT_SYMBOL(simple_read_from_buffer); /** * simple_write_to_buffer - copy data from user space to the buffer * @to: the buffer to write to * @available: the size of the buffer * @ppos: the current position in the buffer * @from: the user space buffer to read from * @count: the maximum number of bytes to read * * The simple_write_to_buffer() function reads up to @count bytes from the user * space address starting at @from into the buffer @to at offset @ppos. * * On success, the number of bytes written is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count) { loff_t pos = *ppos; size_t res; if (pos < 0) return -EINVAL; if (pos >= available || !count) return 0; if (count > available - pos) count = available - pos; res = copy_from_user(to + pos, from, count); if (res == count) return -EFAULT; count -= res; *ppos = pos + count; return count; } EXPORT_SYMBOL(simple_write_to_buffer); /** * memory_read_from_buffer - copy data from the buffer * @to: the kernel space buffer to read to * @count: the maximum number of bytes to read * @ppos: the current position in the buffer * @from: the buffer to read from * @available: the size of the buffer * * The memory_read_from_buffer() function reads up to @count bytes from the * buffer @from at offset @ppos into the kernel space address starting at @to. * * On success, the number of bytes read is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available) { loff_t pos = *ppos; if (pos < 0) return -EINVAL; if (pos >= available) return 0; if (count > available - pos) count = available - pos; memcpy(to, from + pos, count); *ppos = pos + count; return count; } EXPORT_SYMBOL(memory_read_from_buffer); /* * Transaction based IO. * The file expects a single write which triggers the transaction, and then * possibly a read which collects the result - which is stored in a * file-local buffer. */ void simple_transaction_set(struct file *file, size_t n) { struct simple_transaction_argresp *ar = file->private_data; BUG_ON(n > SIMPLE_TRANSACTION_LIMIT); /* * The barrier ensures that ar->size will really remain zero until * ar->data is ready for reading. */ smp_mb(); ar->size = n; } EXPORT_SYMBOL(simple_transaction_set); char *simple_transaction_get(struct file *file, const char __user *buf, size_t size) { struct simple_transaction_argresp *ar; static DEFINE_SPINLOCK(simple_transaction_lock); if (size > SIMPLE_TRANSACTION_LIMIT - 1) return ERR_PTR(-EFBIG); ar = (struct simple_transaction_argresp *)get_zeroed_page(GFP_KERNEL); if (!ar) return ERR_PTR(-ENOMEM); spin_lock(&simple_transaction_lock); /* only one write allowed per open */ if (file->private_data) { spin_unlock(&simple_transaction_lock); free_page((unsigned long)ar); return ERR_PTR(-EBUSY); } file->private_data = ar; spin_unlock(&simple_transaction_lock); if (copy_from_user(ar->data, buf, size)) return ERR_PTR(-EFAULT); return ar->data; } EXPORT_SYMBOL(simple_transaction_get); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos) { struct simple_transaction_argresp *ar = file->private_data; if (!ar) return 0; return simple_read_from_buffer(buf, size, pos, ar->data, ar->size); } EXPORT_SYMBOL(simple_transaction_read); int simple_transaction_release(struct inode *inode, struct file *file) { free_page((unsigned long)file->private_data); return 0; } EXPORT_SYMBOL(simple_transaction_release); /* Simple attribute files */ struct simple_attr { int (*get)(void *, u64 *); int (*set)(void *, u64); char get_buf[24]; /* enough to store a u64 and "\n\0" */ char set_buf[24]; void *data; const char *fmt; /* format for read operation */ struct mutex mutex; /* protects access to these buffers */ }; /* simple_attr_open is called by an actual attribute open file operation * to set the attribute specific access operations. */ int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt) { struct simple_attr *attr; attr = kzalloc(sizeof(*attr), GFP_KERNEL); if (!attr) return -ENOMEM; attr->get = get; attr->set = set; attr->data = inode->i_private; attr->fmt = fmt; mutex_init(&attr->mutex); file->private_data = attr; return nonseekable_open(inode, file); } EXPORT_SYMBOL_GPL(simple_attr_open); int simple_attr_release(struct inode *inode, struct file *file) { kfree(file->private_data); return 0; } EXPORT_SYMBOL_GPL(simple_attr_release); /* GPL-only? This? Really? */ /* read from the buffer that is filled with the get function */ ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { struct simple_attr *attr; size_t size; ssize_t ret; attr = file->private_data; if (!attr->get) return -EACCES; ret = mutex_lock_interruptible(&attr->mutex); if (ret) return ret; if (*ppos && attr->get_buf[0]) { /* continued read */ size = strlen(attr->get_buf); } else { /* first read */ u64 val; ret = attr->get(attr->data, &val); if (ret) goto out; size = scnprintf(attr->get_buf, sizeof(attr->get_buf), attr->fmt, (unsigned long long)val); } ret = simple_read_from_buffer(buf, len, ppos, attr->get_buf, size); out: mutex_unlock(&attr->mutex); return ret; } EXPORT_SYMBOL_GPL(simple_attr_read); /* interpret the buffer as a number to call the set function with */ static ssize_t simple_attr_write_xsigned(struct file *file, const char __user *buf, size_t len, loff_t *ppos, bool is_signed) { struct simple_attr *attr; unsigned long long val; size_t size; ssize_t ret; attr = file->private_data; if (!attr->set) return -EACCES; ret = mutex_lock_interruptible(&attr->mutex); if (ret) return ret; ret = -EFAULT; size = min(sizeof(attr->set_buf) - 1, len); if (copy_from_user(attr->set_buf, buf, size)) goto out; attr->set_buf[size] = '\0'; if (is_signed) ret = kstrtoll(attr->set_buf, 0, &val); else ret = kstrtoull(attr->set_buf, 0, &val); if (ret) goto out; ret = attr->set(attr->data, val); if (ret == 0) ret = len; /* on success, claim we got the whole input */ out: mutex_unlock(&attr->mutex); return ret; } ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return simple_attr_write_xsigned(file, buf, len, ppos, false); } EXPORT_SYMBOL_GPL(simple_attr_write); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return simple_attr_write_xsigned(file, buf, len, ppos, true); } EXPORT_SYMBOL_GPL(simple_attr_write_signed); /** * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation * @sb: filesystem to do the file handle conversion on * @fid: file handle to convert * @fh_len: length of the file handle in bytes * @fh_type: type of file handle * @get_inode: filesystem callback to retrieve inode * * This function decodes @fid as long as it has one of the well-known * Linux filehandle types and calls @get_inode on it to retrieve the * inode for the object specified in the file handle. */ struct dentry *generic_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)) { struct inode *inode = NULL; if (fh_len < 2) return NULL; switch (fh_type) { case FILEID_INO32_GEN: case FILEID_INO32_GEN_PARENT: inode = get_inode(sb, fid->i32.ino, fid->i32.gen); break; } return d_obtain_alias(inode); } EXPORT_SYMBOL_GPL(generic_fh_to_dentry); /** * generic_fh_to_parent - generic helper for the fh_to_parent export operation * @sb: filesystem to do the file handle conversion on * @fid: file handle to convert * @fh_len: length of the file handle in bytes * @fh_type: type of file handle * @get_inode: filesystem callback to retrieve inode * * This function decodes @fid as long as it has one of the well-known * Linux filehandle types and calls @get_inode on it to retrieve the * inode for the _parent_ object specified in the file handle if it * is specified in the file handle, or NULL otherwise. */ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)) { struct inode *inode = NULL; if (fh_len <= 2) return NULL; switch (fh_type) { case FILEID_INO32_GEN_PARENT: inode = get_inode(sb, fid->i32.parent_ino, (fh_len > 3 ? fid->i32.parent_gen : 0)); break; } return d_obtain_alias(inode); } EXPORT_SYMBOL_GPL(generic_fh_to_parent); /** * __generic_file_fsync - generic fsync implementation for simple filesystems * * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. */ int __generic_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; int err; int ret; err = file_write_and_wait_range(file, start, end); if (err) return err; inode_lock(inode); ret = sync_mapping_buffers(inode->i_mapping); if (!(inode->i_state & I_DIRTY_ALL)) goto out; if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) goto out; err = sync_inode_metadata(inode, 1); if (ret == 0) ret = err; out: inode_unlock(inode); /* check and advance again to catch errors after syncing out buffers */ err = file_check_and_advance_wb_err(file); if (ret == 0) ret = err; return ret; } EXPORT_SYMBOL(__generic_file_fsync); /** * generic_file_fsync - generic fsync implementation for simple filesystems * with flush * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * */ int generic_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; int err; err = __generic_file_fsync(file, start, end, datasync); if (err) return err; return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL); } EXPORT_SYMBOL(generic_file_fsync); /** * generic_check_addressable - Check addressability of file system * @blocksize_bits: log of file system block size * @num_blocks: number of blocks in file system * * Determine whether a file system with @num_blocks blocks (and a * block size of 2**@blocksize_bits) is addressable by the sector_t * and page cache of the system. Return 0 if so and -EFBIG otherwise. */ int generic_check_addressable(unsigned blocksize_bits, u64 num_blocks) { u64 last_fs_block = num_blocks - 1; u64 last_fs_page = last_fs_block >> (PAGE_SHIFT - blocksize_bits); if (unlikely(num_blocks == 0)) return 0; if ((blocksize_bits < 9) || (blocksize_bits > PAGE_SHIFT)) return -EINVAL; if ((last_fs_block > (sector_t)(~0ULL) >> (blocksize_bits - 9)) || (last_fs_page > (pgoff_t)(~0ULL))) { return -EFBIG; } return 0; } EXPORT_SYMBOL(generic_check_addressable); /* * No-op implementation of ->fsync for in-memory filesystems. */ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync) { return 0; } EXPORT_SYMBOL(noop_fsync); int noop_set_page_dirty(struct page *page) { /* * Unlike __set_page_dirty_no_writeback that handles dirty page * tracking in the page object, dax does all dirty tracking in * the inode address_space in response to mkwrite faults. In the * dax case we only need to worry about potentially dirty CPU * caches, not dirty page cache pages to write back. * * This callback is defined to prevent fallback to * __set_page_dirty_buffers() in set_page_dirty(). */ return 0; } EXPORT_SYMBOL_GPL(noop_set_page_dirty); void noop_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { /* * There is no page cache to invalidate in the dax case, however * we need this callback defined to prevent falling back to * block_invalidatepage() in do_invalidatepage(). */ } EXPORT_SYMBOL_GPL(noop_invalidatepage); ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { /* * iomap based filesystems support direct I/O without need for * this callback. However, it still needs to be set in * inode->a_ops so that open/fcntl know that direct I/O is * generally supported. */ return -EINVAL; } EXPORT_SYMBOL_GPL(noop_direct_IO); /* Because kfree isn't assignment-compatible with void(void*) ;-/ */ void kfree_link(void *p) { kfree(p); } EXPORT_SYMBOL(kfree_link); /* * nop .set_page_dirty method so that people can use .page_mkwrite on * anon inodes. */ static int anon_set_page_dirty(struct page *page) { return 0; }; /* * A single inode exists for all anon_inode files. Contrary to pipes, * anon_inode inodes have no associated per-instance data, so we need * only allocate one of them. */ struct inode *alloc_anon_inode(struct super_block *s) { static const struct address_space_operations anon_aops = { .set_page_dirty = anon_set_page_dirty, }; struct inode *inode = new_inode_pseudo(s); if (!inode) return ERR_PTR(-ENOMEM); inode->i_ino = get_next_ino(); inode->i_mapping->a_ops = &anon_aops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because mark_inode_dirty() will think * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; inode->i_mode = S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_flags |= S_PRIVATE; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); return inode; } EXPORT_SYMBOL(alloc_anon_inode); /** * simple_nosetlease - generic helper for prohibiting leases * @filp: file pointer * @arg: type of lease to obtain * @flp: new lease supplied for insertion * @priv: private data for lm_setup operation * * Generic helper for filesystems that do not wish to allow leases to be set. * All arguments are ignored and it just returns -EINVAL. */ int simple_nosetlease(struct file *filp, long arg, struct file_lock **flp, void **priv) { return -EINVAL; } EXPORT_SYMBOL(simple_nosetlease); /** * simple_get_link - generic helper to get the target of "fast" symlinks * @dentry: not used here * @inode: the symlink inode * @done: not used here * * Generic helper for filesystems to use for symlink inodes where a pointer to * the symlink target is stored in ->i_link. NOTE: this isn't normally called, * since as an optimization the path lookup code uses any non-NULL ->i_link * directly, without calling ->get_link(). But ->get_link() still must be set, * to mark the inode_operations as being for a symlink. * * Return: the symlink target */ const char *simple_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { return inode->i_link; } EXPORT_SYMBOL(simple_get_link); const struct inode_operations simple_symlink_inode_operations = { .get_link = simple_get_link, }; EXPORT_SYMBOL(simple_symlink_inode_operations); /* * Operations for a permanently empty directory. */ static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return ERR_PTR(-ENOENT); } static int empty_dir_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(inode, stat); return 0; } static int empty_dir_setattr(struct dentry *dentry, struct iattr *attr) { return -EPERM; } static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t size) { return -EOPNOTSUPP; } static const struct inode_operations empty_dir_inode_operations = { .lookup = empty_dir_lookup, .permission = generic_permission, .setattr = empty_dir_setattr, .getattr = empty_dir_getattr, .listxattr = empty_dir_listxattr, }; static loff_t empty_dir_llseek(struct file *file, loff_t offset, int whence) { /* An empty directory has two entries . and .. at offsets 0 and 1 */ return generic_file_llseek_size(file, offset, whence, 2, 2); } static int empty_dir_readdir(struct file *file, struct dir_context *ctx) { dir_emit_dots(file, ctx); return 0; } static const struct file_operations empty_dir_operations = { .llseek = empty_dir_llseek, .read = generic_read_dir, .iterate_shared = empty_dir_readdir, .fsync = noop_fsync, }; void make_empty_dir_inode(struct inode *inode) { set_nlink(inode, 2); inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_rdev = 0; inode->i_size = 0; inode->i_blkbits = PAGE_SHIFT; inode->i_blocks = 0; inode->i_op = &empty_dir_inode_operations; inode->i_opflags &= ~IOP_XATTR; inode->i_fop = &empty_dir_operations; } bool is_empty_dir_inode(struct inode *inode) { return (inode->i_fop == &empty_dir_operations) && (inode->i_op == &empty_dir_inode_operations); } #ifdef CONFIG_UNICODE /* * Determine if the name of a dentry should be casefolded. * * Return: if names will need casefolding */ static bool needs_casefold(const struct inode *dir) { return IS_CASEFOLDED(dir) && dir->i_sb->s_encoding; } /** * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems * @dentry: dentry whose name we are checking against * @len: len of name of dentry * @str: str pointer to name of dentry * @name: Name to compare against * * Return: 0 if names match, 1 if mismatch, or -ERRNO */ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { const struct dentry *parent = READ_ONCE(dentry->d_parent); const struct inode *dir = READ_ONCE(parent->d_inode); const struct super_block *sb = dentry->d_sb; const struct unicode_map *um = sb->s_encoding; struct qstr qstr = QSTR_INIT(str, len); char strbuf[DNAME_INLINE_LEN]; int ret; if (!dir || !needs_casefold(dir)) goto fallback; /* * If the dentry name is stored in-line, then it may be concurrently * modified by a rename. If this happens, the VFS will eventually retry * the lookup, so it doesn't matter what ->d_compare() returns. * However, it's unsafe to call utf8_strncasecmp() with an unstable * string. Therefore, we have to copy the name into a temporary buffer. */ if (len <= DNAME_INLINE_LEN - 1) { memcpy(strbuf, str, len); strbuf[len] = 0; qstr.name = strbuf; /* prevent compiler from optimizing out the temporary buffer */ barrier(); } ret = utf8_strncasecmp(um, name, &qstr); if (ret >= 0) return ret; if (sb_has_strict_encoding(sb)) return -EINVAL; fallback: if (len != name->len) return 1; return !!memcmp(str, name->name, len); } EXPORT_SYMBOL(generic_ci_d_compare); /** * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems * @dentry: dentry of the parent directory * @str: qstr of name whose hash we should fill in * * Return: 0 if hash was successful or unchanged, and -EINVAL on error */ int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str) { const struct inode *dir = READ_ONCE(dentry->d_inode); struct super_block *sb = dentry->d_sb; const struct unicode_map *um = sb->s_encoding; int ret = 0; if (!dir || !needs_casefold(dir)) return 0; ret = utf8_casefold_hash(um, dentry, str); if (ret < 0 && sb_has_strict_encoding(sb)) return -EINVAL; return 0; } EXPORT_SYMBOL(generic_ci_d_hash); #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2008 IBM Corporation * * Authors: * Mimi Zohar <zohar@us.ibm.com> * * File: integrity_iint.c * - implements the integrity hooks: integrity_inode_alloc, * integrity_inode_free * - cache integrity information associated with an inode * using a rbtree tree. */ #include <linux/slab.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/rbtree.h> #include <linux/file.h> #include <linux/uaccess.h> #include <linux/security.h> #include <linux/lsm_hooks.h> #include "integrity.h" static struct rb_root integrity_iint_tree = RB_ROOT; static DEFINE_RWLOCK(integrity_iint_lock); static struct kmem_cache *iint_cache __read_mostly; struct dentry *integrity_dir; /* * __integrity_iint_find - return the iint associated with an inode */ static struct integrity_iint_cache *__integrity_iint_find(struct inode *inode) { struct integrity_iint_cache *iint; struct rb_node *n = integrity_iint_tree.rb_node; while (n) { iint = rb_entry(n, struct integrity_iint_cache, rb_node); if (inode < iint->inode) n = n->rb_left; else if (inode > iint->inode) n = n->rb_right; else return iint; } return NULL; } /* * integrity_iint_find - return the iint associated with an inode */ struct integrity_iint_cache *integrity_iint_find(struct inode *inode) { struct integrity_iint_cache *iint; if (!IS_IMA(inode)) return NULL; read_lock(&integrity_iint_lock); iint = __integrity_iint_find(inode); read_unlock(&integrity_iint_lock); return iint; } #define IMA_MAX_NESTING (FILESYSTEM_MAX_STACK_DEPTH+1) /* * It is not clear that IMA should be nested at all, but as long is it measures * files both on overlayfs and on underlying fs, we need to annotate the iint * mutex to avoid lockdep false positives related to IMA + overlayfs. * See ovl_lockdep_annotate_inode_mutex_key() for more details. */ static inline void iint_lockdep_annotate(struct integrity_iint_cache *iint, struct inode *inode) { #ifdef CONFIG_LOCKDEP static struct lock_class_key iint_mutex_key[IMA_MAX_NESTING]; int depth = inode->i_sb->s_stack_depth; if (WARN_ON_ONCE(depth < 0 || depth >= IMA_MAX_NESTING)) depth = 0; lockdep_set_class(&iint->mutex, &iint_mutex_key[depth]); #endif } static void iint_init_always(struct integrity_iint_cache *iint, struct inode *inode) { iint->ima_hash = NULL; iint->version = 0; iint->flags = 0UL; iint->atomic_flags = 0UL; iint->ima_file_status = INTEGRITY_UNKNOWN; iint->ima_mmap_status = INTEGRITY_UNKNOWN; iint->ima_bprm_status = INTEGRITY_UNKNOWN; iint->ima_read_status = INTEGRITY_UNKNOWN; iint->ima_creds_status = INTEGRITY_UNKNOWN; iint->evm_status = INTEGRITY_UNKNOWN; iint->measured_pcrs = 0; mutex_init(&iint->mutex); iint_lockdep_annotate(iint, inode); } static void iint_free(struct integrity_iint_cache *iint) { kfree(iint->ima_hash); mutex_destroy(&iint->mutex); kmem_cache_free(iint_cache, iint); } /** * integrity_inode_get - find or allocate an iint associated with an inode * @inode: pointer to the inode * @return: allocated iint * * Caller must lock i_mutex */ struct integrity_iint_cache *integrity_inode_get(struct inode *inode) { struct rb_node **p; struct rb_node *node, *parent = NULL; struct integrity_iint_cache *iint, *test_iint; /* * The integrity's "iint_cache" is initialized at security_init(), * unless it is not included in the ordered list of LSMs enabled * on the boot command line. */ if (!iint_cache) panic("%s: lsm=integrity required.\n", __func__); iint = integrity_iint_find(inode); if (iint) return iint; iint = kmem_cache_alloc(iint_cache, GFP_NOFS); if (!iint) return NULL; iint_init_always(iint, inode); write_lock(&integrity_iint_lock); p = &integrity_iint_tree.rb_node; while (*p) { parent = *p; test_iint = rb_entry(parent, struct integrity_iint_cache, rb_node); if (inode < test_iint->inode) { p = &(*p)->rb_left; } else if (inode > test_iint->inode) { p = &(*p)->rb_right; } else { write_unlock(&integrity_iint_lock); kmem_cache_free(iint_cache, iint); return test_iint; } } iint->inode = inode; node = &iint->rb_node; inode->i_flags |= S_IMA; rb_link_node(node, parent, p); rb_insert_color(node, &integrity_iint_tree); write_unlock(&integrity_iint_lock); return iint; } /** * integrity_inode_free - called on security_inode_free * @inode: pointer to the inode * * Free the integrity information(iint) associated with an inode. */ void integrity_inode_free(struct inode *inode) { struct integrity_iint_cache *iint; if (!IS_IMA(inode)) return; write_lock(&integrity_iint_lock); iint = __integrity_iint_find(inode); rb_erase(&iint->rb_node, &integrity_iint_tree); write_unlock(&integrity_iint_lock); iint_free(iint); } static void iint_init_once(void *foo) { struct integrity_iint_cache *iint = foo; memset(iint, 0, sizeof(*iint)); } static int __init integrity_iintcache_init(void) { iint_cache = kmem_cache_create("iint_cache", sizeof(struct integrity_iint_cache), 0, SLAB_PANIC, iint_init_once); return 0; } DEFINE_LSM(integrity) = { .name = "integrity", .init = integrity_iintcache_init, }; /* * integrity_kernel_read - read data from the file * * This is a function for reading file content instead of kernel_read(). * It does not perform locking checks to ensure it cannot be blocked. * It does not perform security checks because it is irrelevant for IMA. * */ int integrity_kernel_read(struct file *file, loff_t offset, void *addr, unsigned long count) { return __kernel_read(file, addr, count, &offset); } /* * integrity_load_keys - load integrity keys hook * * Hooks is called from init/main.c:kernel_init_freeable() * when rootfs is ready */ void __init integrity_load_keys(void) { ima_load_x509(); evm_load_x509(); } static int __init integrity_fs_init(void) { integrity_dir = securityfs_create_dir("integrity", NULL); if (IS_ERR(integrity_dir)) { int ret = PTR_ERR(integrity_dir); if (ret != -ENODEV) pr_err("Unable to create integrity sysfs dir: %d\n", ret); integrity_dir = NULL; return ret; } return 0; } late_initcall(integrity_fs_init) |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #include <linux/dcache.h> #include <linux/fs.h> #include <linux/gfp.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mount.h> #include <linux/srcu.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" /* * Clear all of the marks on an inode when it is being evicted from core */ void __fsnotify_inode_delete(struct inode *inode) { fsnotify_clear_marks_by_inode(inode); } EXPORT_SYMBOL_GPL(__fsnotify_inode_delete); void __fsnotify_vfsmount_delete(struct vfsmount *mnt) { fsnotify_clear_marks_by_mount(mnt); } /** * fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes. * @sb: superblock being unmounted. * * Called during unmount with no locks held, so needs to be safe against * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block. */ static void fsnotify_unmount_inodes(struct super_block *sb) { struct inode *inode, *iput_inode = NULL; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { /* * We cannot __iget() an inode in state I_FREEING, * I_WILL_FREE, or I_NEW which is fine because by that point * the inode cannot have any associated watches. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); continue; } /* * If i_count is zero, the inode cannot have any watches and * doing an __iget/iput with SB_ACTIVE clear would actually * evict all inodes with zero i_count from icache which is * unnecessarily violent and may in fact be illegal to do. * However, we should have been called /after/ evict_inodes * removed all zero refcount inodes, in any case. Test to * be sure. */ if (!atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); iput(iput_inode); /* for each watch, send FS_UNMOUNT and then remove it */ fsnotify_inode(inode, FS_UNMOUNT); fsnotify_inode_delete(inode); iput_inode = inode; cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); iput(iput_inode); } void fsnotify_sb_delete(struct super_block *sb) { fsnotify_unmount_inodes(sb); fsnotify_clear_marks_by_sb(sb); /* Wait for outstanding object references from connectors */ wait_var_event(&sb->s_fsnotify_connectors, !atomic_long_read(&sb->s_fsnotify_connectors)); } /* * Given an inode, first check if we care what happens to our children. Inotify * and dnotify both tell their parents about events. If we care about any event * on a child we run all of our children and set a dentry flag saying that the * parent cares. Thus when an event happens on a child it can quickly tell * if there is a need to find a parent and send the event to the parent. */ void fsnotify_set_children_dentry_flags(struct inode *inode) { struct dentry *alias; if (!S_ISDIR(inode->i_mode)) return; spin_lock(&inode->i_lock); /* run all of the dentries associated with this inode. Since this is a * directory, there damn well better only be one item on this list */ hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { struct dentry *child; /* run all of the children of the original inode and fix their * d_flags to indicate parental interest (their parent is the * original inode) */ spin_lock(&alias->d_lock); list_for_each_entry(child, &alias->d_subdirs, d_child) { if (!child->d_inode) continue; spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&child->d_lock); } spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); } /* * Lazily clear false positive PARENT_WATCHED flag for child whose parent had * stopped watching children. */ static void fsnotify_clear_child_dentry_flag(struct inode *pinode, struct dentry *dentry) { spin_lock(&dentry->d_lock); /* * d_lock is a sufficient barrier to prevent observing a non-watched * parent state from before the fsnotify_set_children_dentry_flags() * or fsnotify_update_flags() call that had set PARENT_WATCHED. */ if (!fsnotify_inode_watches_children(pinode)) dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; spin_unlock(&dentry->d_lock); } /* Are inode/sb/mount interested in parent and name info with this event? */ static bool fsnotify_event_needs_parent(struct inode *inode, struct mount *mnt, __u32 mask) { __u32 marks_mask = 0; /* We only send parent/name to inode/sb/mount for events on non-dir */ if (mask & FS_ISDIR) return false; /* * All events that are possible on child can also may be reported with * parent/name info to inode/sb/mount. Otherwise, a watching parent * could result in events reported with unexpected name info to sb/mount. */ BUILD_BUG_ON(FS_EVENTS_POSS_ON_CHILD & ~FS_EVENTS_POSS_TO_PARENT); /* Did either inode/sb/mount subscribe for events with parent/name? */ marks_mask |= fsnotify_parent_needed_mask(inode->i_fsnotify_mask); marks_mask |= fsnotify_parent_needed_mask(inode->i_sb->s_fsnotify_mask); if (mnt) marks_mask |= fsnotify_parent_needed_mask(mnt->mnt_fsnotify_mask); /* Did they subscribe for this event with parent/name info? */ return mask & marks_mask; } /* * Notify this dentry's parent about a child's events with child name info * if parent is watching or if inode/sb/mount are interested in events with * parent and name info. * * Notify only the child without name info if parent is not watching and * inode/sb/mount are not interested in events with parent and name info. */ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { const struct path *path = fsnotify_data_path(data, data_type); struct mount *mnt = path ? real_mount(path->mnt) : NULL; struct inode *inode = d_inode(dentry); struct dentry *parent; bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED; bool parent_needed, parent_interested; __u32 p_mask; struct inode *p_inode = NULL; struct name_snapshot name; struct qstr *file_name = NULL; int ret = 0; /* * Do inode/sb/mount care about parent and name info on non-dir? * Do they care about any event at all? */ if (!inode->i_fsnotify_marks && !inode->i_sb->s_fsnotify_marks && (!mnt || !mnt->mnt_fsnotify_marks) && !parent_watched) return 0; parent = NULL; parent_needed = fsnotify_event_needs_parent(inode, mnt, mask); if (!parent_watched && !parent_needed) goto notify; /* Does parent inode care about events on children? */ parent = dget_parent(dentry); p_inode = parent->d_inode; p_mask = fsnotify_inode_watches_children(p_inode); if (unlikely(parent_watched && !p_mask)) fsnotify_clear_child_dentry_flag(p_inode, dentry); /* * Include parent/name in notification either if some notification * groups require parent info or the parent is interested in this event. */ parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS; if (parent_needed || parent_interested) { /* When notifying parent, child should be passed as data */ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type)); /* Notify both parent and child with child name info */ take_dentry_name_snapshot(&name, dentry); file_name = &name.name; if (parent_interested) mask |= FS_EVENT_ON_CHILD; } notify: ret = fsnotify(mask, data, data_type, p_inode, file_name, inode, 0); if (file_name) release_dentry_name_snapshot(&name); dput(parent); return ret; } EXPORT_SYMBOL_GPL(__fsnotify_parent); static int fsnotify_handle_inode_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); struct inode *inode = fsnotify_data_inode(data, data_type); const struct fsnotify_ops *ops = group->ops; if (WARN_ON_ONCE(!ops->handle_inode_event)) return 0; if (WARN_ON_ONCE(!inode && !dir)) return 0; if ((inode_mark->flags & FSNOTIFY_MARK_FLAG_EXCL_UNLINK) && path && d_unlinked(path->dentry)) return 0; /* Check interest of this mark in case event was sent with two marks */ if (!(mask & inode_mark->mask & ALL_FSNOTIFY_EVENTS)) return 0; return ops->handle_inode_event(inode_mark, mask, inode, dir, name, cookie); } static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info); struct fsnotify_mark *parent_mark = fsnotify_iter_parent_mark(iter_info); int ret; if (WARN_ON_ONCE(fsnotify_iter_sb_mark(iter_info)) || WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info))) return 0; /* * For FS_RENAME, 'dir' is old dir and 'data' is new dentry. * The only ->handle_inode_event() backend that supports FS_RENAME is * dnotify, where it means file was renamed within same parent. */ if (mask & FS_RENAME) { struct dentry *moved = fsnotify_data_dentry(data, data_type); if (dir != moved->d_parent->d_inode) return 0; } if (parent_mark) { ret = fsnotify_handle_inode_event(group, parent_mark, mask, data, data_type, dir, name, 0); if (ret) return ret; } if (!inode_mark) return 0; /* * Some events can be sent on both parent dir and child marks (e.g. * FS_ATTRIB). If both parent dir and child are watching, report the * event once to parent dir with name (if interested) and once to child * without name (if interested). * * In any case regardless whether the parent is watching or not, the * child watcher is expecting an event without the FS_EVENT_ON_CHILD * flag. The file name is expected if and only if this is a directory * event. */ mask &= ~FS_EVENT_ON_CHILD; if (!(mask & ALL_FSNOTIFY_DIRENT_EVENTS)) { dir = NULL; name = NULL; } return fsnotify_handle_inode_event(group, inode_mark, mask, data, data_type, dir, name, cookie); } static int send_to_group(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info) { struct fsnotify_group *group = NULL; __u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS); __u32 marks_mask = 0; __u32 marks_ignore_mask = 0; bool is_dir = mask & FS_ISDIR; struct fsnotify_mark *mark; int type; if (!iter_info->report_mask) return 0; /* clear ignored on inode modification */ if (mask & FS_MODIFY) { fsnotify_foreach_iter_mark_type(iter_info, mark, type) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) mark->ignore_mask = 0; } } /* Are any of the group marks interested in this event? */ fsnotify_foreach_iter_mark_type(iter_info, mark, type) { group = mark->group; marks_mask |= mark->mask; marks_ignore_mask |= fsnotify_effective_ignore_mask(mark, is_dir, type); } pr_debug("%s: group=%p mask=%x marks_mask=%x marks_ignore_mask=%x data=%p data_type=%d dir=%p cookie=%d\n", __func__, group, mask, marks_mask, marks_ignore_mask, data, data_type, dir, cookie); if (!(test_mask & marks_mask & ~marks_ignore_mask)) return 0; if (group->ops->handle_event) { return group->ops->handle_event(group, mask, data, data_type, dir, file_name, cookie, iter_info); } return fsnotify_handle_event(group, mask, data, data_type, dir, file_name, cookie, iter_info); } static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector **connp) { struct fsnotify_mark_connector *conn; struct hlist_node *node = NULL; conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (conn) node = srcu_dereference(conn->list.first, &fsnotify_mark_srcu); return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } static struct fsnotify_mark *fsnotify_next_mark(struct fsnotify_mark *mark) { struct hlist_node *node = NULL; if (mark) node = srcu_dereference(mark->obj_list.next, &fsnotify_mark_srcu); return hlist_entry_safe(node, struct fsnotify_mark, obj_list); } /* * iter_info is a multi head priority queue of marks. * Pick a subset of marks from queue heads, all with the same group * and set the report_mask to a subset of the selected marks. * Returns false if there are no more groups to iterate. */ static bool fsnotify_iter_select_report_types( struct fsnotify_iter_info *iter_info) { struct fsnotify_group *max_prio_group = NULL; struct fsnotify_mark *mark; int type; /* Choose max prio group among groups of all queue heads */ fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && fsnotify_compare_groups(max_prio_group, mark->group) > 0) max_prio_group = mark->group; } if (!max_prio_group) return false; /* Set the report mask for marks from same group as max prio group */ iter_info->current_group = max_prio_group; iter_info->report_mask = 0; fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && mark->group == iter_info->current_group) { /* * FSNOTIFY_ITER_TYPE_PARENT indicates that this inode * is watching children and interested in this event, * which is an event possible on child. * But is *this mark* watching children? */ if (type == FSNOTIFY_ITER_TYPE_PARENT && !(mark->mask & FS_EVENT_ON_CHILD) && !(fsnotify_ignore_mask(mark) & FS_EVENT_ON_CHILD)) continue; fsnotify_iter_set_report_type(iter_info, type); } } return true; } /* * Pop from iter_info multi head queue, the marks that belong to the group of * current iteration step. */ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info) { struct fsnotify_mark *mark; int type; /* * We cannot use fsnotify_foreach_iter_mark_type() here because we * may need to advance a mark of type X that belongs to current_group * but was not selected for reporting. */ fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && mark->group == iter_info->current_group) iter_info->marks[type] = fsnotify_next_mark(iter_info->marks[type]); } } /* * fsnotify - This is the main call to fsnotify. * * The VFS calls into hook specific functions in linux/fsnotify.h. * Those functions then in turn call here. Here will call out to all of the * registered fsnotify_group. Those groups can then use the notification event * in whatever means they feel necessary. * * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @inode: optional inode associated with event - * If @dir and @inode are both non-NULL, event may be * reported to both. * @cookie: inotify rename cookie */ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, struct inode *inode, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); struct super_block *sb = fsnotify_data_sb(data, data_type); struct fsnotify_iter_info iter_info = {}; struct mount *mnt = NULL; struct inode *inode2 = NULL; struct dentry *moved; int inode2_type; int ret = 0; __u32 test_mask, marks_mask; if (path) mnt = real_mount(path->mnt); if (!inode) { /* Dirent event - report on TYPE_INODE to dir */ inode = dir; /* For FS_RENAME, inode is old_dir and inode2 is new_dir */ if (mask & FS_RENAME) { moved = fsnotify_data_dentry(data, data_type); inode2 = moved->d_parent->d_inode; inode2_type = FSNOTIFY_ITER_TYPE_INODE2; } } else if (mask & FS_EVENT_ON_CHILD) { /* * Event on child - report on TYPE_PARENT to dir if it is * watching children and on TYPE_INODE to child. */ inode2 = dir; inode2_type = FSNOTIFY_ITER_TYPE_PARENT; } /* * Optimization: srcu_read_lock() has a memory barrier which can * be expensive. It protects walking the *_fsnotify_marks lists. * However, if we do not walk the lists, we do not have to do * SRCU because we have no references to any objects and do not * need SRCU to keep them "alive". */ if (!sb->s_fsnotify_marks && (!mnt || !mnt->mnt_fsnotify_marks) && (!inode || !inode->i_fsnotify_marks) && (!inode2 || !inode2->i_fsnotify_marks)) return 0; marks_mask = sb->s_fsnotify_mask; if (mnt) marks_mask |= mnt->mnt_fsnotify_mask; if (inode) marks_mask |= inode->i_fsnotify_mask; if (inode2) marks_mask |= inode2->i_fsnotify_mask; /* * If this is a modify event we may need to clear some ignore masks. * In that case, the object with ignore masks will have the FS_MODIFY * event in its mask. * Otherwise, return if none of the marks care about this type of event. */ test_mask = (mask & ALL_FSNOTIFY_EVENTS); if (!(test_mask & marks_mask)) return 0; iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); iter_info.marks[FSNOTIFY_ITER_TYPE_SB] = fsnotify_first_mark(&sb->s_fsnotify_marks); if (mnt) { iter_info.marks[FSNOTIFY_ITER_TYPE_VFSMOUNT] = fsnotify_first_mark(&mnt->mnt_fsnotify_marks); } if (inode) { iter_info.marks[FSNOTIFY_ITER_TYPE_INODE] = fsnotify_first_mark(&inode->i_fsnotify_marks); } if (inode2) { iter_info.marks[inode2_type] = fsnotify_first_mark(&inode2->i_fsnotify_marks); } /* * We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark * ignore masks are properly reflected for mount/sb mark notifications. * That's why this traversal is so complicated... */ while (fsnotify_iter_select_report_types(&iter_info)) { ret = send_to_group(mask, data, data_type, dir, file_name, cookie, &iter_info); if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS)) goto out; fsnotify_iter_next(&iter_info); } ret = 0; out: srcu_read_unlock(&fsnotify_mark_srcu, iter_info.srcu_idx); return ret; } EXPORT_SYMBOL_GPL(fsnotify); static __init int fsnotify_init(void) { int ret; BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 23); ret = init_srcu_struct(&fsnotify_mark_srcu); if (ret) panic("initializing fsnotify_mark_srcu"); fsnotify_mark_connector_cachep = KMEM_CACHE(fsnotify_mark_connector, SLAB_PANIC); return 0; } core_initcall(fsnotify_init); |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Sleepable Read-Copy Update mechanism for mutual exclusion * * Copyright (C) IBM Corporation, 2006 * Copyright (C) Fujitsu, 2012 * * Author: Paul McKenney <paulmck@linux.ibm.com> * Lai Jiangshan <laijs@cn.fujitsu.com> * * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU/ *.txt * */ #ifndef _LINUX_SRCU_H #define _LINUX_SRCU_H #include <linux/mutex.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/rcu_segcblist.h> struct srcu_struct; #ifdef CONFIG_DEBUG_LOCK_ALLOC int __init_srcu_struct(struct srcu_struct *ssp, const char *name, struct lock_class_key *key); #define init_srcu_struct(ssp) \ ({ \ static struct lock_class_key __srcu_key; \ \ __init_srcu_struct((ssp), #ssp, &__srcu_key); \ }) #define __SRCU_DEP_MAP_INIT(srcu_name) .dep_map = { .name = #srcu_name }, #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ int init_srcu_struct(struct srcu_struct *ssp); #define __SRCU_DEP_MAP_INIT(srcu_name) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_TINY_SRCU #include <linux/srcutiny.h> #elif defined(CONFIG_TREE_SRCU) #include <linux/srcutree.h> #elif defined(CONFIG_SRCU) #error "Unknown SRCU implementation specified to kernel configuration" #else /* Dummy definition for things like notifiers. Actual use gets link error. */ struct srcu_struct { }; #endif void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); void synchronize_srcu(struct srcu_struct *ssp); unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * srcu_read_lock_held - might we be in SRCU read-side critical section? * @ssp: The srcu_struct structure to check * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, * this assumes we are in an SRCU read-side critical section unless it can * prove otherwise. * * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * * Note that SRCU is based on its own statemachine and it doesn't * relies on normal RCU, it can be called from the CPU which * is in the idle loop from an RCU point of view or offline. */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { if (!debug_lockdep_rcu_enabled()) return 1; return lock_is_held(&ssp->dep_map); } #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { return 1; } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * @c: condition to check for update-side use * * If PROVE_RCU is enabled, invoking this outside of an RCU read-side * critical section will result in an RCU-lockdep splat, unless @c evaluates * to 1. The @c argument will normally be a logical expression containing * lockdep_is_held() calls. */ #define srcu_dereference_check(p, ssp, c) \ __rcu_dereference_check((p), (c) || srcu_read_lock_held(ssp), __rcu) /** * srcu_dereference - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * * Makes rcu_dereference_check() do the dirty work. If PROVE_RCU * is enabled, invoking this outside of an RCU read-side critical * section will result in an RCU-lockdep splat. */ #define srcu_dereference(p, ssp) srcu_dereference_check((p), (ssp), 0) /** * srcu_dereference_notrace - no tracing and no lockdep calls from here * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. */ #define srcu_dereference_notrace(p, ssp) srcu_dereference_check((p), (ssp), 1) /** * srcu_read_lock - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section. Note that SRCU read-side * critical sections may be nested. However, it is illegal to * call anything that waits on an SRCU grace period for the same * srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). * * Note that srcu_read_lock() and the matching srcu_read_unlock() must * occur in the same context, for example, it is illegal to invoke * srcu_read_unlock() in an irq handler if the matching srcu_read_lock() * was invoked in process context. */ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { int retval; retval = __srcu_read_lock(ssp); rcu_lock_acquire(&(ssp)->dep_map); return retval; } /* Used by tracing, cannot be traced and cannot invoke lockdep. */ static inline notrace int srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) { int retval; retval = __srcu_read_lock(ssp); return retval; } /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section. */ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); rcu_lock_release(&(ssp)->dep_map); __srcu_read_unlock(ssp, idx); } /* Used by tracing, cannot be traced and cannot call lockdep. */ static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) { __srcu_read_unlock(ssp, idx); } /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * * Converts the preceding srcu_read_unlock into a two-way memory barrier. * * Call this after srcu_read_unlock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_unlock will appear to happen after * the preceding srcu_read_unlock. */ static inline void smp_mb__after_srcu_read_unlock(void) { /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Macros for manipulating and testing page->flags */ #ifndef PAGE_FLAGS_H #define PAGE_FLAGS_H #include <linux/types.h> #include <linux/bug.h> #include <linux/mmdebug.h> #ifndef __GENERATING_BOUNDS_H #include <linux/mm_types.h> #include <generated/bounds.h> #endif /* !__GENERATING_BOUNDS_H */ /* * Various page->flags bits: * * PG_reserved is set for special pages. The "struct page" of such a page * should in general not be touched (e.g. set dirty) except by its owner. * Pages marked as PG_reserved include: * - Pages part of the kernel image (including vDSO) and similar (e.g. BIOS, * initrd, HW tables) * - Pages reserved or allocated early during boot (before the page allocator * was initialized). This includes (depending on the architecture) the * initial vmemmap, initial page tables, crashkernel, elfcorehdr, and much * much more. Once (if ever) freed, PG_reserved is cleared and they will * be given to the page allocator. * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying * to read/write these pages might end badly. Don't touch! * - The zero page(s) * - Pages not added to the page allocator when onlining a section because * they were excluded via the online_page_callback() or because they are * PG_hwpoison. * - Pages allocated in the context of kexec/kdump (loaded kernel image, * control pages, vmcoreinfo) * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are * not marked PG_reserved (as they might be in use by somebody else who does * not respect the caching strategy). * - Pages part of an offline section (struct pages of offline sections should * not be trusted as they will be initialized when first onlined). * - MCA pages on ia64 * - Pages holding CPU notes for POWER Firmware Assisted Dump * - Device memory (e.g. PMEM, DAX, HMM) * Some PG_reserved pages will be excluded from the hibernation image. * PG_reserved does in general not hinder anybody from dumping or swapping * and is no longer required for remap_pfn_range(). ioremap might require it. * Consequently, PG_reserved for a page mapped into user space can indicate * the zero page, the vDSO, MMIO pages or device memory. * * The PG_private bitflag is set on pagecache pages if they contain filesystem * specific data (which is normally at page->private). It can be used by * private allocations for its own usage. * * During initiation of disk I/O, PG_locked is set. This bit is set before I/O * and cleared when writeback _starts_ or when read _completes_. PG_writeback * is set before writeback starts and cleared when it finishes. * * PG_locked also pins a page in pagecache, and blocks truncation of the file * while it is held. * * page_waitqueue(page) is a wait queue of all tasks waiting for the page * to become unlocked. * * PG_swapbacked is set when a page uses swap as a backing storage. This are * usually PageAnon or shmem pages but please note that even anonymous pages * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as * a result of MADV_FREE). * * PG_uptodate tells whether the page's contents is valid. When a read * completes, the page becomes uptodate, unless a disk I/O error happened. * * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * * PG_error is set to indicate that an I/O error occurred on this page. * * PG_arch_1 is an architecture specific page state bit. The generic code * guarantees that this bit is cleared for a page when it first is entered into * the page cache. * * PG_hwpoison indicates that a page got corrupted in hardware and contains * data with incorrect ECC bits that triggered a machine check. Accessing is * not safe since it may cause another machine check. Don't touch! */ /* * Don't use the *_dontuse flags. Use the macros. Otherwise you'll break * locked- and dirty-page accounting. * * The page flags field is split into two parts, the main flags area * which extends from the low bits upwards, and the fields area which * extends from the high bits downwards. * * | FIELD | ... | FLAGS | * N-1 ^ 0 * (NR_PAGEFLAGS) * * The fields area is reserved for fields mapping zone, node (for NUMA) and * SPARSEMEM section (for variants of SPARSEMEM that require section ids like * SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP). */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_active, PG_workingset, PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, PG_reserved, PG_private, /* If pagecache, has fs-private data */ PG_private_2, /* If pagecache, has fs aux data */ PG_writeback, /* Page is under writeback */ PG_head, /* A head page */ PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ #ifdef CONFIG_MMU PG_mlocked, /* Page is vma mlocked */ #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED PG_uncached, /* Page has been mapped as uncached */ #endif #ifdef CONFIG_MEMORY_FAILURE PG_hwpoison, /* hardware poisoned page. Don't touch */ #endif #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) PG_young, PG_idle, #endif #ifdef CONFIG_64BIT PG_arch_2, #endif __NR_PAGEFLAGS, /* Filesystems */ PG_checked = PG_owner_priv_1, /* SwapBacked */ PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */ /* Two page bits are conscripted by FS-Cache to maintain local caching * state. These bits are set on pages belonging to the netfs's inodes * when those inodes are being locally cached. */ PG_fscache = PG_private_2, /* page backed by cache */ /* XEN */ /* Pinned in Xen as a read-only pagetable page. */ PG_pinned = PG_owner_priv_1, /* Pinned as part of domain save (see xen_mm_pin_all()). */ PG_savepinned = PG_dirty, /* Has a grant mapping of another (foreign) domain's page. */ PG_foreign = PG_owner_priv_1, /* Remapped by swiotlb-xen. */ PG_xen_remapped = PG_owner_priv_1, /* SLOB */ PG_slob_free = PG_private, /* Compound pages. Stored in first tail page's flags */ PG_double_map = PG_workingset, /* non-lru isolated movable page */ PG_isolated = PG_reclaim, /* Only valid for buddy pages. Used to track pages that are reported */ PG_reported = PG_uptodate, }; #ifndef __GENERATING_BOUNDS_H struct page; /* forward declaration */ static inline struct page *compound_head(struct page *page) { unsigned long head = READ_ONCE(page->compound_head); if (unlikely(head & 1)) return (struct page *) (head - 1); return page; } static __always_inline int PageTail(struct page *page) { return READ_ONCE(page->compound_head) & 1; } static __always_inline int PageCompound(struct page *page) { return test_bit(PG_head, &page->flags) || PageTail(page); } #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { return page->flags == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM void page_init_poison(struct page *page, size_t size); #else static inline void page_init_poison(struct page *page, size_t size) { } #endif /* * Page flags policies wrt compound pages * * PF_POISONED_CHECK * check if this struct page poisoned/uninitialized * * PF_ANY: * the page flag is relevant for small, head and tail pages. * * PF_HEAD: * for compound page all operations related to the page flag applied to * head page. * * PF_ONLY_HEAD: * for compound page, callers only ever operate on the head page. * * PF_NO_TAIL: * modifications of the page flag must be done on small or head pages, * checks can be done on tail pages too. * * PF_NO_COMPOUND: * the page flag is not relevant for compound pages. * * PF_SECOND: * the page flag is stored in the first tail page. */ #define PF_POISONED_CHECK(page) ({ \ VM_BUG_ON_PGFLAGS(PagePoisoned(page), page); \ page; }) #define PF_ANY(page, enforce) PF_POISONED_CHECK(page) #define PF_HEAD(page, enforce) PF_POISONED_CHECK(compound_head(page)) #define PF_ONLY_HEAD(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(PageTail(page), page); \ PF_POISONED_CHECK(page); }) #define PF_NO_TAIL(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \ PF_POISONED_CHECK(compound_head(page)); }) #define PF_NO_COMPOUND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \ PF_POISONED_CHECK(page); }) #define PF_SECOND(page, enforce) ({ \ VM_BUG_ON_PGFLAGS(!PageHead(page), page); \ PF_POISONED_CHECK(&page[1]); }) /* * Macros to create function definitions for page flags */ #define TESTPAGEFLAG(uname, lname, policy) \ static __always_inline int Page##uname(struct page *page) \ { return test_bit(PG_##lname, &policy(page, 0)->flags); } #define SETPAGEFLAG(uname, lname, policy) \ static __always_inline void SetPage##uname(struct page *page) \ { set_bit(PG_##lname, &policy(page, 1)->flags); } #define CLEARPAGEFLAG(uname, lname, policy) \ static __always_inline void ClearPage##uname(struct page *page) \ { clear_bit(PG_##lname, &policy(page, 1)->flags); } #define __SETPAGEFLAG(uname, lname, policy) \ static __always_inline void __SetPage##uname(struct page *page) \ { __set_bit(PG_##lname, &policy(page, 1)->flags); } #define __CLEARPAGEFLAG(uname, lname, policy) \ static __always_inline void __ClearPage##uname(struct page *page) \ { __clear_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTSETFLAG(uname, lname, policy) \ static __always_inline int TestSetPage##uname(struct page *page) \ { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTCLEARFLAG(uname, lname, policy) \ static __always_inline int TestClearPage##uname(struct page *page) \ { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } #define PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ SETPAGEFLAG(uname, lname, policy) \ CLEARPAGEFLAG(uname, lname, policy) #define __PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ __SETPAGEFLAG(uname, lname, policy) \ __CLEARPAGEFLAG(uname, lname, policy) #define TESTSCFLAG(uname, lname, policy) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) #define TESTPAGEFLAG_FALSE(uname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname) \ SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname) #define TESTSCFLAG_FALSE(uname) \ TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) PAGEFLAG(Referenced, referenced, PF_HEAD) TESTCLEARFLAG(Referenced, referenced, PF_HEAD) __SETPAGEFLAG(Referenced, referenced, PF_HEAD) PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND) TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND) PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND); PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) TESTCLEARFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND) PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) /* * Private page markings that may be used by the filesystem that owns the page * for its own purposes. * - PG_private and PG_private_2 cause releasepage() and co to be invoked */ PAGEFLAG(Private, private, PF_ANY) __SETPAGEFLAG(Private, private, PF_ANY) __CLEARPAGEFLAG(Private, private, PF_ANY) PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY) PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY) /* * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND) TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND) #ifdef CONFIG_HIGHMEM /* * Must use a macro here due to header dependency issues. page_zone() is not * available at this point. */ #define PageHighMem(__p) is_highmem_idx(page_zonenum(__p)) #else PAGEFLAG_FALSE(HighMem) #endif #ifdef CONFIG_SWAP static __always_inline int PageSwapCache(struct page *page) { #ifdef CONFIG_THP_SWAP page = compound_head(page); #endif return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags); } SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) #else PAGEFLAG_FALSE(SwapCache) #endif PAGEFLAG(Unevictable, unevictable, PF_HEAD) __CLEARPAGEFLAG(Unevictable, unevictable, PF_HEAD) TESTCLEARFLAG(Unevictable, unevictable, PF_HEAD) #ifdef CONFIG_MMU PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) __CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL) #else PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked) TESTSCFLAG_FALSE(Mlocked) #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND) #else PAGEFLAG_FALSE(Uncached) #endif #ifdef CONFIG_MEMORY_FAILURE PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) extern bool take_page_off_buddy(struct page *page); #else PAGEFLAG_FALSE(HWPoison) #define __PG_HWPOISON 0 #endif #if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) TESTPAGEFLAG(Young, young, PF_ANY) SETPAGEFLAG(Young, young, PF_ANY) TESTCLEARFLAG(Young, young, PF_ANY) PAGEFLAG(Idle, idle, PF_ANY) #endif /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set * operations as both should be shielded with the zone lock to prevent * any possible races on the setting or clearing of the bit. */ __PAGEFLAG(Reported, reported, PF_NO_COMPOUND) /* * On an anonymous page mapped into a user virtual memory area, * page->mapping points to its anon_vma, not to a struct address_space; * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON * bit; and then page->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable * page and then page->mapping points a struct address_space. * * Please note that, confusingly, "page_mapping" refers to the inode * address_space which maps the page from disk; whereas "page_mapped" * refers to user virtual address space into which the page is mapped. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 #define PAGE_MAPPING_KSM (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE) static __always_inline int PageMappingFlags(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } static __always_inline int PageAnon(struct page *page) { page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; } static __always_inline int __PageMovable(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; } #ifdef CONFIG_KSM /* * A KSM page is one of those write-protected "shared pages" or "merged pages" * which KSM maps into multiple mms, wherever identical anonymous page content * is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any * anon_vma, but to that page's node of the stable tree. */ static __always_inline int PageKsm(struct page *page) { page = compound_head(page); return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } #else TESTPAGEFLAG_FALSE(Ksm) #endif u64 stable_page_flags(struct page *page); static inline int PageUptodate(struct page *page) { int ret; page = compound_head(page); ret = test_bit(PG_uptodate, &(page)->flags); /* * Must ensure that the data we read out of the page is loaded * _after_ we've loaded page->flags to check for PageUptodate. * We can skip the barrier if the page is not uptodate, because * we wouldn't be reading anything from it. * * See SetPageUptodate() for the other side of the story. */ if (ret) smp_rmb(); return ret; } static __always_inline void __SetPageUptodate(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); smp_wmb(); __set_bit(PG_uptodate, &page->flags); } static __always_inline void SetPageUptodate(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); /* * Memory barrier must be issued before setting the PG_uptodate bit, * so that all previous stores issued in order to bring the page * uptodate are actually visible before PageUptodate becomes true. */ smp_wmb(); set_bit(PG_uptodate, &page->flags); } CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) int test_clear_page_writeback(struct page *page); int __test_set_page_writeback(struct page *page, bool keep_write); #define test_set_page_writeback(page) \ __test_set_page_writeback(page, false) #define test_set_page_writeback_keepwrite(page) \ __test_set_page_writeback(page, true) static inline void set_page_writeback(struct page *page) { test_set_page_writeback(page); } static inline void set_page_writeback_keepwrite(struct page *page) { test_set_page_writeback_keepwrite(page); } __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) static __always_inline void set_compound_head(struct page *page, struct page *head) { WRITE_ONCE(page->compound_head, (unsigned long)head + 1); } static __always_inline void clear_compound_head(struct page *page) { WRITE_ONCE(page->compound_head, 0); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline void ClearPageCompound(struct page *page) { BUG_ON(!PageHead(page)); ClearPageHead(page); } #endif #define PG_head_mask ((1UL << PG_head)) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); int PageHeadHuge(struct page *page); bool page_huge_active(struct page *page); #else TESTPAGEFLAG_FALSE(Huge) TESTPAGEFLAG_FALSE(HeadHuge) static inline bool page_huge_active(struct page *page) { return 0; } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for * normal or transparent huge pages. * * PageTransHuge() returns true for both transparent huge and * hugetlbfs pages, but not normal pages. PageTransHuge() can only be * called only in the core VM paths where hugetlbfs pages can't exist. */ static inline int PageTransHuge(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); return PageHead(page); } /* * PageTransCompound returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransCompound(struct page *page) { return PageCompound(page); } /* * PageTransCompoundMap is the same as PageTransCompound, but it also * guarantees the primary MMU has the entire compound page mapped * through pmd_trans_huge, which in turn guarantees the secondary MMUs * can also map the entire compound page. This allows the secondary * MMUs to call get_user_pages() only once for each compound page and * to immediately map the entire compound page with a single secondary * MMU fault. If there will be a pmd split later, the secondary MMUs * will get an update through the MMU notifier invalidation through * split_huge_pmd(). * * Unlike PageTransCompound, this is safe to be called only while * split_huge_pmd() cannot run from under us, like if protected by the * MMU notifier, otherwise it may result in page->_mapcount check false * positives. * * We have to treat page cache THP differently since every subpage of it * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE * mapped in the current process so comparing subpage's _mapcount to * compound_mapcount to filter out PTE mapped case. */ static inline int PageTransCompoundMap(struct page *page) { struct page *head; if (!PageTransCompound(page)) return 0; if (PageAnon(page)) return atomic_read(&page->_mapcount) < 0; head = compound_head(page); /* File THP is PMD mapped and not PTE mapped */ return atomic_read(&page->_mapcount) == atomic_read(compound_mapcount_ptr(head)); } /* * PageTransTail returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. */ static inline int PageTransTail(struct page *page) { return PageTail(page); } /* * PageDoubleMap indicates that the compound page is mapped with PTEs as well * as PMDs. * * This is required for optimization of rmap operations for THP: we can postpone * per small page mapcount accounting (and its overhead from atomic operations) * until the first PMD split. * * For the page PageDoubleMap means ->_mapcount in all sub-pages is offset up * by one. This reference will go away with last compound_mapcount. * * See also __split_huge_pmd_locked() and page_remove_anon_compound_rmap(). */ PAGEFLAG(DoubleMap, double_map, PF_SECOND) TESTSCFLAG(DoubleMap, double_map, PF_SECOND) #else TESTPAGEFLAG_FALSE(TransHuge) TESTPAGEFLAG_FALSE(TransCompound) TESTPAGEFLAG_FALSE(TransCompoundMap) TESTPAGEFLAG_FALSE(TransTail) PAGEFLAG_FALSE(DoubleMap) TESTSCFLAG_FALSE(DoubleMap) #endif /* * For pages that are never mapped to userspace (and aren't PageSlab), * page_type may be used. Because it is initialised to -1, we invert the * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and * low bits so that an underflow or overflow of page_mapcount() won't be * mistaken for a page type value. */ #define PAGE_TYPE_BASE 0xf0000000 /* Reserve 0x0000007f to catch underflows of page_mapcount */ #define PAGE_MAPCOUNT_RESERVE -128 #define PG_buddy 0x00000080 #define PG_offline 0x00000100 #define PG_kmemcg 0x00000200 #define PG_table 0x00000400 #define PG_guard 0x00000800 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) static inline int page_has_type(struct page *page) { return (int)page->page_type < PAGE_MAPCOUNT_RESERVE; } #define PAGE_TYPE_OPS(uname, lname) \ static __always_inline int Page##uname(struct page *page) \ { \ return PageType(page, PG_##lname); \ } \ static __always_inline void __SetPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!PageType(page, 0), page); \ page->page_type &= ~PG_##lname; \ } \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type |= PG_##lname; \ } /* * PageBuddy() indicates that the page is free and in the buddy system * (see mm/page_alloc.c). */ PAGE_TYPE_OPS(Buddy, buddy) /* * PageOffline() indicates that the page is logically offline although the * containing section is online. (e.g. inflated in a balloon driver or * not onlined when onlining the section). * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. * * If a driver wants to allow to offline unmovable PageOffline() pages without * putting them back to the buddy, it can do so via the memory notifier by * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() * pages (now with a reference count of zero) are treated like free pages, * allowing the containing memory block to get offlined. A driver that * relies on this feature is aware that re-onlining the memory block will * require to re-set the pages PageOffline() and not giving them to the * buddy via online_page_callback_t. */ PAGE_TYPE_OPS(Offline, offline) /* * If kmemcg is enabled, the buddy allocator will set PageKmemcg() on * pages allocated with __GFP_ACCOUNT. It gets cleared on page free. */ PAGE_TYPE_OPS(Kmemcg, kmemcg) /* * Marks pages in use as page tables. */ PAGE_TYPE_OPS(Table, table) /* * Marks guardpages used with debug_pagealloc. */ PAGE_TYPE_OPS(Guard, guard) extern bool is_free_buddy_page(struct page *page); __PAGEFLAG(Isolated, isolated, PF_ANY); /* * If network-based swap is enabled, sl*b must keep track of whether pages * were allocated from pfmemalloc reserves. */ static inline int PageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); return PageActive(page); } static inline void SetPageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); SetPageActive(page); } static inline void __ClearPageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); __ClearPageActive(page); } static inline void ClearPageSlabPfmemalloc(struct page *page) { VM_BUG_ON_PAGE(!PageSlab(page), page); ClearPageActive(page); } #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else #define __PG_MLOCKED 0 #endif /* * Flags checked when a page is freed. Pages being freed should not have * these flags set. It they are, there is a problem. */ #define PAGE_FLAGS_CHECK_AT_FREE \ (1UL << PG_lru | 1UL << PG_locked | \ 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ 1UL << PG_slab | 1UL << PG_active | \ 1UL << PG_unevictable | __PG_MLOCKED) /* * Flags checked when a page is prepped for return by the page allocator. * Pages being prepped should not have these flags set. It they are set, * there has been a kernel bug or struct page corruption. * * __PG_HWPOISON is exceptional because it needs to be kept beyond page's * alloc-free cycle to prevent from reusing the page. */ #define PAGE_FLAGS_CHECK_AT_PREP \ (((1UL << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) /** * page_has_private - Determine if page has private stuff * @page: The page to be checked * * Determine if a page has private stuff, indicating that release routines * should be invoked upon it. */ static inline int page_has_private(struct page *page) { return !!(page->flags & PAGE_FLAGS_PRIVATE); } #undef PF_ANY #undef PF_HEAD #undef PF_ONLY_HEAD #undef PF_NO_TAIL #undef PF_NO_COMPOUND #undef PF_SECOND #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BIT_SPINLOCK_H #define __LINUX_BIT_SPINLOCK_H #include <linux/kernel.h> #include <linux/preempt.h> #include <linux/atomic.h> #include <linux/bug.h> /* * bit-based spin_lock() * * Don't use this unless you really need to: spin_lock() and spin_unlock() * are significantly faster. */ static inline void bit_spin_lock(int bitnum, unsigned long *addr) { /* * Assuming the lock is uncontended, this never enters * the body of the outer loop. If it is contended, then * within the inner loop a non-atomic test is used to * busywait with less bus contention for a good time to * attempt to acquire the lock bit. */ preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) while (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); do { cpu_relax(); } while (test_bit(bitnum, addr)); preempt_disable(); } #endif __acquire(bitlock); } /* * Return true if it was acquired */ static inline int bit_spin_trylock(int bitnum, unsigned long *addr) { preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) if (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); return 0; } #endif __acquire(bitlock); return 1; } /* * bit-based spin_unlock() */ static inline void bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); } /* * bit-based spin_unlock() * non-atomic version, which can be used eg. if the bit lock itself is * protecting the rest of the flags in the word. */ static inline void __bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) __clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); } /* * Return true if the lock is held. */ static inline int bit_spin_is_locked(int bitnum, unsigned long *addr) { #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) return test_bit(bitnum, addr); #elif defined CONFIG_PREEMPT_COUNT return preempt_count(); #else return 1; #endif } #endif /* __LINUX_BIT_SPINLOCK_H */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 | // SPDX-License-Identifier: GPL-2.0-only /* * Implementation of the kernel access vector cache (AVC). * * Authors: Stephen Smalley, <sds@tycho.nsa.gov> * James Morris <jmorris@redhat.com> * * Update: KaiGai, Kohei <kaigai@ak.jp.nec.com> * Replaced the avc_lock spinlock by RCU. * * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/types.h> #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/dcache.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/percpu.h> #include <linux/list.h> #include <net/sock.h> #include <linux/un.h> #include <net/af_unix.h> #include <linux/ip.h> #include <linux/audit.h> #include <linux/ipv6.h> #include <net/ipv6.h> #include "avc.h" #include "avc_ss.h" #include "classmap.h" #define CREATE_TRACE_POINTS #include <trace/events/avc.h> #define AVC_CACHE_SLOTS 512 #define AVC_DEF_CACHE_THRESHOLD 512 #define AVC_CACHE_RECLAIM 16 #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS #define avc_cache_stats_incr(field) this_cpu_inc(avc_cache_stats.field) #else #define avc_cache_stats_incr(field) do {} while (0) #endif struct avc_entry { u32 ssid; u32 tsid; u16 tclass; struct av_decision avd; struct avc_xperms_node *xp_node; }; struct avc_node { struct avc_entry ae; struct hlist_node list; /* anchored in avc_cache->slots[i] */ struct rcu_head rhead; }; struct avc_xperms_decision_node { struct extended_perms_decision xpd; struct list_head xpd_list; /* list of extended_perms_decision */ }; struct avc_xperms_node { struct extended_perms xp; struct list_head xpd_head; /* list head of extended_perms_decision */ }; struct avc_cache { struct hlist_head slots[AVC_CACHE_SLOTS]; /* head for avc_node->list */ spinlock_t slots_lock[AVC_CACHE_SLOTS]; /* lock for writes */ atomic_t lru_hint; /* LRU hint for reclaim scan */ atomic_t active_nodes; u32 latest_notif; /* latest revocation notification */ }; struct avc_callback_node { int (*callback) (u32 event); u32 events; struct avc_callback_node *next; }; #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS DEFINE_PER_CPU(struct avc_cache_stats, avc_cache_stats) = { 0 }; #endif struct selinux_avc { unsigned int avc_cache_threshold; struct avc_cache avc_cache; }; static struct selinux_avc selinux_avc; void selinux_avc_init(struct selinux_avc **avc) { int i; selinux_avc.avc_cache_threshold = AVC_DEF_CACHE_THRESHOLD; for (i = 0; i < AVC_CACHE_SLOTS; i++) { INIT_HLIST_HEAD(&selinux_avc.avc_cache.slots[i]); spin_lock_init(&selinux_avc.avc_cache.slots_lock[i]); } atomic_set(&selinux_avc.avc_cache.active_nodes, 0); atomic_set(&selinux_avc.avc_cache.lru_hint, 0); *avc = &selinux_avc; } unsigned int avc_get_cache_threshold(struct selinux_avc *avc) { return avc->avc_cache_threshold; } void avc_set_cache_threshold(struct selinux_avc *avc, unsigned int cache_threshold) { avc->avc_cache_threshold = cache_threshold; } static struct avc_callback_node *avc_callbacks; static struct kmem_cache *avc_node_cachep; static struct kmem_cache *avc_xperms_data_cachep; static struct kmem_cache *avc_xperms_decision_cachep; static struct kmem_cache *avc_xperms_cachep; static inline int avc_hash(u32 ssid, u32 tsid, u16 tclass) { return (ssid ^ (tsid<<2) ^ (tclass<<4)) & (AVC_CACHE_SLOTS - 1); } /** * avc_init - Initialize the AVC. * * Initialize the access vector cache. */ void __init avc_init(void) { avc_node_cachep = kmem_cache_create("avc_node", sizeof(struct avc_node), 0, SLAB_PANIC, NULL); avc_xperms_cachep = kmem_cache_create("avc_xperms_node", sizeof(struct avc_xperms_node), 0, SLAB_PANIC, NULL); avc_xperms_decision_cachep = kmem_cache_create( "avc_xperms_decision_node", sizeof(struct avc_xperms_decision_node), 0, SLAB_PANIC, NULL); avc_xperms_data_cachep = kmem_cache_create("avc_xperms_data", sizeof(struct extended_perms_data), 0, SLAB_PANIC, NULL); } int avc_get_hash_stats(struct selinux_avc *avc, char *page) { int i, chain_len, max_chain_len, slots_used; struct avc_node *node; struct hlist_head *head; rcu_read_lock(); slots_used = 0; max_chain_len = 0; for (i = 0; i < AVC_CACHE_SLOTS; i++) { head = &avc->avc_cache.slots[i]; if (!hlist_empty(head)) { slots_used++; chain_len = 0; hlist_for_each_entry_rcu(node, head, list) chain_len++; if (chain_len > max_chain_len) max_chain_len = chain_len; } } rcu_read_unlock(); return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n" "longest chain: %d\n", atomic_read(&avc->avc_cache.active_nodes), slots_used, AVC_CACHE_SLOTS, max_chain_len); } /* * using a linked list for extended_perms_decision lookup because the list is * always small. i.e. less than 5, typically 1 */ static struct extended_perms_decision *avc_xperms_decision_lookup(u8 driver, struct avc_xperms_node *xp_node) { struct avc_xperms_decision_node *xpd_node; list_for_each_entry(xpd_node, &xp_node->xpd_head, xpd_list) { if (xpd_node->xpd.driver == driver) return &xpd_node->xpd; } return NULL; } static inline unsigned int avc_xperms_has_perm(struct extended_perms_decision *xpd, u8 perm, u8 which) { unsigned int rc = 0; if ((which == XPERMS_ALLOWED) && (xpd->used & XPERMS_ALLOWED)) rc = security_xperm_test(xpd->allowed->p, perm); else if ((which == XPERMS_AUDITALLOW) && (xpd->used & XPERMS_AUDITALLOW)) rc = security_xperm_test(xpd->auditallow->p, perm); else if ((which == XPERMS_DONTAUDIT) && (xpd->used & XPERMS_DONTAUDIT)) rc = security_xperm_test(xpd->dontaudit->p, perm); return rc; } static void avc_xperms_allow_perm(struct avc_xperms_node *xp_node, u8 driver, u8 perm) { struct extended_perms_decision *xpd; security_xperm_set(xp_node->xp.drivers.p, driver); xpd = avc_xperms_decision_lookup(driver, xp_node); if (xpd && xpd->allowed) security_xperm_set(xpd->allowed->p, perm); } static void avc_xperms_decision_free(struct avc_xperms_decision_node *xpd_node) { struct extended_perms_decision *xpd; xpd = &xpd_node->xpd; if (xpd->allowed) kmem_cache_free(avc_xperms_data_cachep, xpd->allowed); if (xpd->auditallow) kmem_cache_free(avc_xperms_data_cachep, xpd->auditallow); if (xpd->dontaudit) kmem_cache_free(avc_xperms_data_cachep, xpd->dontaudit); kmem_cache_free(avc_xperms_decision_cachep, xpd_node); } static void avc_xperms_free(struct avc_xperms_node *xp_node) { struct avc_xperms_decision_node *xpd_node, *tmp; if (!xp_node) return; list_for_each_entry_safe(xpd_node, tmp, &xp_node->xpd_head, xpd_list) { list_del(&xpd_node->xpd_list); avc_xperms_decision_free(xpd_node); } kmem_cache_free(avc_xperms_cachep, xp_node); } static void avc_copy_xperms_decision(struct extended_perms_decision *dest, struct extended_perms_decision *src) { dest->driver = src->driver; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) memcpy(dest->allowed->p, src->allowed->p, sizeof(src->allowed->p)); if (dest->used & XPERMS_AUDITALLOW) memcpy(dest->auditallow->p, src->auditallow->p, sizeof(src->auditallow->p)); if (dest->used & XPERMS_DONTAUDIT) memcpy(dest->dontaudit->p, src->dontaudit->p, sizeof(src->dontaudit->p)); } /* * similar to avc_copy_xperms_decision, but only copy decision * information relevant to this perm */ static inline void avc_quick_copy_xperms_decision(u8 perm, struct extended_perms_decision *dest, struct extended_perms_decision *src) { /* * compute index of the u32 of the 256 bits (8 u32s) that contain this * command permission */ u8 i = perm >> 5; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) dest->allowed->p[i] = src->allowed->p[i]; if (dest->used & XPERMS_AUDITALLOW) dest->auditallow->p[i] = src->auditallow->p[i]; if (dest->used & XPERMS_DONTAUDIT) dest->dontaudit->p[i] = src->dontaudit->p[i]; } static struct avc_xperms_decision_node *avc_xperms_decision_alloc(u8 which) { struct avc_xperms_decision_node *xpd_node; struct extended_perms_decision *xpd; xpd_node = kmem_cache_zalloc(avc_xperms_decision_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd_node) return NULL; xpd = &xpd_node->xpd; if (which & XPERMS_ALLOWED) { xpd->allowed = kmem_cache_zalloc(avc_xperms_data_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd->allowed) goto error; } if (which & XPERMS_AUDITALLOW) { xpd->auditallow = kmem_cache_zalloc(avc_xperms_data_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd->auditallow) goto error; } if (which & XPERMS_DONTAUDIT) { xpd->dontaudit = kmem_cache_zalloc(avc_xperms_data_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd->dontaudit) goto error; } return xpd_node; error: avc_xperms_decision_free(xpd_node); return NULL; } static int avc_add_xperms_decision(struct avc_node *node, struct extended_perms_decision *src) { struct avc_xperms_decision_node *dest_xpd; dest_xpd = avc_xperms_decision_alloc(src->used); if (!dest_xpd) return -ENOMEM; avc_copy_xperms_decision(&dest_xpd->xpd, src); list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head); node->ae.xp_node->xp.len++; return 0; } static struct avc_xperms_node *avc_xperms_alloc(void) { struct avc_xperms_node *xp_node; xp_node = kmem_cache_zalloc(avc_xperms_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xp_node) return xp_node; INIT_LIST_HEAD(&xp_node->xpd_head); return xp_node; } static int avc_xperms_populate(struct avc_node *node, struct avc_xperms_node *src) { struct avc_xperms_node *dest; struct avc_xperms_decision_node *dest_xpd; struct avc_xperms_decision_node *src_xpd; if (src->xp.len == 0) return 0; dest = avc_xperms_alloc(); if (!dest) return -ENOMEM; memcpy(dest->xp.drivers.p, src->xp.drivers.p, sizeof(dest->xp.drivers.p)); dest->xp.len = src->xp.len; /* for each source xpd allocate a destination xpd and copy */ list_for_each_entry(src_xpd, &src->xpd_head, xpd_list) { dest_xpd = avc_xperms_decision_alloc(src_xpd->xpd.used); if (!dest_xpd) goto error; avc_copy_xperms_decision(&dest_xpd->xpd, &src_xpd->xpd); list_add(&dest_xpd->xpd_list, &dest->xpd_head); } node->ae.xp_node = dest; return 0; error: avc_xperms_free(dest); return -ENOMEM; } static inline u32 avc_xperms_audit_required(u32 requested, struct av_decision *avd, struct extended_perms_decision *xpd, u8 perm, int result, u32 *deniedp) { u32 denied, audited; denied = requested & ~avd->allowed; if (unlikely(denied)) { audited = denied & avd->auditdeny; if (audited && xpd) { if (avc_xperms_has_perm(xpd, perm, XPERMS_DONTAUDIT)) audited &= ~requested; } } else if (result) { audited = denied = requested; } else { audited = requested & avd->auditallow; if (audited && xpd) { if (!avc_xperms_has_perm(xpd, perm, XPERMS_AUDITALLOW)) audited &= ~requested; } } *deniedp = denied; return audited; } static inline int avc_xperms_audit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct av_decision *avd, struct extended_perms_decision *xpd, u8 perm, int result, struct common_audit_data *ad) { u32 audited, denied; audited = avc_xperms_audit_required( requested, avd, xpd, perm, result, &denied); if (likely(!audited)) return 0; return slow_avc_audit(state, ssid, tsid, tclass, requested, audited, denied, result, ad); } static void avc_node_free(struct rcu_head *rhead) { struct avc_node *node = container_of(rhead, struct avc_node, rhead); avc_xperms_free(node->ae.xp_node); kmem_cache_free(avc_node_cachep, node); avc_cache_stats_incr(frees); } static void avc_node_delete(struct selinux_avc *avc, struct avc_node *node) { hlist_del_rcu(&node->list); call_rcu(&node->rhead, avc_node_free); atomic_dec(&avc->avc_cache.active_nodes); } static void avc_node_kill(struct selinux_avc *avc, struct avc_node *node) { avc_xperms_free(node->ae.xp_node); kmem_cache_free(avc_node_cachep, node); avc_cache_stats_incr(frees); atomic_dec(&avc->avc_cache.active_nodes); } static void avc_node_replace(struct selinux_avc *avc, struct avc_node *new, struct avc_node *old) { hlist_replace_rcu(&old->list, &new->list); call_rcu(&old->rhead, avc_node_free); atomic_dec(&avc->avc_cache.active_nodes); } static inline int avc_reclaim_node(struct selinux_avc *avc) { struct avc_node *node; int hvalue, try, ecx; unsigned long flags; struct hlist_head *head; spinlock_t *lock; for (try = 0, ecx = 0; try < AVC_CACHE_SLOTS; try++) { hvalue = atomic_inc_return(&avc->avc_cache.lru_hint) & (AVC_CACHE_SLOTS - 1); head = &avc->avc_cache.slots[hvalue]; lock = &avc->avc_cache.slots_lock[hvalue]; if (!spin_trylock_irqsave(lock, flags)) continue; rcu_read_lock(); hlist_for_each_entry(node, head, list) { avc_node_delete(avc, node); avc_cache_stats_incr(reclaims); ecx++; if (ecx >= AVC_CACHE_RECLAIM) { rcu_read_unlock(); spin_unlock_irqrestore(lock, flags); goto out; } } rcu_read_unlock(); spin_unlock_irqrestore(lock, flags); } out: return ecx; } static struct avc_node *avc_alloc_node(struct selinux_avc *avc) { struct avc_node *node; node = kmem_cache_zalloc(avc_node_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!node) goto out; INIT_HLIST_NODE(&node->list); avc_cache_stats_incr(allocations); if (atomic_inc_return(&avc->avc_cache.active_nodes) > avc->avc_cache_threshold) avc_reclaim_node(avc); out: return node; } static void avc_node_populate(struct avc_node *node, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd) { node->ae.ssid = ssid; node->ae.tsid = tsid; node->ae.tclass = tclass; memcpy(&node->ae.avd, avd, sizeof(node->ae.avd)); } static inline struct avc_node *avc_search_node(struct selinux_avc *avc, u32 ssid, u32 tsid, u16 tclass) { struct avc_node *node, *ret = NULL; int hvalue; struct hlist_head *head; hvalue = avc_hash(ssid, tsid, tclass); head = &avc->avc_cache.slots[hvalue]; hlist_for_each_entry_rcu(node, head, list) { if (ssid == node->ae.ssid && tclass == node->ae.tclass && tsid == node->ae.tsid) { ret = node; break; } } return ret; } /** * avc_lookup - Look up an AVC entry. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * * Look up an AVC entry that is valid for the * (@ssid, @tsid), interpreting the permissions * based on @tclass. If a valid AVC entry exists, * then this function returns the avc_node. * Otherwise, this function returns NULL. */ static struct avc_node *avc_lookup(struct selinux_avc *avc, u32 ssid, u32 tsid, u16 tclass) { struct avc_node *node; avc_cache_stats_incr(lookups); node = avc_search_node(avc, ssid, tsid, tclass); if (node) return node; avc_cache_stats_incr(misses); return NULL; } static int avc_latest_notif_update(struct selinux_avc *avc, int seqno, int is_insert) { int ret = 0; static DEFINE_SPINLOCK(notif_lock); unsigned long flag; spin_lock_irqsave(¬if_lock, flag); if (is_insert) { if (seqno < avc->avc_cache.latest_notif) { pr_warn("SELinux: avc: seqno %d < latest_notif %d\n", seqno, avc->avc_cache.latest_notif); ret = -EAGAIN; } } else { if (seqno > avc->avc_cache.latest_notif) avc->avc_cache.latest_notif = seqno; } spin_unlock_irqrestore(¬if_lock, flag); return ret; } /** * avc_insert - Insert an AVC entry. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @avd: resulting av decision * @xp_node: resulting extended permissions * * Insert an AVC entry for the SID pair * (@ssid, @tsid) and class @tclass. * The access vectors and the sequence number are * normally provided by the security server in * response to a security_compute_av() call. If the * sequence number @avd->seqno is not less than the latest * revocation notification, then the function copies * the access vectors into a cache entry, returns * avc_node inserted. Otherwise, this function returns NULL. */ static struct avc_node *avc_insert(struct selinux_avc *avc, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd, struct avc_xperms_node *xp_node) { struct avc_node *pos, *node = NULL; int hvalue; unsigned long flag; spinlock_t *lock; struct hlist_head *head; if (avc_latest_notif_update(avc, avd->seqno, 1)) return NULL; node = avc_alloc_node(avc); if (!node) return NULL; avc_node_populate(node, ssid, tsid, tclass, avd); if (avc_xperms_populate(node, xp_node)) { avc_node_kill(avc, node); return NULL; } hvalue = avc_hash(ssid, tsid, tclass); head = &avc->avc_cache.slots[hvalue]; lock = &avc->avc_cache.slots_lock[hvalue]; spin_lock_irqsave(lock, flag); hlist_for_each_entry(pos, head, list) { if (pos->ae.ssid == ssid && pos->ae.tsid == tsid && pos->ae.tclass == tclass) { avc_node_replace(avc, node, pos); goto found; } } hlist_add_head_rcu(&node->list, head); found: spin_unlock_irqrestore(lock, flag); return node; } /** * avc_audit_pre_callback - SELinux specific information * will be called by generic audit code * @ab: the audit buffer * @a: audit_data */ static void avc_audit_pre_callback(struct audit_buffer *ab, void *a) { struct common_audit_data *ad = a; struct selinux_audit_data *sad = ad->selinux_audit_data; u32 av = sad->audited; const char **perms; int i, perm; audit_log_format(ab, "avc: %s ", sad->denied ? "denied" : "granted"); if (av == 0) { audit_log_format(ab, " null"); return; } perms = secclass_map[sad->tclass-1].perms; audit_log_format(ab, " {"); i = 0; perm = 1; while (i < (sizeof(av) * 8)) { if ((perm & av) && perms[i]) { audit_log_format(ab, " %s", perms[i]); av &= ~perm; } i++; perm <<= 1; } if (av) audit_log_format(ab, " 0x%x", av); audit_log_format(ab, " } for "); } /** * avc_audit_post_callback - SELinux specific information * will be called by generic audit code * @ab: the audit buffer * @a: audit_data */ static void avc_audit_post_callback(struct audit_buffer *ab, void *a) { struct common_audit_data *ad = a; struct selinux_audit_data *sad = ad->selinux_audit_data; char *scontext = NULL; char *tcontext = NULL; const char *tclass = NULL; u32 scontext_len; u32 tcontext_len; int rc; rc = security_sid_to_context(sad->state, sad->ssid, &scontext, &scontext_len); if (rc) audit_log_format(ab, " ssid=%d", sad->ssid); else audit_log_format(ab, " scontext=%s", scontext); rc = security_sid_to_context(sad->state, sad->tsid, &tcontext, &tcontext_len); if (rc) audit_log_format(ab, " tsid=%d", sad->tsid); else audit_log_format(ab, " tcontext=%s", tcontext); tclass = secclass_map[sad->tclass-1].name; audit_log_format(ab, " tclass=%s", tclass); if (sad->denied) audit_log_format(ab, " permissive=%u", sad->result ? 0 : 1); trace_selinux_audited(sad, scontext, tcontext, tclass); kfree(tcontext); kfree(scontext); /* in case of invalid context report also the actual context string */ rc = security_sid_to_context_inval(sad->state, sad->ssid, &scontext, &scontext_len); if (!rc && scontext) { if (scontext_len && scontext[scontext_len - 1] == '\0') scontext_len--; audit_log_format(ab, " srawcon="); audit_log_n_untrustedstring(ab, scontext, scontext_len); kfree(scontext); } rc = security_sid_to_context_inval(sad->state, sad->tsid, &scontext, &scontext_len); if (!rc && scontext) { if (scontext_len && scontext[scontext_len - 1] == '\0') scontext_len--; audit_log_format(ab, " trawcon="); audit_log_n_untrustedstring(ab, scontext, scontext_len); kfree(scontext); } } /* This is the slow part of avc audit with big stack footprint */ noinline int slow_avc_audit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u32 audited, u32 denied, int result, struct common_audit_data *a) { struct common_audit_data stack_data; struct selinux_audit_data sad; if (WARN_ON(!tclass || tclass >= ARRAY_SIZE(secclass_map))) return -EINVAL; if (!a) { a = &stack_data; a->type = LSM_AUDIT_DATA_NONE; } sad.tclass = tclass; sad.requested = requested; sad.ssid = ssid; sad.tsid = tsid; sad.audited = audited; sad.denied = denied; sad.result = result; sad.state = state; a->selinux_audit_data = &sad; common_lsm_audit(a, avc_audit_pre_callback, avc_audit_post_callback); return 0; } /** * avc_add_callback - Register a callback for security events. * @callback: callback function * @events: security events * * Register a callback function for events in the set @events. * Returns %0 on success or -%ENOMEM if insufficient memory * exists to add the callback. */ int __init avc_add_callback(int (*callback)(u32 event), u32 events) { struct avc_callback_node *c; int rc = 0; c = kmalloc(sizeof(*c), GFP_KERNEL); if (!c) { rc = -ENOMEM; goto out; } c->callback = callback; c->events = events; c->next = avc_callbacks; avc_callbacks = c; out: return rc; } /** * avc_update_node Update an AVC entry * @event : Updating event * @perms : Permission mask bits * @ssid,@tsid,@tclass : identifier of an AVC entry * @seqno : sequence number when decision was made * @xpd: extended_perms_decision to be added to the node * @flags: the AVC_* flags, e.g. AVC_NONBLOCKING, AVC_EXTENDED_PERMS, or 0. * * if a valid AVC entry doesn't exist,this function returns -ENOENT. * if kmalloc() called internal returns NULL, this function returns -ENOMEM. * otherwise, this function updates the AVC entry. The original AVC-entry object * will release later by RCU. */ static int avc_update_node(struct selinux_avc *avc, u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, u32 tsid, u16 tclass, u32 seqno, struct extended_perms_decision *xpd, u32 flags) { int hvalue, rc = 0; unsigned long flag; struct avc_node *pos, *node, *orig = NULL; struct hlist_head *head; spinlock_t *lock; /* * If we are in a non-blocking code path, e.g. VFS RCU walk, * then we must not add permissions to a cache entry * because we will not audit the denial. Otherwise, * during the subsequent blocking retry (e.g. VFS ref walk), we * will find the permissions already granted in the cache entry * and won't audit anything at all, leading to silent denials in * permissive mode that only appear when in enforcing mode. * * See the corresponding handling of MAY_NOT_BLOCK in avc_audit() * and selinux_inode_permission(). */ if (flags & AVC_NONBLOCKING) return 0; node = avc_alloc_node(avc); if (!node) { rc = -ENOMEM; goto out; } /* Lock the target slot */ hvalue = avc_hash(ssid, tsid, tclass); head = &avc->avc_cache.slots[hvalue]; lock = &avc->avc_cache.slots_lock[hvalue]; spin_lock_irqsave(lock, flag); hlist_for_each_entry(pos, head, list) { if (ssid == pos->ae.ssid && tsid == pos->ae.tsid && tclass == pos->ae.tclass && seqno == pos->ae.avd.seqno){ orig = pos; break; } } if (!orig) { rc = -ENOENT; avc_node_kill(avc, node); goto out_unlock; } /* * Copy and replace original node. */ avc_node_populate(node, ssid, tsid, tclass, &orig->ae.avd); if (orig->ae.xp_node) { rc = avc_xperms_populate(node, orig->ae.xp_node); if (rc) { avc_node_kill(avc, node); goto out_unlock; } } switch (event) { case AVC_CALLBACK_GRANT: node->ae.avd.allowed |= perms; if (node->ae.xp_node && (flags & AVC_EXTENDED_PERMS)) avc_xperms_allow_perm(node->ae.xp_node, driver, xperm); break; case AVC_CALLBACK_TRY_REVOKE: case AVC_CALLBACK_REVOKE: node->ae.avd.allowed &= ~perms; break; case AVC_CALLBACK_AUDITALLOW_ENABLE: node->ae.avd.auditallow |= perms; break; case AVC_CALLBACK_AUDITALLOW_DISABLE: node->ae.avd.auditallow &= ~perms; break; case AVC_CALLBACK_AUDITDENY_ENABLE: node->ae.avd.auditdeny |= perms; break; case AVC_CALLBACK_AUDITDENY_DISABLE: node->ae.avd.auditdeny &= ~perms; break; case AVC_CALLBACK_ADD_XPERMS: avc_add_xperms_decision(node, xpd); break; } avc_node_replace(avc, node, orig); out_unlock: spin_unlock_irqrestore(lock, flag); out: return rc; } /** * avc_flush - Flush the cache */ static void avc_flush(struct selinux_avc *avc) { struct hlist_head *head; struct avc_node *node; spinlock_t *lock; unsigned long flag; int i; for (i = 0; i < AVC_CACHE_SLOTS; i++) { head = &avc->avc_cache.slots[i]; lock = &avc->avc_cache.slots_lock[i]; spin_lock_irqsave(lock, flag); /* * With preemptable RCU, the outer spinlock does not * prevent RCU grace periods from ending. */ rcu_read_lock(); hlist_for_each_entry(node, head, list) avc_node_delete(avc, node); rcu_read_unlock(); spin_unlock_irqrestore(lock, flag); } } /** * avc_ss_reset - Flush the cache and revalidate migrated permissions. * @seqno: policy sequence number */ int avc_ss_reset(struct selinux_avc *avc, u32 seqno) { struct avc_callback_node *c; int rc = 0, tmprc; avc_flush(avc); for (c = avc_callbacks; c; c = c->next) { if (c->events & AVC_CALLBACK_RESET) { tmprc = c->callback(AVC_CALLBACK_RESET); /* save the first error encountered for the return value and continue processing the callbacks */ if (!rc) rc = tmprc; } } avc_latest_notif_update(avc, seqno, 0); return rc; } /* * Slow-path helper function for avc_has_perm_noaudit, * when the avc_node lookup fails. We get called with * the RCU read lock held, and need to return with it * still held, but drop if for the security compute. * * Don't inline this, since it's the slow-path and just * results in a bigger stack frame. */ static noinline struct avc_node *avc_compute_av(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd, struct avc_xperms_node *xp_node) { rcu_read_unlock(); INIT_LIST_HEAD(&xp_node->xpd_head); security_compute_av(state, ssid, tsid, tclass, avd, &xp_node->xp); rcu_read_lock(); return avc_insert(state->avc, ssid, tsid, tclass, avd, xp_node); } static noinline int avc_denied(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u8 driver, u8 xperm, unsigned int flags, struct av_decision *avd) { if (flags & AVC_STRICT) return -EACCES; if (enforcing_enabled(state) && !(avd->flags & AVD_FLAGS_PERMISSIVE)) return -EACCES; avc_update_node(state->avc, AVC_CALLBACK_GRANT, requested, driver, xperm, ssid, tsid, tclass, avd->seqno, NULL, flags); return 0; } /* * The avc extended permissions logic adds an additional 256 bits of * permissions to an avc node when extended permissions for that node are * specified in the avtab. If the additional 256 permissions is not adequate, * as-is the case with ioctls, then multiple may be chained together and the * driver field is used to specify which set contains the permission. */ int avc_has_extended_perms(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u8 driver, u8 xperm, struct common_audit_data *ad) { struct avc_node *node; struct av_decision avd; u32 denied; struct extended_perms_decision local_xpd; struct extended_perms_decision *xpd = NULL; struct extended_perms_data allowed; struct extended_perms_data auditallow; struct extended_perms_data dontaudit; struct avc_xperms_node local_xp_node; struct avc_xperms_node *xp_node; int rc = 0, rc2; xp_node = &local_xp_node; if (WARN_ON(!requested)) return -EACCES; rcu_read_lock(); node = avc_lookup(state->avc, ssid, tsid, tclass); if (unlikely(!node)) { node = avc_compute_av(state, ssid, tsid, tclass, &avd, xp_node); } else { memcpy(&avd, &node->ae.avd, sizeof(avd)); xp_node = node->ae.xp_node; } /* if extended permissions are not defined, only consider av_decision */ if (!xp_node || !xp_node->xp.len) goto decision; local_xpd.allowed = &allowed; local_xpd.auditallow = &auditallow; local_xpd.dontaudit = &dontaudit; xpd = avc_xperms_decision_lookup(driver, xp_node); if (unlikely(!xpd)) { /* * Compute the extended_perms_decision only if the driver * is flagged */ if (!security_xperm_test(xp_node->xp.drivers.p, driver)) { avd.allowed &= ~requested; goto decision; } rcu_read_unlock(); security_compute_xperms_decision(state, ssid, tsid, tclass, driver, &local_xpd); rcu_read_lock(); avc_update_node(state->avc, AVC_CALLBACK_ADD_XPERMS, requested, driver, xperm, ssid, tsid, tclass, avd.seqno, &local_xpd, 0); } else { avc_quick_copy_xperms_decision(xperm, &local_xpd, xpd); } xpd = &local_xpd; if (!avc_xperms_has_perm(xpd, xperm, XPERMS_ALLOWED)) avd.allowed &= ~requested; decision: denied = requested & ~(avd.allowed); if (unlikely(denied)) rc = avc_denied(state, ssid, tsid, tclass, requested, driver, xperm, AVC_EXTENDED_PERMS, &avd); rcu_read_unlock(); rc2 = avc_xperms_audit(state, ssid, tsid, tclass, requested, &avd, xpd, xperm, rc, ad); if (rc2) return rc2; return rc; } /** * avc_has_perm_noaudit - Check permissions but perform no auditing. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions, interpreted based on @tclass * @flags: AVC_STRICT, AVC_NONBLOCKING, or 0 * @avd: access vector decisions * * Check the AVC to determine whether the @requested permissions are granted * for the SID pair (@ssid, @tsid), interpreting the permissions * based on @tclass, and call the security server on a cache miss to obtain * a new decision and add it to the cache. Return a copy of the decisions * in @avd. Return %0 if all @requested permissions are granted, * -%EACCES if any permissions are denied, or another -errno upon * other errors. This function is typically called by avc_has_perm(), * but may also be called directly to separate permission checking from * auditing, e.g. in cases where a lock must be held for the check but * should be released for the auditing. */ inline int avc_has_perm_noaudit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, unsigned int flags, struct av_decision *avd) { struct avc_node *node; struct avc_xperms_node xp_node; int rc = 0; u32 denied; if (WARN_ON(!requested)) return -EACCES; rcu_read_lock(); node = avc_lookup(state->avc, ssid, tsid, tclass); if (unlikely(!node)) node = avc_compute_av(state, ssid, tsid, tclass, avd, &xp_node); else memcpy(avd, &node->ae.avd, sizeof(*avd)); denied = requested & ~(avd->allowed); if (unlikely(denied)) rc = avc_denied(state, ssid, tsid, tclass, requested, 0, 0, flags, avd); rcu_read_unlock(); return rc; } /** * avc_has_perm - Check permissions and perform any appropriate auditing. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions, interpreted based on @tclass * @auditdata: auxiliary audit data * * Check the AVC to determine whether the @requested permissions are granted * for the SID pair (@ssid, @tsid), interpreting the permissions * based on @tclass, and call the security server on a cache miss to obtain * a new decision and add it to the cache. Audit the granting or denial of * permissions in accordance with the policy. Return %0 if all @requested * permissions are granted, -%EACCES if any permissions are denied, or * another -errno upon other errors. */ int avc_has_perm(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata) { struct av_decision avd; int rc, rc2; rc = avc_has_perm_noaudit(state, ssid, tsid, tclass, requested, 0, &avd); rc2 = avc_audit(state, ssid, tsid, tclass, requested, &avd, rc, auditdata, 0); if (rc2) return rc2; return rc; } int avc_has_perm_flags(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata, int flags) { struct av_decision avd; int rc, rc2; rc = avc_has_perm_noaudit(state, ssid, tsid, tclass, requested, (flags & MAY_NOT_BLOCK) ? AVC_NONBLOCKING : 0, &avd); rc2 = avc_audit(state, ssid, tsid, tclass, requested, &avd, rc, auditdata, flags); if (rc2) return rc2; return rc; } u32 avc_policy_seqno(struct selinux_state *state) { return state->avc->avc_cache.latest_notif; } void avc_disable(void) { /* * If you are looking at this because you have realized that we are * not destroying the avc_node_cachep it might be easy to fix, but * I don't know the memory barrier semantics well enough to know. It's * possible that some other task dereferenced security_ops when * it still pointed to selinux operations. If that is the case it's * possible that it is about to use the avc and is about to need the * avc_node_cachep. I know I could wrap the security.c security_ops call * in an rcu_lock, but seriously, it's not worth it. Instead I just flush * the cache and get that memory back. */ if (avc_node_cachep) { avc_flush(selinux_state.avc); /* kmem_cache_destroy(avc_node_cachep); */ } } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMIOTRACE_H #define _LINUX_MMIOTRACE_H #include <linux/types.h> #include <linux/list.h> struct kmmio_probe; struct pt_regs; typedef void (*kmmio_pre_handler_t)(struct kmmio_probe *, struct pt_regs *, unsigned long addr); typedef void (*kmmio_post_handler_t)(struct kmmio_probe *, unsigned long condition, struct pt_regs *); struct kmmio_probe { /* kmmio internal list: */ struct list_head list; /* start location of the probe point: */ unsigned long addr; /* length of the probe region: */ unsigned long len; /* Called before addr is executed: */ kmmio_pre_handler_t pre_handler; /* Called after addr is executed: */ kmmio_post_handler_t post_handler; void *private; }; extern unsigned int kmmio_count; extern int register_kmmio_probe(struct kmmio_probe *p); extern void unregister_kmmio_probe(struct kmmio_probe *p); extern int kmmio_init(void); extern void kmmio_cleanup(void); #ifdef CONFIG_MMIOTRACE /* kmmio is active by some kmmio_probes? */ static inline int is_kmmio_active(void) { return kmmio_count; } /* Called from page fault handler. */ extern int kmmio_handler(struct pt_regs *regs, unsigned long addr); /* Called from ioremap.c */ extern void mmiotrace_ioremap(resource_size_t offset, unsigned long size, void __iomem *addr); extern void mmiotrace_iounmap(volatile void __iomem *addr); /* For anyone to insert markers. Remember trailing newline. */ extern __printf(1, 2) int mmiotrace_printk(const char *fmt, ...); #else /* !CONFIG_MMIOTRACE: */ static inline int is_kmmio_active(void) { return 0; } static inline int kmmio_handler(struct pt_regs *regs, unsigned long addr) { return 0; } static inline void mmiotrace_ioremap(resource_size_t offset, unsigned long size, void __iomem *addr) { } static inline void mmiotrace_iounmap(volatile void __iomem *addr) { } static inline __printf(1, 2) int mmiotrace_printk(const char *fmt, ...) { return 0; } #endif /* CONFIG_MMIOTRACE */ enum mm_io_opcode { MMIO_READ = 0x1, /* struct mmiotrace_rw */ MMIO_WRITE = 0x2, /* struct mmiotrace_rw */ MMIO_PROBE = 0x3, /* struct mmiotrace_map */ MMIO_UNPROBE = 0x4, /* struct mmiotrace_map */ MMIO_UNKNOWN_OP = 0x5, /* struct mmiotrace_rw */ }; struct mmiotrace_rw { resource_size_t phys; /* PCI address of register */ unsigned long value; unsigned long pc; /* optional program counter */ int map_id; unsigned char opcode; /* one of MMIO_{READ,WRITE,UNKNOWN_OP} */ unsigned char width; /* size of register access in bytes */ }; struct mmiotrace_map { resource_size_t phys; /* base address in PCI space */ unsigned long virt; /* base virtual address */ unsigned long len; /* mapping size */ int map_id; unsigned char opcode; /* MMIO_PROBE or MMIO_UNPROBE */ }; /* in kernel/trace/trace_mmiotrace.c */ extern void enable_mmiotrace(void); extern void disable_mmiotrace(void); extern void mmio_trace_rw(struct mmiotrace_rw *rw); extern void mmio_trace_mapping(struct mmiotrace_map *map); extern __printf(1, 0) int mmio_trace_printk(const char *fmt, va_list args); #endif /* _LINUX_MMIOTRACE_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM pagemap #if !defined(_TRACE_PAGEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGEMAP_H #include <linux/tracepoint.h> #include <linux/mm.h> #define PAGEMAP_MAPPED 0x0001u #define PAGEMAP_ANONYMOUS 0x0002u #define PAGEMAP_FILE 0x0004u #define PAGEMAP_SWAPCACHE 0x0008u #define PAGEMAP_SWAPBACKED 0x0010u #define PAGEMAP_MAPPEDDISK 0x0020u #define PAGEMAP_BUFFERS 0x0040u #define trace_pagemap_flags(page) ( \ (PageAnon(page) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ (page_mapped(page) ? PAGEMAP_MAPPED : 0) | \ (PageSwapCache(page) ? PAGEMAP_SWAPCACHE : 0) | \ (PageSwapBacked(page) ? PAGEMAP_SWAPBACKED : 0) | \ (PageMappedToDisk(page) ? PAGEMAP_MAPPEDDISK : 0) | \ (page_has_private(page) ? PAGEMAP_BUFFERS : 0) \ ) TRACE_EVENT(mm_lru_insertion, TP_PROTO( struct page *page, int lru ), TP_ARGS(page, lru), TP_STRUCT__entry( __field(struct page *, page ) __field(unsigned long, pfn ) __field(int, lru ) __field(unsigned long, flags ) ), TP_fast_assign( __entry->page = page; __entry->pfn = page_to_pfn(page); __entry->lru = lru; __entry->flags = trace_pagemap_flags(page); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("page=%p pfn=%lu lru=%d flags=%s%s%s%s%s%s", __entry->page, __entry->pfn, __entry->lru, __entry->flags & PAGEMAP_MAPPED ? "M" : " ", __entry->flags & PAGEMAP_ANONYMOUS ? "a" : "f", __entry->flags & PAGEMAP_SWAPCACHE ? "s" : " ", __entry->flags & PAGEMAP_SWAPBACKED ? "b" : " ", __entry->flags & PAGEMAP_MAPPEDDISK ? "d" : " ", __entry->flags & PAGEMAP_BUFFERS ? "B" : " ") ); TRACE_EVENT(mm_lru_activate, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field(struct page *, page ) __field(unsigned long, pfn ) ), TP_fast_assign( __entry->page = page; __entry->pfn = page_to_pfn(page); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("page=%p pfn=%lu", __entry->page, __entry->pfn) ); #endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NUMA memory policies for Linux. * Copyright 2003,2004 Andi Kleen SuSE Labs */ #ifndef _LINUX_MEMPOLICY_H #define _LINUX_MEMPOLICY_H 1 #include <linux/sched.h> #include <linux/mmzone.h> #include <linux/dax.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <uapi/linux/mempolicy.h> struct mm_struct; #ifdef CONFIG_NUMA /* * Describe a memory policy. * * A mempolicy can be either associated with a process or with a VMA. * For VMA related allocations the VMA policy is preferred, otherwise * the process policy is used. Interrupts ignore the memory policy * of the current process. * * Locking policy for interleave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when * mpol_put() decrements the reference count to zero. * * Duplicating policy objects: * mpol_dup() allocates a new mempolicy and copies the specified mempolicy * to the new storage. The reference count of the new object is initialized * to 1, representing the caller of mpol_dup(). */ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ union { short preferred_node; /* preferred */ nodemask_t nodes; /* interleave/bind */ /* undefined for default */ } v; union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; }; /* * Support for managing mempolicy data objects (clone, copy, destroy) * The default fast path of a NULL MPOL_DEFAULT policy is always inlined. */ extern void __mpol_put(struct mempolicy *pol); static inline void mpol_put(struct mempolicy *pol) { if (pol) __mpol_put(pol); } /* * Does mempolicy pol need explicit unref after use? * Currently only needed for shared policies. */ static inline int mpol_needs_cond_ref(struct mempolicy *pol) { return (pol && (pol->flags & MPOL_F_SHARED)); } static inline void mpol_cond_put(struct mempolicy *pol) { if (mpol_needs_cond_ref(pol)) __mpol_put(pol); } extern struct mempolicy *__mpol_dup(struct mempolicy *pol); static inline struct mempolicy *mpol_dup(struct mempolicy *pol) { if (pol) pol = __mpol_dup(pol); return pol; } #define vma_policy(vma) ((vma)->vm_policy) static inline void mpol_get(struct mempolicy *pol) { if (pol) atomic_inc(&pol->refcnt); } extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b); static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (a == b) return true; return __mpol_equal(a, b); } /* * Tree of shared policies for a shared memory region. * Maintain the policies in a pseudo mm that contains vmas. The vmas * carry the policy. As a special twist the pseudo mm is indexed in pages, not * bytes, so that we can work with shared memory segments bigger than * unsigned long. */ struct sp_node { struct rb_node nd; unsigned long start, end; struct mempolicy *policy; }; struct shared_policy { struct rb_root root; rwlock_t lock; }; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); int mpol_set_shared_policy(struct shared_policy *info, struct vm_area_struct *vma, struct mempolicy *new); void mpol_free_shared_policy(struct shared_policy *p); struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx); struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); extern void numa_policy_init(void); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern bool mempolicy_nodemask_intersects(struct task_struct *tsk, const nodemask_t *mask); extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy); static inline nodemask_t *policy_nodemask_current(gfp_t gfp) { struct mempolicy *mpol = get_task_policy(current); return policy_nodemask(gfp, mpol); } extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; static inline void check_highest_zone(enum zone_type k) { if (k > policy_zone && k != ZONE_MOVABLE) policy_zone = k; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags); #ifdef CONFIG_TMPFS extern int mpol_parse_str(char *str, struct mempolicy **mpol); #endif extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); extern void mpol_put_task_policy(struct task_struct *); #else struct mempolicy {}; static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { return true; } static inline void mpol_put(struct mempolicy *p) { } static inline void mpol_cond_put(struct mempolicy *pol) { } static inline void mpol_get(struct mempolicy *pol) { } struct shared_policy {}; static inline void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { } static inline void mpol_free_shared_policy(struct shared_policy *p) { } static inline struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) { return NULL; } #define vma_policy(vma) NULL static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { return 0; } static inline void numa_policy_init(void) { } static inline void numa_default_policy(void) { } static inline void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { } static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } static inline int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { *mpol = NULL; *nodemask = NULL; return 0; } static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return 0; } static inline void check_highest_zone(int k) { } #ifdef CONFIG_TMPFS static inline int mpol_parse_str(char *str, struct mempolicy **mpol) { return 1; /* error */ } #endif static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long address) { return -1; /* no node preference */ } static inline void mpol_put_task_policy(struct task_struct *task) { } static inline nodemask_t *policy_nodemask_current(gfp_t gfp) { return NULL; } #endif /* CONFIG_NUMA */ #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_NOTIFY_H #define _LINUX_FS_NOTIFY_H /* * include/linux/fsnotify.h - generic hooks for filesystem notification, to * reduce in-source duplication from both dnotify and inotify. * * We don't compile any of this away in some complicated menagerie of ifdefs. * Instead, we rely on the code inside to optimize away as needed. * * (C) Copyright 2005 Robert Love */ #include <linux/fsnotify_backend.h> #include <linux/audit.h> #include <linux/slab.h> #include <linux/bug.h> /* * Notify this @dir inode about a change in a child directory entry. * The directory entry may have turned positive or negative or its inode may * have changed (i.e. renamed over). * * Unlike fsnotify_parent(), the event will be reported regardless of the * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ static inline int fsnotify_name(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0) return 0; return fsnotify(mask, data, data_type, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) { if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0) return; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify(mask, inode, FSNOTIFY_EVENT_INODE, NULL, NULL, inode, 0); } /* Notify this dentry's parent about a child's events. */ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { struct inode *inode = d_inode(dentry); if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0) return 0; if (S_ISDIR(inode->i_mode)) { mask |= FS_ISDIR; /* sb/mount marks are not interested in name of directory */ if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) goto notify_child; } /* disconnected dentry cannot notify parent */ if (IS_ROOT(dentry)) goto notify_child; return __fsnotify_parent(dentry, mask, data, data_type); notify_child: return fsnotify(mask, data, data_type, NULL, NULL, inode, 0); } /* * Simple wrappers to consolidate calls to fsnotify_parent() when an event * is on a file/dentry. */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } static inline int fsnotify_file(struct file *file, __u32 mask) { const struct path *path = &file->f_path; /* * FMODE_NONOTIFY are fds generated by fanotify itself which should not * generate new events. We also don't want to generate events for * FMODE_PATH fds (involves open & close events) as they are just * handle creation / destruction events and not "real" file events. */ if (file->f_mode & (FMODE_NONOTIFY | FMODE_PATH)) return 0; return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } /* Simple call site for access decisions */ static inline int fsnotify_perm(struct file *file, int mask) { int ret; __u32 fsnotify_mask = 0; if (!(mask & (MAY_READ | MAY_OPEN))) return 0; if (mask & MAY_OPEN) { fsnotify_mask = FS_OPEN_PERM; if (file->f_flags & __FMODE_EXEC) { ret = fsnotify_file(file, FS_OPEN_EXEC_PERM); if (ret) return ret; } } else if (mask & MAY_READ) { fsnotify_mask = FS_ACCESS_PERM; } return fsnotify_file(file, fsnotify_mask); } /* * fsnotify_link_count - inode's link count changed */ static inline void fsnotify_link_count(struct inode *inode) { fsnotify_inode(inode, FS_ATTRIB); } /* * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir */ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, const struct qstr *old_name, int isdir, struct inode *target, struct dentry *moved) { struct inode *source = moved->d_inode; u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; __u32 rename_mask = FS_RENAME; const struct qstr *new_name = &moved->d_name; if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; rename_mask |= FS_ISDIR; } /* Event with information about both old and new parent+name */ fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY, old_dir, old_name, 0); fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_dir, old_name, fs_cookie); fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_dir, new_name, fs_cookie); if (target) fsnotify_link_count(target); fsnotify_inode(source, FS_MOVE_SELF); audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE); } /* * fsnotify_inode_delete - and inode is being evicted from cache, clean up is needed */ static inline void fsnotify_inode_delete(struct inode *inode) { __fsnotify_inode_delete(inode); } /* * fsnotify_vfsmount_delete - a vfsmount is being destroyed, clean up is needed */ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) { __fsnotify_vfsmount_delete(mnt); } /* * fsnotify_inoderemove - an inode is going away */ static inline void fsnotify_inoderemove(struct inode *inode) { fsnotify_inode(inode, FS_DELETE_SELF); __fsnotify_inode_delete(inode); } /* * fsnotify_create - 'name' was linked in * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_create(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory * * Caller must make sure that new_dentry->d_name is stable. * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry) { fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE, dir, &new_dentry->d_name, 0); } /* * fsnotify_delete - @dentry was unlinked and unhashed * * Caller must make sure that dentry->d_name is stable. * * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode * as this may be called after d_delete() and old_dentry may be negative. */ static inline void fsnotify_delete(struct inode *dir, struct inode *inode, struct dentry *dentry) { __u32 mask = FS_DELETE; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, 0); } /** * d_delete_notify - delete a dentry and call fsnotify_delete() * @dentry: The dentry to delete * * This helper is used to guaranty that the unlinked inode cannot be found * by lookup of this name after fsnotify_delete() event has been delivered. */ static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); ihold(inode); d_delete(dentry); fsnotify_delete(dir, inode, dentry); iput(inode); } /* * fsnotify_unlink - 'name' was unlinked * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_mkdir - directory 'name' was created * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR); } /* * fsnotify_rmdir - directory 'name' was removed * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_access - file was read */ static inline void fsnotify_access(struct file *file) { fsnotify_file(file, FS_ACCESS); } /* * fsnotify_modify - file was modified */ static inline void fsnotify_modify(struct file *file) { fsnotify_file(file, FS_MODIFY); } /* * fsnotify_open - file was opened */ static inline void fsnotify_open(struct file *file) { __u32 mask = FS_OPEN; if (file->f_flags & __FMODE_EXEC) mask |= FS_OPEN_EXEC; fsnotify_file(file, mask); } /* * fsnotify_close - file was closed */ static inline void fsnotify_close(struct file *file) { __u32 mask = (file->f_mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; fsnotify_file(file, mask); } /* * fsnotify_xattr - extended attributes were changed */ static inline void fsnotify_xattr(struct dentry *dentry) { fsnotify_dentry(dentry, FS_ATTRIB); } /* * fsnotify_change - notify_change event. file was modified and/or metadata * was changed. */ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) { __u32 mask = 0; if (ia_valid & ATTR_UID) mask |= FS_ATTRIB; if (ia_valid & ATTR_GID) mask |= FS_ATTRIB; if (ia_valid & ATTR_SIZE) mask |= FS_MODIFY; /* both times implies a utime(s) call */ if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME)) mask |= FS_ATTRIB; else if (ia_valid & ATTR_ATIME) mask |= FS_ACCESS; else if (ia_valid & ATTR_MTIME) mask |= FS_MODIFY; if (ia_valid & ATTR_MODE) mask |= FS_ATTRIB; if (mask) fsnotify_dentry(dentry, mask); } static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, int error) { struct fs_error_report report = { .error = error, .inode = inode, .sb = sb, }; return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, NULL, NULL, NULL, 0); } #endif /* _LINUX_FS_NOTIFY_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic pidhash and scalable, time-bounded PID allocator * * (C) 2002-2003 Nadia Yvette Chambers, IBM * (C) 2004 Nadia Yvette Chambers, Oracle * (C) 2002-2004 Ingo Molnar, Red Hat * * pid-structures are backing objects for tasks sharing a given ID to chain * against. There is very little to them aside from hashing them and * parking tasks using given ID's on a list. * * The hash is always changed with the tasklist_lock write-acquired, * and the hash is only accessed with the tasklist_lock at least * read-acquired, so there's no additional SMP locking needed here. * * We have a list of bitmap pages, which bitmaps represent the PID space. * Allocating and freeing PIDs is completely lockless. The worst-case * allocation scenario when all but one out of 1 million PIDs possible are * allocated already: the scanning of 32 list entries and at most PAGE_SIZE * bytes. The typical fastpath is a single successful setbit. Freeing is O(1). * * Pid namespaces: * (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc. * (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM * Many thanks to Oleg Nesterov for comments and help * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/memblock.h> #include <linux/pid_namespace.h> #include <linux/init_task.h> #include <linux/syscalls.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/anon_inodes.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h> #include <net/sock.h> #include <uapi/linux/pidfd.h> struct pid init_struct_pid = { .count = REFCOUNT_INIT(1), .tasks = { { .first = NULL }, { .first = NULL }, { .first = NULL }, }, .level = 0, .numbers = { { .nr = 0, .ns = &init_pid_ns, }, } }; int pid_max = PID_MAX_DEFAULT; #define RESERVED_PIDS 300 int pid_max_min = RESERVED_PIDS + 1; int pid_max_max = PID_MAX_LIMIT; /* * PID-map pages start out as NULL, they get allocated upon * first use and are never deallocated. This way a low pid_max * value does not cause lots of bitmaps to be allocated, but * the scheme scales to up to 4 million PIDs, runtime. */ struct pid_namespace init_pid_ns = { .kref = KREF_INIT(2), .idr = IDR_INIT(init_pid_ns.idr), .pid_allocated = PIDNS_ADDING, .level = 0, .child_reaper = &init_task, .user_ns = &init_user_ns, .ns.inum = PROC_PID_INIT_INO, #ifdef CONFIG_PID_NS .ns.ops = &pidns_operations, #endif }; EXPORT_SYMBOL_GPL(init_pid_ns); /* * Note: disable interrupts while the pidmap_lock is held as an * interrupt might come in and do read_lock(&tasklist_lock). * * If we don't disable interrupts there is a nasty deadlock between * detach_pid()->free_pid() and another cpu that does * spin_lock(&pidmap_lock) followed by an interrupt routine that does * read_lock(&tasklist_lock); * * After we clean up the tasklist_lock and know there are no * irq handlers that take it we can leave the interrupts enabled. * For now it is easier to be safe than to prove it can't happen. */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); void put_pid(struct pid *pid) { struct pid_namespace *ns; if (!pid) return; ns = pid->numbers[pid->level].ns; if (refcount_dec_and_test(&pid->count)) { kmem_cache_free(ns->pid_cachep, pid); put_pid_ns(ns); } } EXPORT_SYMBOL_GPL(put_pid); static void delayed_put_pid(struct rcu_head *rhp) { struct pid *pid = container_of(rhp, struct pid, rcu); put_pid(pid); } void free_pid(struct pid *pid) { /* We can be called with write_lock_irq(&tasklist_lock) held */ int i; unsigned long flags; spin_lock_irqsave(&pidmap_lock, flags); for (i = 0; i <= pid->level; i++) { struct upid *upid = pid->numbers + i; struct pid_namespace *ns = upid->ns; switch (--ns->pid_allocated) { case 2: case 1: /* When all that is left in the pid namespace * is the reaper wake up the reaper. The reaper * may be sleeping in zap_pid_ns_processes(). */ wake_up_process(ns->child_reaper); break; case PIDNS_ADDING: /* Handle a fork failure of the first process */ WARN_ON(ns->child_reaper); ns->pid_allocated = 0; break; } idr_remove(&ns->idr, upid->nr); } spin_unlock_irqrestore(&pidmap_lock, flags); call_rcu(&pid->rcu, delayed_put_pid); } struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size) { struct pid *pid; enum pid_type type; int i, nr; struct pid_namespace *tmp; struct upid *upid; int retval = -ENOMEM; /* * set_tid_size contains the size of the set_tid array. Starting at * the most nested currently active PID namespace it tells alloc_pid() * which PID to set for a process in that most nested PID namespace * up to set_tid_size PID namespaces. It does not have to set the PID * for a process in all nested PID namespaces but set_tid_size must * never be greater than the current ns->level + 1. */ if (set_tid_size > ns->level + 1) return ERR_PTR(-EINVAL); pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); if (!pid) return ERR_PTR(retval); tmp = ns; pid->level = ns->level; for (i = ns->level; i >= 0; i--) { int tid = 0; if (set_tid_size) { tid = set_tid[ns->level - i]; retval = -EINVAL; if (tid < 1 || tid >= pid_max) goto out_free; /* * Also fail if a PID != 1 is requested and * no PID 1 exists. */ if (tid != 1 && !tmp->child_reaper) goto out_free; retval = -EPERM; if (!checkpoint_restore_ns_capable(tmp->user_ns)) goto out_free; set_tid_size--; } idr_preload(GFP_KERNEL); spin_lock_irq(&pidmap_lock); if (tid) { nr = idr_alloc(&tmp->idr, NULL, tid, tid + 1, GFP_ATOMIC); /* * If ENOSPC is returned it means that the PID is * alreay in use. Return EEXIST in that case. */ if (nr == -ENOSPC) nr = -EEXIST; } else { int pid_min = 1; /* * init really needs pid 1, but after reaching the * maximum wrap back to RESERVED_PIDS */ if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) pid_min = RESERVED_PIDS; /* * Store a null pointer so find_pid_ns does not find * a partially initialized PID (see below). */ nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, pid_max, GFP_ATOMIC); } spin_unlock_irq(&pidmap_lock); idr_preload_end(); if (nr < 0) { retval = (nr == -ENOSPC) ? -EAGAIN : nr; goto out_free; } pid->numbers[i].nr = nr; pid->numbers[i].ns = tmp; tmp = tmp->parent; } /* * ENOMEM is not the most obvious choice especially for the case * where the child subreaper has already exited and the pid * namespace denies the creation of any new processes. But ENOMEM * is what we have exposed to userspace for a long time and it is * documented behavior for pid namespaces. So we can't easily * change it even if there were an error code better suited. */ retval = -ENOMEM; get_pid_ns(ns); refcount_set(&pid->count, 1); spin_lock_init(&pid->lock); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); init_waitqueue_head(&pid->wait_pidfd); INIT_HLIST_HEAD(&pid->inodes); upid = pid->numbers + ns->level; spin_lock_irq(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) goto out_unlock; for ( ; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); upid->ns->pid_allocated++; } spin_unlock_irq(&pidmap_lock); return pid; out_unlock: spin_unlock_irq(&pidmap_lock); put_pid_ns(ns); out_free: spin_lock_irq(&pidmap_lock); while (++i <= ns->level) { upid = pid->numbers + i; idr_remove(&upid->ns->idr, upid->nr); } /* On failure to allocate the first pid, reset the state */ if (ns->pid_allocated == PIDNS_ADDING) idr_set_cursor(&ns->idr, 0); spin_unlock_irq(&pidmap_lock); kmem_cache_free(ns->pid_cachep, pid); return ERR_PTR(retval); } void disable_pid_allocation(struct pid_namespace *ns) { spin_lock_irq(&pidmap_lock); ns->pid_allocated &= ~PIDNS_ADDING; spin_unlock_irq(&pidmap_lock); } struct pid *find_pid_ns(int nr, struct pid_namespace *ns) { return idr_find(&ns->idr, nr); } EXPORT_SYMBOL_GPL(find_pid_ns); struct pid *find_vpid(int nr) { return find_pid_ns(nr, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(find_vpid); static struct pid **task_pid_ptr(struct task_struct *task, enum pid_type type) { return (type == PIDTYPE_PID) ? &task->thread_pid : &task->signal->pids[type]; } /* * attach_pid() must be called with the tasklist_lock write-held. */ void attach_pid(struct task_struct *task, enum pid_type type) { struct pid *pid = *task_pid_ptr(task, type); hlist_add_head_rcu(&task->pid_links[type], &pid->tasks[type]); } static void __change_pid(struct task_struct *task, enum pid_type type, struct pid *new) { struct pid **pid_ptr = task_pid_ptr(task, type); struct pid *pid; int tmp; pid = *pid_ptr; hlist_del_rcu(&task->pid_links[type]); *pid_ptr = new; for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pid_has_task(pid, tmp)) return; free_pid(pid); } void detach_pid(struct task_struct *task, enum pid_type type) { __change_pid(task, type, NULL); } void change_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { __change_pid(task, type, pid); attach_pid(task, type); } void exchange_tids(struct task_struct *left, struct task_struct *right) { struct pid *pid1 = left->thread_pid; struct pid *pid2 = right->thread_pid; struct hlist_head *head1 = &pid1->tasks[PIDTYPE_PID]; struct hlist_head *head2 = &pid2->tasks[PIDTYPE_PID]; /* Swap the single entry tid lists */ hlists_swap_heads_rcu(head1, head2); /* Swap the per task_struct pid */ rcu_assign_pointer(left->thread_pid, pid2); rcu_assign_pointer(right->thread_pid, pid1); /* Swap the cached value */ WRITE_ONCE(left->pid, pid_nr(pid2)); WRITE_ONCE(right->pid, pid_nr(pid1)); } /* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */ void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type type) { if (type == PIDTYPE_PID) new->thread_pid = old->thread_pid; hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]); } struct task_struct *pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result = NULL; if (pid) { struct hlist_node *first; first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]), lockdep_tasklist_lock_is_held()); if (first) result = hlist_entry(first, struct task_struct, pid_links[(type)]); } return result; } EXPORT_SYMBOL(pid_task); /* * Must be called under rcu_read_lock(). */ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "find_task_by_pid_ns() needs rcu_read_lock() protection"); return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); } struct task_struct *find_task_by_vpid(pid_t vnr) { return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); } struct task_struct *find_get_task_by_vpid(pid_t nr) { struct task_struct *task; rcu_read_lock(); task = find_task_by_vpid(nr); if (task) get_task_struct(task); rcu_read_unlock(); return task; } struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; rcu_read_lock(); pid = get_pid(rcu_dereference(*task_pid_ptr(task, type))); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(get_task_pid); struct task_struct *get_pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result; rcu_read_lock(); result = pid_task(pid, type); if (result) get_task_struct(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(get_pid_task); struct pid *find_get_pid(pid_t nr) { struct pid *pid; rcu_read_lock(); pid = get_pid(find_vpid(nr)); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(find_get_pid); pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns) { struct upid *upid; pid_t nr = 0; if (pid && ns->level <= pid->level) { upid = &pid->numbers[ns->level]; if (upid->ns == ns) nr = upid->nr; } return nr; } EXPORT_SYMBOL_GPL(pid_nr_ns); pid_t pid_vnr(struct pid *pid) { return pid_nr_ns(pid, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(pid_vnr); pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns) { pid_t nr = 0; rcu_read_lock(); if (!ns) ns = task_active_pid_ns(current); nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns); rcu_read_unlock(); return nr; } EXPORT_SYMBOL(__task_pid_nr_ns); struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); } EXPORT_SYMBOL_GPL(task_active_pid_ns); /* * Used by proc to find the first pid that is greater than or equal to nr. * * If there is a pid at nr this function is exactly the same as find_pid_ns. */ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) { return idr_get_next(&ns->idr, &nr); } struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) { struct fd f; struct pid *pid; f = fdget(fd); if (!f.file) return ERR_PTR(-EBADF); pid = pidfd_pid(f.file); if (!IS_ERR(pid)) { get_pid(pid); *flags = f.file->f_flags; } fdput(f); return pid; } /** * pidfd_create() - Create a new pid file descriptor. * * @pid: struct pid that the pidfd will reference * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set. * * Note, that this function can only be called after the fd table has * been unshared to avoid leaking the pidfd to the new process. * * This symbol should not be explicitly exported to loadable modules. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ int pidfd_create(struct pid *pid, unsigned int flags) { int fd; if (!pid || !pid_has_task(pid, PIDTYPE_TGID)) return -EINVAL; if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC)) return -EINVAL; fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid), flags | O_RDWR | O_CLOEXEC); if (fd < 0) put_pid(pid); return fd; } /** * pidfd_open() - Open new pid file descriptor. * * @pid: pid for which to retrieve a pidfd * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set for * the process identified by @pid. Currently, the process identified by * @pid must be a thread-group leader. This restriction currently exists * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot * be used with CLONE_THREAD) and pidfd polling (only supports thread group * leaders). * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; struct pid *p; if (flags & ~PIDFD_NONBLOCK) return -EINVAL; if (pid <= 0) return -EINVAL; p = find_get_pid(pid); if (!p) return -ESRCH; fd = pidfd_create(p, flags); put_pid(p); return fd; } void __init pid_idr_init(void) { /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING); /* bump default and minimum pid_max based on number of cpus */ pid_max = min(pid_max_max, max_t(int, pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pid_max_min = max_t(int, pid_max_min, PIDS_PER_CPU_MIN * num_possible_cpus()); pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min); idr_init(&init_pid_ns.idr); init_pid_ns.pid_cachep = KMEM_CACHE(pid, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); } static struct file *__pidfd_fget(struct task_struct *task, int fd) { struct file *file; int ret; ret = down_read_killable(&task->signal->exec_update_lock); if (ret) return ERR_PTR(ret); if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS)) file = fget_task(task, fd); else file = ERR_PTR(-EPERM); up_read(&task->signal->exec_update_lock); return file ?: ERR_PTR(-EBADF); } static int pidfd_getfd(struct pid *pid, int fd) { struct task_struct *task; struct file *file; int ret; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; file = __pidfd_fget(task, fd); put_task_struct(task); if (IS_ERR(file)) return PTR_ERR(file); ret = receive_fd(file, O_CLOEXEC); fput(file); return ret; } /** * sys_pidfd_getfd() - Get a file descriptor from another process * * @pidfd: the pidfd file descriptor of the process * @fd: the file descriptor number to get * @flags: flags on how to get the fd (reserved) * * This syscall gets a copy of a file descriptor from another process * based on the pidfd, and file descriptor number. It requires that * the calling process has the ability to ptrace the process represented * by the pidfd. The process which is having its file descriptor copied * is otherwise unaffected. * * Return: On success, a cloexec file descriptor is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd, unsigned int, flags) { struct pid *pid; struct fd f; int ret; /* flags is currently unused - make sure it's unset */ if (flags) return -EINVAL; f = fdget(pidfd); if (!f.file) return -EBADF; pid = pidfd_pid(f.file); if (IS_ERR(pid)) ret = PTR_ERR(pid); else ret = pidfd_getfd(pid, fd); fdput(f); return ret; } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/locks.c * * Provide support for fcntl()'s F_GETLK, F_SETLK, and F_SETLKW calls. * Doug Evans (dje@spiff.uucp), August 07, 1992 * * Deadlock detection added. * FIXME: one thing isn't handled yet: * - mandatory locks (requires lots of changes elsewhere) * Kelly Carmichael (kelly@[142.24.8.65]), September 17, 1994. * * Miscellaneous edits, and a total rewrite of posix_lock_file() code. * Kai Petzke (wpp@marie.physik.tu-berlin.de), 1994 * * Converted file_lock_table to a linked list from an array, which eliminates * the limits on how many active file locks are open. * Chad Page (pageone@netcom.com), November 27, 1994 * * Removed dependency on file descriptors. dup()'ed file descriptors now * get the same locks as the original file descriptors, and a close() on * any file descriptor removes ALL the locks on the file for the current * process. Since locks still depend on the process id, locks are inherited * after an exec() but not after a fork(). This agrees with POSIX, and both * BSD and SVR4 practice. * Andy Walker (andy@lysaker.kvaerner.no), February 14, 1995 * * Scrapped free list which is redundant now that we allocate locks * dynamically with kmalloc()/kfree(). * Andy Walker (andy@lysaker.kvaerner.no), February 21, 1995 * * Implemented two lock personalities - FL_FLOCK and FL_POSIX. * * FL_POSIX locks are created with calls to fcntl() and lockf() through the * fcntl() system call. They have the semantics described above. * * FL_FLOCK locks are created with calls to flock(), through the flock() * system call, which is new. Old C libraries implement flock() via fcntl() * and will continue to use the old, broken implementation. * * FL_FLOCK locks follow the 4.4 BSD flock() semantics. They are associated * with a file pointer (filp). As a result they can be shared by a parent * process and its children after a fork(). They are removed when the last * file descriptor referring to the file pointer is closed (unless explicitly * unlocked). * * FL_FLOCK locks never deadlock, an existing lock is always removed before * upgrading from shared to exclusive (or vice versa). When this happens * any processes blocked by the current lock are woken up and allowed to * run before the new lock is applied. * Andy Walker (andy@lysaker.kvaerner.no), June 09, 1995 * * Removed some race conditions in flock_lock_file(), marked other possible * races. Just grep for FIXME to see them. * Dmitry Gorodchanin (pgmdsg@ibi.com), February 09, 1996. * * Addressed Dmitry's concerns. Deadlock checking no longer recursive. * Lock allocation changed to GFP_ATOMIC as we can't afford to sleep * once we've checked for blocking and deadlocking. * Andy Walker (andy@lysaker.kvaerner.no), April 03, 1996. * * Initial implementation of mandatory locks. SunOS turned out to be * a rotten model, so I implemented the "obvious" semantics. * See 'Documentation/filesystems/mandatory-locking.rst' for details. * Andy Walker (andy@lysaker.kvaerner.no), April 06, 1996. * * Don't allow mandatory locks on mmap()'ed files. Added simple functions to * check if a file has mandatory locks, used by mmap(), open() and creat() to * see if system call should be rejected. Ref. HP-UX/SunOS/Solaris Reference * Manual, Section 2. * Andy Walker (andy@lysaker.kvaerner.no), April 09, 1996. * * Tidied up block list handling. Added '/proc/locks' interface. * Andy Walker (andy@lysaker.kvaerner.no), April 24, 1996. * * Fixed deadlock condition for pathological code that mixes calls to * flock() and fcntl(). * Andy Walker (andy@lysaker.kvaerner.no), April 29, 1996. * * Allow only one type of locking scheme (FL_POSIX or FL_FLOCK) to be in use * for a given file at a time. Changed the CONFIG_LOCK_MANDATORY scheme to * guarantee sensible behaviour in the case where file system modules might * be compiled with different options than the kernel itself. * Andy Walker (andy@lysaker.kvaerner.no), May 15, 1996. * * Added a couple of missing wake_up() calls. Thanks to Thomas Meckel * (Thomas.Meckel@mni.fh-giessen.de) for spotting this. * Andy Walker (andy@lysaker.kvaerner.no), May 15, 1996. * * Changed FL_POSIX locks to use the block list in the same way as FL_FLOCK * locks. Changed process synchronisation to avoid dereferencing locks that * have already been freed. * Andy Walker (andy@lysaker.kvaerner.no), Sep 21, 1996. * * Made the block list a circular list to minimise searching in the list. * Andy Walker (andy@lysaker.kvaerner.no), Sep 25, 1996. * * Made mandatory locking a mount option. Default is not to allow mandatory * locking. * Andy Walker (andy@lysaker.kvaerner.no), Oct 04, 1996. * * Some adaptations for NFS support. * Olaf Kirch (okir@monad.swb.de), Dec 1996, * * Fixed /proc/locks interface so that we can't overrun the buffer we are handed. * Andy Walker (andy@lysaker.kvaerner.no), May 12, 1997. * * Use slab allocator instead of kmalloc/kfree. * Use generic list implementation from <linux/list.h>. * Sped up posix_locks_deadlock by only considering blocked locks. * Matthew Wilcox <willy@debian.org>, March, 2000. * * Leases and LOCK_MAND * Matthew Wilcox <willy@debian.org>, June, 2000. * Stephen Rothwell <sfr@canb.auug.org.au>, June, 2000. * * Locking conflicts and dependencies: * If multiple threads attempt to lock the same byte (or flock the same file) * only one can be granted the lock, and other must wait their turn. * The first lock has been "applied" or "granted", the others are "waiting" * and are "blocked" by the "applied" lock.. * * Waiting and applied locks are all kept in trees whose properties are: * * - the root of a tree may be an applied or waiting lock. * - every other node in the tree is a waiting lock that * conflicts with every ancestor of that node. * * Every such tree begins life as a waiting singleton which obviously * satisfies the above properties. * * The only ways we modify trees preserve these properties: * * 1. We may add a new leaf node, but only after first verifying that it * conflicts with all of its ancestors. * 2. We may remove the root of a tree, creating a new singleton * tree from the root and N new trees rooted in the immediate * children. * 3. If the root of a tree is not currently an applied lock, we may * apply it (if possible). * 4. We may upgrade the root of the tree (either extend its range, * or upgrade its entire range from read to write). * * When an applied lock is modified in a way that reduces or downgrades any * part of its range, we remove all its children (2 above). This particularly * happens when a lock is unlocked. * * For each of those child trees we "wake up" the thread which is * waiting for the lock so it can continue handling as follows: if the * root of the tree applies, we do so (3). If it doesn't, it must * conflict with some applied lock. We remove (wake up) all of its children * (2), and add it is a new leaf to the tree rooted in the applied * lock (1). We then repeat the process recursively with those * children. * */ #include <linux/capability.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/time.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/hashtable.h> #include <linux/percpu.h> #define CREATE_TRACE_POINTS #include <trace/events/filelock.h> #include <linux/uaccess.h> #define IS_POSIX(fl) (fl->fl_flags & FL_POSIX) #define IS_FLOCK(fl) (fl->fl_flags & FL_FLOCK) #define IS_LEASE(fl) (fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) #define IS_OFDLCK(fl) (fl->fl_flags & FL_OFDLCK) #define IS_REMOTELCK(fl) (fl->fl_pid <= 0) static bool lease_breaking(struct file_lock *fl) { return fl->fl_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING); } static int target_leasetype(struct file_lock *fl) { if (fl->fl_flags & FL_UNLOCK_PENDING) return F_UNLCK; if (fl->fl_flags & FL_DOWNGRADE_PENDING) return F_RDLCK; return fl->fl_type; } int leases_enable = 1; int lease_break_time = 45; /* * The global file_lock_list is only used for displaying /proc/locks, so we * keep a list on each CPU, with each list protected by its own spinlock. * Global serialization is done using file_rwsem. * * Note that alterations to the list also require that the relevant flc_lock is * held. */ struct file_lock_list_struct { spinlock_t lock; struct hlist_head hlist; }; static DEFINE_PER_CPU(struct file_lock_list_struct, file_lock_list); DEFINE_STATIC_PERCPU_RWSEM(file_rwsem); /* * The blocked_hash is used to find POSIX lock loops for deadlock detection. * It is protected by blocked_lock_lock. * * We hash locks by lockowner in order to optimize searching for the lock a * particular lockowner is waiting on. * * FIXME: make this value scale via some heuristic? We generally will want more * buckets when we have more lockowners holding locks, but that's a little * difficult to determine without knowing what the workload will look like. */ #define BLOCKED_HASH_BITS 7 static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); /* * This lock protects the blocked_hash. Generally, if you're accessing it, you * want to be holding this lock. * * In addition, it also protects the fl->fl_blocked_requests list, and the * fl->fl_blocker pointer for file_lock structures that are acting as lock * requests (in contrast to those that are acting as records of acquired locks). * * Note that when we acquire this lock in order to change the above fields, * we often hold the flc_lock as well. In certain cases, when reading the fields * protected by this lock, we can skip acquiring it iff we already hold the * flc_lock. */ static DEFINE_SPINLOCK(blocked_lock_lock); static struct kmem_cache *flctx_cache __read_mostly; static struct kmem_cache *filelock_cache __read_mostly; static struct file_lock_context * locks_get_lock_context(struct inode *inode, int type) { struct file_lock_context *ctx; /* paired with cmpxchg() below */ ctx = locks_inode_context(inode); if (likely(ctx) || type == F_UNLCK) goto out; ctx = kmem_cache_alloc(flctx_cache, GFP_KERNEL); if (!ctx) goto out; spin_lock_init(&ctx->flc_lock); INIT_LIST_HEAD(&ctx->flc_flock); INIT_LIST_HEAD(&ctx->flc_posix); INIT_LIST_HEAD(&ctx->flc_lease); /* * Assign the pointer if it's not already assigned. If it is, then * free the context we just allocated. */ if (cmpxchg(&inode->i_flctx, NULL, ctx)) { kmem_cache_free(flctx_cache, ctx); ctx = locks_inode_context(inode); } out: trace_locks_get_lock_context(inode, type, ctx); return ctx; } static void locks_dump_ctx_list(struct list_head *list, char *list_type) { struct file_lock *fl; list_for_each_entry(fl, list, fl_list) { pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid); } } static void locks_check_ctx_lists(struct inode *inode) { struct file_lock_context *ctx = inode->i_flctx; if (unlikely(!list_empty(&ctx->flc_flock) || !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_lease))) { pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%lx:\n", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); locks_dump_ctx_list(&ctx->flc_flock, "FLOCK"); locks_dump_ctx_list(&ctx->flc_posix, "POSIX"); locks_dump_ctx_list(&ctx->flc_lease, "LEASE"); } } static void locks_check_ctx_file_list(struct file *filp, struct list_head *list, char *list_type) { struct file_lock *fl; struct inode *inode = locks_inode(filp); list_for_each_entry(fl, list, fl_list) if (fl->fl_file == filp) pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%lx " " fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino, fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid); } void locks_free_lock_context(struct inode *inode) { struct file_lock_context *ctx = locks_inode_context(inode); if (unlikely(ctx)) { locks_check_ctx_lists(inode); kmem_cache_free(flctx_cache, ctx); } } static void locks_init_lock_heads(struct file_lock *fl) { INIT_HLIST_NODE(&fl->fl_link); INIT_LIST_HEAD(&fl->fl_list); INIT_LIST_HEAD(&fl->fl_blocked_requests); INIT_LIST_HEAD(&fl->fl_blocked_member); init_waitqueue_head(&fl->fl_wait); } /* Allocate an empty lock structure. */ struct file_lock *locks_alloc_lock(void) { struct file_lock *fl = kmem_cache_zalloc(filelock_cache, GFP_KERNEL); if (fl) locks_init_lock_heads(fl); return fl; } EXPORT_SYMBOL_GPL(locks_alloc_lock); void locks_release_private(struct file_lock *fl) { BUG_ON(waitqueue_active(&fl->fl_wait)); BUG_ON(!list_empty(&fl->fl_list)); BUG_ON(!list_empty(&fl->fl_blocked_requests)); BUG_ON(!list_empty(&fl->fl_blocked_member)); BUG_ON(!hlist_unhashed(&fl->fl_link)); if (fl->fl_ops) { if (fl->fl_ops->fl_release_private) fl->fl_ops->fl_release_private(fl); fl->fl_ops = NULL; } if (fl->fl_lmops) { if (fl->fl_lmops->lm_put_owner) { fl->fl_lmops->lm_put_owner(fl->fl_owner); fl->fl_owner = NULL; } fl->fl_lmops = NULL; } } EXPORT_SYMBOL_GPL(locks_release_private); /** * locks_owner_has_blockers - Check for blocking lock requests * @flctx: file lock context * @owner: lock owner * * Return values: * %true: @owner has at least one blocker * %false: @owner has no blockers */ bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { struct file_lock *fl; spin_lock(&flctx->flc_lock); list_for_each_entry(fl, &flctx->flc_posix, fl_list) { if (fl->fl_owner != owner) continue; if (!list_empty(&fl->fl_blocked_requests)) { spin_unlock(&flctx->flc_lock); return true; } } spin_unlock(&flctx->flc_lock); return false; } EXPORT_SYMBOL_GPL(locks_owner_has_blockers); /* Free a lock which is not in use. */ void locks_free_lock(struct file_lock *fl) { locks_release_private(fl); kmem_cache_free(filelock_cache, fl); } EXPORT_SYMBOL(locks_free_lock); static void locks_dispose_list(struct list_head *dispose) { struct file_lock *fl; while (!list_empty(dispose)) { fl = list_first_entry(dispose, struct file_lock, fl_list); list_del_init(&fl->fl_list); locks_free_lock(fl); } } void locks_init_lock(struct file_lock *fl) { memset(fl, 0, sizeof(struct file_lock)); locks_init_lock_heads(fl); } EXPORT_SYMBOL(locks_init_lock); /* * Initialize a new lock from an existing file_lock structure. */ void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { new->fl_owner = fl->fl_owner; new->fl_pid = fl->fl_pid; new->fl_file = NULL; new->fl_flags = fl->fl_flags; new->fl_type = fl->fl_type; new->fl_start = fl->fl_start; new->fl_end = fl->fl_end; new->fl_lmops = fl->fl_lmops; new->fl_ops = NULL; if (fl->fl_lmops) { if (fl->fl_lmops->lm_get_owner) fl->fl_lmops->lm_get_owner(fl->fl_owner); } } EXPORT_SYMBOL(locks_copy_conflock); void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { /* "new" must be a freshly-initialized lock */ WARN_ON_ONCE(new->fl_ops); locks_copy_conflock(new, fl); new->fl_file = fl->fl_file; new->fl_ops = fl->fl_ops; if (fl->fl_ops) { if (fl->fl_ops->fl_copy_lock) fl->fl_ops->fl_copy_lock(new, fl); } } EXPORT_SYMBOL(locks_copy_lock); static void locks_move_blocks(struct file_lock *new, struct file_lock *fl) { struct file_lock *f; /* * As ctx->flc_lock is held, new requests cannot be added to * ->fl_blocked_requests, so we don't need a lock to check if it * is empty. */ if (list_empty(&fl->fl_blocked_requests)) return; spin_lock(&blocked_lock_lock); list_splice_init(&fl->fl_blocked_requests, &new->fl_blocked_requests); list_for_each_entry(f, &new->fl_blocked_requests, fl_blocked_member) f->fl_blocker = new; spin_unlock(&blocked_lock_lock); } static inline int flock_translate_cmd(int cmd) { if (cmd & LOCK_MAND) return cmd & (LOCK_MAND | LOCK_RW); switch (cmd) { case LOCK_SH: return F_RDLCK; case LOCK_EX: return F_WRLCK; case LOCK_UN: return F_UNLCK; } return -EINVAL; } /* Fill in a file_lock structure with an appropriate FLOCK lock. */ static struct file_lock * flock_make_lock(struct file *filp, unsigned int cmd, struct file_lock *fl) { int type = flock_translate_cmd(cmd); if (type < 0) return ERR_PTR(type); if (fl == NULL) { fl = locks_alloc_lock(); if (fl == NULL) return ERR_PTR(-ENOMEM); } else { locks_init_lock(fl); } fl->fl_file = filp; fl->fl_owner = filp; fl->fl_pid = current->tgid; fl->fl_flags = FL_FLOCK; fl->fl_type = type; fl->fl_end = OFFSET_MAX; return fl; } static int assign_type(struct file_lock *fl, long type) { switch (type) { case F_RDLCK: case F_WRLCK: case F_UNLCK: fl->fl_type = type; break; default: return -EINVAL; } return 0; } static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl, struct flock64 *l) { switch (l->l_whence) { case SEEK_SET: fl->fl_start = 0; break; case SEEK_CUR: fl->fl_start = filp->f_pos; break; case SEEK_END: fl->fl_start = i_size_read(file_inode(filp)); break; default: return -EINVAL; } if (l->l_start > OFFSET_MAX - fl->fl_start) return -EOVERFLOW; fl->fl_start += l->l_start; if (fl->fl_start < 0) return -EINVAL; /* POSIX-1996 leaves the case l->l_len < 0 undefined; POSIX-2001 defines it. */ if (l->l_len > 0) { if (l->l_len - 1 > OFFSET_MAX - fl->fl_start) return -EOVERFLOW; fl->fl_end = fl->fl_start + l->l_len - 1; } else if (l->l_len < 0) { if (fl->fl_start + l->l_len < 0) return -EINVAL; fl->fl_end = fl->fl_start - 1; fl->fl_start += l->l_len; } else fl->fl_end = OFFSET_MAX; fl->fl_owner = current->files; fl->fl_pid = current->tgid; fl->fl_file = filp; fl->fl_flags = FL_POSIX; fl->fl_ops = NULL; fl->fl_lmops = NULL; return assign_type(fl, l->l_type); } /* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX * style lock. */ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl, struct flock *l) { struct flock64 ll = { .l_type = l->l_type, .l_whence = l->l_whence, .l_start = l->l_start, .l_len = l->l_len, }; return flock64_to_posix_lock(filp, fl, &ll); } /* default lease lock manager operations */ static bool lease_break_callback(struct file_lock *fl) { kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG); return false; } static void lease_setup(struct file_lock *fl, void **priv) { struct file *filp = fl->fl_file; struct fasync_struct *fa = *priv; /* * fasync_insert_entry() returns the old entry if any. If there was no * old entry, then it used "priv" and inserted it into the fasync list. * Clear the pointer to indicate that it shouldn't be freed. */ if (!fasync_insert_entry(fa->fa_fd, filp, &fl->fl_fasync, fa)) *priv = NULL; __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); } static const struct lock_manager_operations lease_manager_ops = { .lm_break = lease_break_callback, .lm_change = lease_modify, .lm_setup = lease_setup, }; /* * Initialize a lease, use the default lock manager operations */ static int lease_init(struct file *filp, long type, struct file_lock *fl) { if (assign_type(fl, type) != 0) return -EINVAL; fl->fl_owner = filp; fl->fl_pid = current->tgid; fl->fl_file = filp; fl->fl_flags = FL_LEASE; fl->fl_start = 0; fl->fl_end = OFFSET_MAX; fl->fl_ops = NULL; fl->fl_lmops = &lease_manager_ops; return 0; } /* Allocate a file_lock initialised to this type of lease */ static struct file_lock *lease_alloc(struct file *filp, long type) { struct file_lock *fl = locks_alloc_lock(); int error = -ENOMEM; if (fl == NULL) return ERR_PTR(error); error = lease_init(filp, type, fl); if (error) { locks_free_lock(fl); return ERR_PTR(error); } return fl; } /* Check if two locks overlap each other. */ static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2) { return ((fl1->fl_end >= fl2->fl_start) && (fl2->fl_end >= fl1->fl_start)); } /* * Check whether two locks have the same owner. */ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2) { return fl1->fl_owner == fl2->fl_owner; } /* Must be called with the flc_lock held! */ static void locks_insert_global_locks(struct file_lock *fl) { struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list); percpu_rwsem_assert_held(&file_rwsem); spin_lock(&fll->lock); fl->fl_link_cpu = smp_processor_id(); hlist_add_head(&fl->fl_link, &fll->hlist); spin_unlock(&fll->lock); } /* Must be called with the flc_lock held! */ static void locks_delete_global_locks(struct file_lock *fl) { struct file_lock_list_struct *fll; percpu_rwsem_assert_held(&file_rwsem); /* * Avoid taking lock if already unhashed. This is safe since this check * is done while holding the flc_lock, and new insertions into the list * also require that it be held. */ if (hlist_unhashed(&fl->fl_link)) return; fll = per_cpu_ptr(&file_lock_list, fl->fl_link_cpu); spin_lock(&fll->lock); hlist_del_init(&fl->fl_link); spin_unlock(&fll->lock); } static unsigned long posix_owner_key(struct file_lock *fl) { return (unsigned long)fl->fl_owner; } static void locks_insert_global_blocked(struct file_lock *waiter) { lockdep_assert_held(&blocked_lock_lock); hash_add(blocked_hash, &waiter->fl_link, posix_owner_key(waiter)); } static void locks_delete_global_blocked(struct file_lock *waiter) { lockdep_assert_held(&blocked_lock_lock); hash_del(&waiter->fl_link); } /* Remove waiter from blocker's block list. * When blocker ends up pointing to itself then the list is empty. * * Must be called with blocked_lock_lock held. */ static void __locks_delete_block(struct file_lock *waiter) { locks_delete_global_blocked(waiter); list_del_init(&waiter->fl_blocked_member); } static void __locks_wake_up_blocks(struct file_lock *blocker) { while (!list_empty(&blocker->fl_blocked_requests)) { struct file_lock *waiter; waiter = list_first_entry(&blocker->fl_blocked_requests, struct file_lock, fl_blocked_member); __locks_delete_block(waiter); if (waiter->fl_lmops && waiter->fl_lmops->lm_notify) waiter->fl_lmops->lm_notify(waiter); else wake_up(&waiter->fl_wait); /* * The setting of fl_blocker to NULL marks the "done" * point in deleting a block. Paired with acquire at the top * of locks_delete_block(). */ smp_store_release(&waiter->fl_blocker, NULL); } } /** * locks_delete_lock - stop waiting for a file lock * @waiter: the lock which was waiting * * lockd/nfsd need to disconnect the lock while working on it. */ int locks_delete_block(struct file_lock *waiter) { int status = -ENOENT; /* * If fl_blocker is NULL, it won't be set again as this thread "owns" * the lock and is the only one that might try to claim the lock. * * We use acquire/release to manage fl_blocker so that we can * optimize away taking the blocked_lock_lock in many cases. * * The smp_load_acquire guarantees two things: * * 1/ that fl_blocked_requests can be tested locklessly. If something * was recently added to that list it must have been in a locked region * *before* the locked region when fl_blocker was set to NULL. * * 2/ that no other thread is accessing 'waiter', so it is safe to free * it. __locks_wake_up_blocks is careful not to touch waiter after * fl_blocker is released. * * If a lockless check of fl_blocker shows it to be NULL, we know that * no new locks can be inserted into its fl_blocked_requests list, and * can avoid doing anything further if the list is empty. */ if (!smp_load_acquire(&waiter->fl_blocker) && list_empty(&waiter->fl_blocked_requests)) return status; spin_lock(&blocked_lock_lock); if (waiter->fl_blocker) status = 0; __locks_wake_up_blocks(waiter); __locks_delete_block(waiter); /* * The setting of fl_blocker to NULL marks the "done" point in deleting * a block. Paired with acquire at the top of this function. */ smp_store_release(&waiter->fl_blocker, NULL); spin_unlock(&blocked_lock_lock); return status; } EXPORT_SYMBOL(locks_delete_block); /* Insert waiter into blocker's block list. * We use a circular list so that processes can be easily woken up in * the order they blocked. The documentation doesn't require this but * it seems like the reasonable thing to do. * * Must be called with both the flc_lock and blocked_lock_lock held. The * fl_blocked_requests list itself is protected by the blocked_lock_lock, * but by ensuring that the flc_lock is also held on insertions we can avoid * taking the blocked_lock_lock in some cases when we see that the * fl_blocked_requests list is empty. * * Rather than just adding to the list, we check for conflicts with any existing * waiters, and add beneath any waiter that blocks the new waiter. * Thus wakeups don't happen until needed. */ static void __locks_insert_block(struct file_lock *blocker, struct file_lock *waiter, bool conflict(struct file_lock *, struct file_lock *)) { struct file_lock *fl; BUG_ON(!list_empty(&waiter->fl_blocked_member)); new_blocker: list_for_each_entry(fl, &blocker->fl_blocked_requests, fl_blocked_member) if (conflict(fl, waiter)) { blocker = fl; goto new_blocker; } waiter->fl_blocker = blocker; list_add_tail(&waiter->fl_blocked_member, &blocker->fl_blocked_requests); if (IS_POSIX(blocker) && !IS_OFDLCK(blocker)) locks_insert_global_blocked(waiter); /* The requests in waiter->fl_blocked are known to conflict with * waiter, but might not conflict with blocker, or the requests * and lock which block it. So they all need to be woken. */ __locks_wake_up_blocks(waiter); } /* Must be called with flc_lock held. */ static void locks_insert_block(struct file_lock *blocker, struct file_lock *waiter, bool conflict(struct file_lock *, struct file_lock *)) { spin_lock(&blocked_lock_lock); __locks_insert_block(blocker, waiter, conflict); spin_unlock(&blocked_lock_lock); } /* * Wake up processes blocked waiting for blocker. * * Must be called with the inode->flc_lock held! */ static void locks_wake_up_blocks(struct file_lock *blocker) { /* * Avoid taking global lock if list is empty. This is safe since new * blocked requests are only added to the list under the flc_lock, and * the flc_lock is always held here. Note that removal from the * fl_blocked_requests list does not require the flc_lock, so we must * recheck list_empty() after acquiring the blocked_lock_lock. */ if (list_empty(&blocker->fl_blocked_requests)) return; spin_lock(&blocked_lock_lock); __locks_wake_up_blocks(blocker); spin_unlock(&blocked_lock_lock); } static void locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before) { list_add_tail(&fl->fl_list, before); locks_insert_global_locks(fl); } static void locks_unlink_lock_ctx(struct file_lock *fl) { locks_delete_global_locks(fl); list_del_init(&fl->fl_list); locks_wake_up_blocks(fl); } static void locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose) { locks_unlink_lock_ctx(fl); if (dispose) list_add(&fl->fl_list, dispose); else locks_free_lock(fl); } /* Determine if lock sys_fl blocks lock caller_fl. Common functionality * checks for shared/exclusive status of overlapping locks. */ static bool locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl) { if (sys_fl->fl_type == F_WRLCK) return true; if (caller_fl->fl_type == F_WRLCK) return true; return false; } /* Determine if lock sys_fl blocks lock caller_fl. POSIX specific * checking before calling the locks_conflict(). */ static bool posix_locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl) { /* POSIX locks owned by the same process do not conflict with * each other. */ if (posix_same_owner(caller_fl, sys_fl)) return false; /* Check whether they overlap */ if (!locks_overlap(caller_fl, sys_fl)) return false; return locks_conflict(caller_fl, sys_fl); } /* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific * checking before calling the locks_conflict(). */ static bool flock_locks_conflict(struct file_lock *caller_fl, struct file_lock *sys_fl) { /* FLOCK locks referring to the same filp do not conflict with * each other. */ if (caller_fl->fl_file == sys_fl->fl_file) return false; if ((caller_fl->fl_type & LOCK_MAND) || (sys_fl->fl_type & LOCK_MAND)) return false; return locks_conflict(caller_fl, sys_fl); } void posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; struct file_lock_context *ctx; struct inode *inode = locks_inode(filp); void *owner; void (*func)(void); ctx = locks_inode_context(inode); if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->fl_type = F_UNLCK; return; } retry: spin_lock(&ctx->flc_lock); list_for_each_entry(cfl, &ctx->flc_posix, fl_list) { if (!posix_locks_conflict(fl, cfl)) continue; if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable && (*cfl->fl_lmops->lm_lock_expirable)(cfl)) { owner = cfl->fl_lmops->lm_mod_owner; func = cfl->fl_lmops->lm_expire_lock; __module_get(owner); spin_unlock(&ctx->flc_lock); (*func)(); module_put(owner); goto retry; } locks_copy_conflock(fl, cfl); goto out; } fl->fl_type = F_UNLCK; out: spin_unlock(&ctx->flc_lock); return; } EXPORT_SYMBOL(posix_test_lock); /* * Deadlock detection: * * We attempt to detect deadlocks that are due purely to posix file * locks. * * We assume that a task can be waiting for at most one lock at a time. * So for any acquired lock, the process holding that lock may be * waiting on at most one other lock. That lock in turns may be held by * someone waiting for at most one other lock. Given a requested lock * caller_fl which is about to wait for a conflicting lock block_fl, we * follow this chain of waiters to ensure we are not about to create a * cycle. * * Since we do this before we ever put a process to sleep on a lock, we * are ensured that there is never a cycle; that is what guarantees that * the while() loop in posix_locks_deadlock() eventually completes. * * Note: the above assumption may not be true when handling lock * requests from a broken NFS client. It may also fail in the presence * of tasks (such as posix threads) sharing the same open file table. * To handle those cases, we just bail out after a few iterations. * * For FL_OFDLCK locks, the owner is the filp, not the files_struct. * Because the owner is not even nominally tied to a thread of * execution, the deadlock detection below can't reasonably work well. Just * skip it for those. * * In principle, we could do a more limited deadlock detection on FL_OFDLCK * locks that just checks for the case where two tasks are attempting to * upgrade from read to write locks on the same inode. */ #define MAX_DEADLK_ITERATIONS 10 /* Find a lock that the owner of the given block_fl is blocking on. */ static struct file_lock *what_owner_is_waiting_for(struct file_lock *block_fl) { struct file_lock *fl; hash_for_each_possible(blocked_hash, fl, fl_link, posix_owner_key(block_fl)) { if (posix_same_owner(fl, block_fl)) { while (fl->fl_blocker) fl = fl->fl_blocker; return fl; } } return NULL; } /* Must be called with the blocked_lock_lock held! */ static int posix_locks_deadlock(struct file_lock *caller_fl, struct file_lock *block_fl) { int i = 0; lockdep_assert_held(&blocked_lock_lock); /* * This deadlock detector can't reasonably detect deadlocks with * FL_OFDLCK locks, since they aren't owned by a process, per-se. */ if (IS_OFDLCK(caller_fl)) return 0; while ((block_fl = what_owner_is_waiting_for(block_fl))) { if (i++ > MAX_DEADLK_ITERATIONS) return 0; if (posix_same_owner(caller_fl, block_fl)) return 1; } return 0; } /* Try to create a FLOCK lock on filp. We always insert new FLOCK locks * after any leases, but before any posix locks. * * Note that if called with an FL_EXISTS argument, the caller may determine * whether or not a lock was successfully freed by testing the return * value for -ENOENT. */ static int flock_lock_inode(struct inode *inode, struct file_lock *request) { struct file_lock *new_fl = NULL; struct file_lock *fl; struct file_lock_context *ctx; int error = 0; bool found = false; LIST_HEAD(dispose); ctx = locks_get_lock_context(inode, request->fl_type); if (!ctx) { if (request->fl_type != F_UNLCK) return -ENOMEM; return (request->fl_flags & FL_EXISTS) ? -ENOENT : 0; } if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) { new_fl = locks_alloc_lock(); if (!new_fl) return -ENOMEM; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); if (request->fl_flags & FL_ACCESS) goto find_conflict; list_for_each_entry(fl, &ctx->flc_flock, fl_list) { if (request->fl_file != fl->fl_file) continue; if (request->fl_type == fl->fl_type) goto out; found = true; locks_delete_lock_ctx(fl, &dispose); break; } if (request->fl_type == F_UNLCK) { if ((request->fl_flags & FL_EXISTS) && !found) error = -ENOENT; goto out; } find_conflict: list_for_each_entry(fl, &ctx->flc_flock, fl_list) { if (!flock_locks_conflict(request, fl)) continue; error = -EAGAIN; if (!(request->fl_flags & FL_SLEEP)) goto out; error = FILE_LOCK_DEFERRED; locks_insert_block(fl, request, flock_locks_conflict); goto out; } if (request->fl_flags & FL_ACCESS) goto out; locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); locks_insert_lock_ctx(new_fl, &ctx->flc_flock); new_fl = NULL; error = 0; out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); trace_flock_lock_inode(inode, request, error); return error; } static int posix_lock_inode(struct inode *inode, struct file_lock *request, struct file_lock *conflock) { struct file_lock *fl, *tmp; struct file_lock *new_fl = NULL; struct file_lock *new_fl2 = NULL; struct file_lock *left = NULL; struct file_lock *right = NULL; struct file_lock_context *ctx; int error; bool added = false; LIST_HEAD(dispose); void *owner; void (*func)(void); ctx = locks_get_lock_context(inode, request->fl_type); if (!ctx) return (request->fl_type == F_UNLCK) ? 0 : -ENOMEM; /* * We may need two file_lock structures for this operation, * so we get them in advance to avoid races. * * In some cases we can be sure, that no new locks will be needed */ if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK || request->fl_start != 0 || request->fl_end != OFFSET_MAX)) { new_fl = locks_alloc_lock(); new_fl2 = locks_alloc_lock(); } retry: percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); /* * New lock request. Walk all POSIX locks and look for conflicts. If * there are any, either return error or put the request on the * blocker's list of waiters and the global blocked_hash. */ if (request->fl_type != F_UNLCK) { list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (!posix_locks_conflict(request, fl)) continue; if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable && (*fl->fl_lmops->lm_lock_expirable)(fl)) { owner = fl->fl_lmops->lm_mod_owner; func = fl->fl_lmops->lm_expire_lock; __module_get(owner); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); (*func)(); module_put(owner); goto retry; } if (conflock) locks_copy_conflock(conflock, fl); error = -EAGAIN; if (!(request->fl_flags & FL_SLEEP)) goto out; /* * Deadlock detection and insertion into the blocked * locks list must be done while holding the same lock! */ error = -EDEADLK; spin_lock(&blocked_lock_lock); /* * Ensure that we don't find any locks blocked on this * request during deadlock detection. */ __locks_wake_up_blocks(request); if (likely(!posix_locks_deadlock(request, fl))) { error = FILE_LOCK_DEFERRED; __locks_insert_block(fl, request, posix_locks_conflict); } spin_unlock(&blocked_lock_lock); goto out; } } /* If we're just looking for a conflict, we're done. */ error = 0; if (request->fl_flags & FL_ACCESS) goto out; /* Find the first old lock with the same owner as the new lock */ list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (posix_same_owner(request, fl)) break; } /* Process locks with this owner. */ list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) { if (!posix_same_owner(request, fl)) break; /* Detect adjacent or overlapping regions (if same lock type) */ if (request->fl_type == fl->fl_type) { /* In all comparisons of start vs end, use * "start - 1" rather than "end + 1". If end * is OFFSET_MAX, end + 1 will become negative. */ if (fl->fl_end < request->fl_start - 1) continue; /* If the next lock in the list has entirely bigger * addresses than the new one, insert the lock here. */ if (fl->fl_start - 1 > request->fl_end) break; /* If we come here, the new and old lock are of the * same type and adjacent or overlapping. Make one * lock yielding from the lower start address of both * locks to the higher end address. */ if (fl->fl_start > request->fl_start) fl->fl_start = request->fl_start; else request->fl_start = fl->fl_start; if (fl->fl_end < request->fl_end) fl->fl_end = request->fl_end; else request->fl_end = fl->fl_end; if (added) { locks_delete_lock_ctx(fl, &dispose); continue; } request = fl; added = true; } else { /* Processing for different lock types is a bit * more complex. */ if (fl->fl_end < request->fl_start) continue; if (fl->fl_start > request->fl_end) break; if (request->fl_type == F_UNLCK) added = true; if (fl->fl_start < request->fl_start) left = fl; /* If the next lock in the list has a higher end * address than the new one, insert the new one here. */ if (fl->fl_end > request->fl_end) { right = fl; break; } if (fl->fl_start >= request->fl_start) { /* The new lock completely replaces an old * one (This may happen several times). */ if (added) { locks_delete_lock_ctx(fl, &dispose); continue; } /* * Replace the old lock with new_fl, and * remove the old one. It's safe to do the * insert here since we know that we won't be * using new_fl later, and that the lock is * just replacing an existing lock. */ error = -ENOLCK; if (!new_fl) goto out; locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); request = new_fl; new_fl = NULL; locks_insert_lock_ctx(request, &fl->fl_list); locks_delete_lock_ctx(fl, &dispose); added = true; } } } /* * The above code only modifies existing locks in case of merging or * replacing. If new lock(s) need to be inserted all modifications are * done below this, so it's safe yet to bail out. */ error = -ENOLCK; /* "no luck" */ if (right && left == right && !new_fl2) goto out; error = 0; if (!added) { if (request->fl_type == F_UNLCK) { if (request->fl_flags & FL_EXISTS) error = -ENOENT; goto out; } if (!new_fl) { error = -ENOLCK; goto out; } locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); locks_insert_lock_ctx(new_fl, &fl->fl_list); fl = new_fl; new_fl = NULL; } if (right) { if (left == right) { /* The new lock breaks the old one in two pieces, * so we have to use the second new lock. */ left = new_fl2; new_fl2 = NULL; locks_copy_lock(left, right); locks_insert_lock_ctx(left, &fl->fl_list); } right->fl_start = request->fl_end + 1; locks_wake_up_blocks(right); } if (left) { left->fl_end = request->fl_start - 1; locks_wake_up_blocks(left); } out: trace_posix_lock_inode(inode, request, error); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); /* * Free any unused locks. */ if (new_fl) locks_free_lock(new_fl); if (new_fl2) locks_free_lock(new_fl2); locks_dispose_list(&dispose); return error; } /** * posix_lock_file - Apply a POSIX-style lock to a file * @filp: The file to apply the lock to * @fl: The lock to be applied * @conflock: Place to return a copy of the conflicting lock, if found. * * Add a POSIX style lock to a file. * We merge adjacent & overlapping locks whenever possible. * POSIX locks are sorted by owner task, then by starting address * * Note that if called with an FL_EXISTS argument, the caller may determine * whether or not a lock was successfully freed by testing the return * value for -ENOENT. */ int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return posix_lock_inode(locks_inode(filp), fl, conflock); } EXPORT_SYMBOL(posix_lock_file); /** * posix_lock_inode_wait - Apply a POSIX-style lock to a file * @inode: inode of file to which lock request should be applied * @fl: The lock to be applied * * Apply a POSIX style lock request to an inode. */ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep (); for (;;) { error = posix_lock_inode(inode, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, list_empty(&fl->fl_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } #ifdef CONFIG_MANDATORY_FILE_LOCKING /** * locks_mandatory_locked - Check for an active lock * @file: the file to check * * Searches the inode's list of locks to find any POSIX locks which conflict. * This function is called from locks_verify_locked() only. */ int locks_mandatory_locked(struct file *file) { int ret; struct inode *inode = locks_inode(file); struct file_lock_context *ctx; struct file_lock *fl; ctx = smp_load_acquire(&inode->i_flctx); if (!ctx || list_empty_careful(&ctx->flc_posix)) return 0; /* * Search the lock list for this inode for any POSIX locks. */ spin_lock(&ctx->flc_lock); ret = 0; list_for_each_entry(fl, &ctx->flc_posix, fl_list) { if (fl->fl_owner != current->files && fl->fl_owner != file) { ret = -EAGAIN; break; } } spin_unlock(&ctx->flc_lock); return ret; } /** * locks_mandatory_area - Check for a conflicting lock * @inode: the file to check * @filp: how the file was opened (if it was) * @start: first byte in the file to check * @end: lastbyte in the file to check * @type: %F_WRLCK for a write lock, else %F_RDLCK * * Searches the inode's list of locks to find any POSIX locks which conflict. */ int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start, loff_t end, unsigned char type) { struct file_lock fl; int error; bool sleep = false; locks_init_lock(&fl); fl.fl_pid = current->tgid; fl.fl_file = filp; fl.fl_flags = FL_POSIX | FL_ACCESS; if (filp && !(filp->f_flags & O_NONBLOCK)) sleep = true; fl.fl_type = type; fl.fl_start = start; fl.fl_end = end; for (;;) { if (filp) { fl.fl_owner = filp; fl.fl_flags &= ~FL_SLEEP; error = posix_lock_inode(inode, &fl, NULL); if (!error) break; } if (sleep) fl.fl_flags |= FL_SLEEP; fl.fl_owner = current->files; error = posix_lock_inode(inode, &fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl.fl_wait, list_empty(&fl.fl_blocked_member)); if (!error) { /* * If we've been sleeping someone might have * changed the permissions behind our back. */ if (__mandatory_lock(inode)) continue; } break; } locks_delete_block(&fl); return error; } EXPORT_SYMBOL(locks_mandatory_area); #endif /* CONFIG_MANDATORY_FILE_LOCKING */ static void lease_clear_pending(struct file_lock *fl, int arg) { switch (arg) { case F_UNLCK: fl->fl_flags &= ~FL_UNLOCK_PENDING; fallthrough; case F_RDLCK: fl->fl_flags &= ~FL_DOWNGRADE_PENDING; } } /* We already had a lease on this file; just change its type */ int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { int error = assign_type(fl, arg); if (error) return error; lease_clear_pending(fl, arg); locks_wake_up_blocks(fl); if (arg == F_UNLCK) { struct file *filp = fl->fl_file; f_delown(filp); filp->f_owner.signum = 0; fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync); if (fl->fl_fasync != NULL) { printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); fl->fl_fasync = NULL; } locks_delete_lock_ctx(fl, dispose); } return 0; } EXPORT_SYMBOL(lease_modify); static bool past_time(unsigned long then) { if (!then) /* 0 is a special value meaning "this never expires": */ return false; return time_after(jiffies, then); } static void time_out_leases(struct inode *inode, struct list_head *dispose) { struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl, *tmp; lockdep_assert_held(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) lease_modify(fl, F_RDLCK, dispose); if (past_time(fl->fl_break_time)) lease_modify(fl, F_UNLCK, dispose); } } static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker) { bool rc; if (lease->fl_lmops->lm_breaker_owns_lease && lease->fl_lmops->lm_breaker_owns_lease(lease)) return false; if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT)) { rc = false; goto trace; } if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE)) { rc = false; goto trace; } rc = locks_conflict(breaker, lease); trace: trace_leases_conflict(rc, lease, breaker); return rc; } static bool any_leases_conflict(struct inode *inode, struct file_lock *breaker) { struct file_lock_context *ctx = inode->i_flctx; struct file_lock *fl; lockdep_assert_held(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (leases_conflict(fl, breaker)) return true; } return false; } /** * __break_lease - revoke all outstanding leases on file * @inode: the inode of the file to return * @mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR: * break all leases * @type: FL_LEASE: break leases and delegations; FL_DELEG: break * only delegations * * break_lease (inlined for speed) has checked there already is at least * some kind of lock (maybe a lease) on this file. Leases are broken on * a call to open() or truncate(). This function can sleep unless you * specified %O_NONBLOCK to your open(). */ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { int error = 0; struct file_lock_context *ctx; struct file_lock *new_fl, *fl, *tmp; unsigned long break_time; int want_write = (mode & O_ACCMODE) != O_RDONLY; LIST_HEAD(dispose); new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK); if (IS_ERR(new_fl)) return PTR_ERR(new_fl); new_fl->fl_flags = type; /* typically we will check that ctx is non-NULL before calling */ ctx = locks_inode_context(inode); if (!ctx) { WARN_ON_ONCE(1); goto free_lock; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); if (!any_leases_conflict(inode, new_fl)) goto out; break_time = 0; if (lease_break_time > 0) { break_time = jiffies + lease_break_time * HZ; if (break_time == 0) break_time++; /* so that 0 means no break time */ } list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { if (!leases_conflict(fl, new_fl)) continue; if (want_write) { if (fl->fl_flags & FL_UNLOCK_PENDING) continue; fl->fl_flags |= FL_UNLOCK_PENDING; fl->fl_break_time = break_time; } else { if (lease_breaking(fl)) continue; fl->fl_flags |= FL_DOWNGRADE_PENDING; fl->fl_downgrade_time = break_time; } if (fl->fl_lmops->lm_break(fl)) locks_delete_lock_ctx(fl, &dispose); } if (list_empty(&ctx->flc_lease)) goto out; if (mode & O_NONBLOCK) { trace_break_lease_noblock(inode, new_fl); error = -EWOULDBLOCK; goto out; } restart: fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list); break_time = fl->fl_break_time; if (break_time != 0) break_time -= jiffies; if (break_time == 0) break_time++; locks_insert_block(fl, new_fl, leases_conflict); trace_break_lease_block(inode, new_fl); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->fl_wait, list_empty(&new_fl->fl_blocked_member), break_time); percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); locks_delete_block(new_fl); if (error >= 0) { /* * Wait for the next conflicting lease that has not been * broken yet */ if (error == 0) time_out_leases(inode, &dispose); if (any_leases_conflict(inode, new_fl)) goto restart; error = 0; } out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); free_lock: locks_free_lock(new_fl); return error; } EXPORT_SYMBOL(__break_lease); /** * lease_get_mtime - update modified time of an inode with exclusive lease * @inode: the inode * @time: pointer to a timespec which contains the last modified time * * This is to force NFS clients to flush their caches for files with * exclusive leases. The justification is that if someone has an * exclusive lease, then they could be modifying it. */ void lease_get_mtime(struct inode *inode, struct timespec64 *time) { bool has_lease = false; struct file_lock_context *ctx; struct file_lock *fl; ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); fl = list_first_entry_or_null(&ctx->flc_lease, struct file_lock, fl_list); if (fl && (fl->fl_type == F_WRLCK)) has_lease = true; spin_unlock(&ctx->flc_lock); } if (has_lease) *time = current_time(inode); } EXPORT_SYMBOL(lease_get_mtime); /** * fcntl_getlease - Enquire what lease is currently active * @filp: the file * * The value returned by this function will be one of * (if no lease break is pending): * * %F_RDLCK to indicate a shared lease is held. * * %F_WRLCK to indicate an exclusive lease is held. * * %F_UNLCK to indicate no lease is held. * * (if a lease break is pending): * * %F_RDLCK to indicate an exclusive lease needs to be * changed to a shared lease (or removed). * * %F_UNLCK to indicate the lease needs to be removed. * * XXX: sfr & willy disagree over whether F_INPROGRESS * should be returned to userspace. */ int fcntl_getlease(struct file *filp) { struct file_lock *fl; struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; int type = F_UNLCK; LIST_HEAD(dispose); ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file != filp) continue; type = target_leasetype(fl); break; } spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } return type; } /** * check_conflicting_open - see if the given file points to an inode that has * an existing open that would conflict with the * desired lease. * @filp: file to check * @arg: type of lease that we're trying to acquire * @flags: current lock flags * * Check to see if there's an existing open fd on this file that would * conflict with the lease we're trying to set. */ static int check_conflicting_open(struct file *filp, const long arg, int flags) { struct inode *inode = locks_inode(filp); int self_wcount = 0, self_rcount = 0; if (flags & FL_LAYOUT) return 0; if (flags & FL_DELEG) /* We leave these checks to the caller */ return 0; if (arg == F_RDLCK) return inode_is_open_for_write(inode) ? -EAGAIN : 0; else if (arg != F_WRLCK) return 0; /* * Make sure that only read/write count is from lease requestor. * Note that this will result in denying write leases when i_writecount * is negative, which is what we want. (We shouldn't grant write leases * on files open for execution.) */ if (filp->f_mode & FMODE_WRITE) self_wcount = 1; else if (filp->f_mode & FMODE_READ) self_rcount = 1; if (atomic_read(&inode->i_writecount) != self_wcount || atomic_read(&inode->i_readcount) != self_rcount) return -EAGAIN; return 0; } static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv) { struct file_lock *fl, *my_fl = NULL, *lease; struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; LIST_HEAD(dispose); lease = *flp; trace_generic_add_lease(inode, lease); /* Note that arg is never F_UNLCK here */ ctx = locks_get_lock_context(inode, arg); if (!ctx) return -ENOMEM; /* * In the delegation case we need mutual exclusion with * a number of operations that take the i_mutex. We trylock * because delegations are an optional optimization, and if * there's some chance of a conflict--we'd rather not * bother, maybe that's a sign this just isn't a good file to * hand out a delegation on. */ if (is_deleg && !inode_trylock(inode)) return -EAGAIN; if (is_deleg && arg == F_WRLCK) { /* Write delegations are not currently supported: */ inode_unlock(inode); WARN_ON_ONCE(1); return -EINVAL; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); error = check_conflicting_open(filp, arg, lease->fl_flags); if (error) goto out; /* * At this point, we know that if there is an exclusive * lease on this file, then we hold it on this filp * (otherwise our open of this file would have blocked). * And if we are trying to acquire an exclusive lease, * then the file is not open by anyone (including us) * except for this filp. */ error = -EAGAIN; list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp && fl->fl_owner == lease->fl_owner) { my_fl = fl; continue; } /* * No exclusive leases if someone else has a lease on * this file: */ if (arg == F_WRLCK) goto out; /* * Modifying our existing lease is OK, but no getting a * new lease if someone else is opening for write: */ if (fl->fl_flags & FL_UNLOCK_PENDING) goto out; } if (my_fl != NULL) { lease = my_fl; error = lease->fl_lmops->lm_change(lease, arg, &dispose); if (error) goto out; goto out_setup; } error = -EINVAL; if (!leases_enable) goto out; locks_insert_lock_ctx(lease, &ctx->flc_lease); /* * The check in break_lease() is lockless. It's possible for another * open to race in after we did the earlier check for a conflicting * open but before the lease was inserted. Check again for a * conflicting open and cancel the lease if there is one. * * We also add a barrier here to ensure that the insertion of the lock * precedes these checks. */ smp_mb(); error = check_conflicting_open(filp, arg, lease->fl_flags); if (error) { locks_unlink_lock_ctx(lease); goto out; } out_setup: if (lease->fl_lmops->lm_setup) lease->fl_lmops->lm_setup(lease, priv); out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); if (!error && !my_fl) *flp = NULL; return error; } static int generic_delete_lease(struct file *filp, void *owner) { int error = -EAGAIN; struct file_lock *fl, *victim = NULL; struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; LIST_HEAD(dispose); ctx = locks_inode_context(inode); if (!ctx) { trace_generic_delete_lease(inode, NULL); return error; } percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { if (fl->fl_file == filp && fl->fl_owner == owner) { victim = fl; break; } } trace_generic_delete_lease(inode, victim); if (victim) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); return error; } /** * generic_setlease - sets a lease on an open file * @filp: file pointer * @arg: type of lease to obtain * @flp: input - file_lock to use, output - file_lock inserted * @priv: private data for lm_setup (may be NULL if lm_setup * doesn't require it) * * The (input) flp->fl_lmops->lm_break function is required * by break_lease(). */ int generic_setlease(struct file *filp, long arg, struct file_lock **flp, void **priv) { struct inode *inode = locks_inode(filp); int error; if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE)) return -EACCES; if (!S_ISREG(inode->i_mode)) return -EINVAL; error = security_file_lock(filp, arg); if (error) return error; switch (arg) { case F_UNLCK: return generic_delete_lease(filp, *priv); case F_RDLCK: case F_WRLCK: if (!(*flp)->fl_lmops->lm_break) { WARN_ON_ONCE(1); return -ENOLCK; } return generic_add_lease(filp, arg, flp, priv); default: return -EINVAL; } } EXPORT_SYMBOL(generic_setlease); #if IS_ENABLED(CONFIG_SRCU) /* * Kernel subsystems can register to be notified on any attempt to set * a new lease with the lease_notifier_chain. This is used by (e.g.) nfsd * to close files that it may have cached when there is an attempt to set a * conflicting lease. */ static struct srcu_notifier_head lease_notifier_chain; static inline void lease_notifier_chain_init(void) { srcu_init_notifier_head(&lease_notifier_chain); } static inline void setlease_notifier(long arg, struct file_lock *lease) { if (arg != F_UNLCK) srcu_notifier_call_chain(&lease_notifier_chain, arg, lease); } int lease_register_notifier(struct notifier_block *nb) { return srcu_notifier_chain_register(&lease_notifier_chain, nb); } EXPORT_SYMBOL_GPL(lease_register_notifier); void lease_unregister_notifier(struct notifier_block *nb) { srcu_notifier_chain_unregister(&lease_notifier_chain, nb); } EXPORT_SYMBOL_GPL(lease_unregister_notifier); #else /* !IS_ENABLED(CONFIG_SRCU) */ static inline void lease_notifier_chain_init(void) { } static inline void setlease_notifier(long arg, struct file_lock *lease) { } int lease_register_notifier(struct notifier_block *nb) { return 0; } EXPORT_SYMBOL_GPL(lease_register_notifier); void lease_unregister_notifier(struct notifier_block *nb) { } EXPORT_SYMBOL_GPL(lease_unregister_notifier); #endif /* IS_ENABLED(CONFIG_SRCU) */ /** * vfs_setlease - sets a lease on an open file * @filp: file pointer * @arg: type of lease to obtain * @lease: file_lock to use when adding a lease * @priv: private info for lm_setup when adding a lease (may be * NULL if lm_setup doesn't require it) * * Call this to establish a lease on the file. The "lease" argument is not * used for F_UNLCK requests and may be NULL. For commands that set or alter * an existing lease, the ``(*lease)->fl_lmops->lm_break`` operation must be * set; if not, this function will return -ENOLCK (and generate a scary-looking * stack trace). * * The "priv" pointer is passed directly to the lm_setup function as-is. It * may be NULL if the lm_setup operation doesn't require it. */ int vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv) { if (lease) setlease_notifier(arg, *lease); if (filp->f_op->setlease) return filp->f_op->setlease(filp, arg, lease, priv); else return generic_setlease(filp, arg, lease, priv); } EXPORT_SYMBOL_GPL(vfs_setlease); static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg) { struct file_lock *fl; struct fasync_struct *new; int error; fl = lease_alloc(filp, arg); if (IS_ERR(fl)) return PTR_ERR(fl); new = fasync_alloc(); if (!new) { locks_free_lock(fl); return -ENOMEM; } new->fa_fd = fd; error = vfs_setlease(filp, arg, &fl, (void **)&new); if (fl) locks_free_lock(fl); if (new) fasync_free(new); return error; } /** * fcntl_setlease - sets a lease on an open file * @fd: open file descriptor * @filp: file pointer * @arg: type of lease to obtain * * Call this fcntl to establish a lease on the file. * Note that you also need to call %F_SETSIG to * receive a signal when the lease is broken. */ int fcntl_setlease(unsigned int fd, struct file *filp, long arg) { if (arg == F_UNLCK) return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp); return do_fcntl_add_lease(fd, filp, arg); } /** * flock_lock_inode_wait - Apply a FLOCK-style lock to a file * @inode: inode of the file to apply to * @fl: The lock to be applied * * Apply a FLOCK style lock request to an inode. */ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int error; might_sleep(); for (;;) { error = flock_lock_inode(inode, fl); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, list_empty(&fl->fl_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } /** * locks_lock_inode_wait - Apply a lock to an inode * @inode: inode of the file to apply to * @fl: The lock to be applied * * Apply a POSIX or FLOCK style lock request to an inode. */ int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int res = 0; switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { case FL_POSIX: res = posix_lock_inode_wait(inode, fl); break; case FL_FLOCK: res = flock_lock_inode_wait(inode, fl); break; default: BUG(); } return res; } EXPORT_SYMBOL(locks_lock_inode_wait); /** * sys_flock: - flock() system call. * @fd: the file descriptor to lock. * @cmd: the type of lock to apply. * * Apply a %FL_FLOCK style lock to an open file descriptor. * The @cmd can be one of: * * - %LOCK_SH -- a shared lock. * - %LOCK_EX -- an exclusive lock. * - %LOCK_UN -- remove an existing lock. * - %LOCK_MAND -- a 'mandatory' flock. * This exists to emulate Windows Share Modes. * * %LOCK_MAND can be combined with %LOCK_READ or %LOCK_WRITE to allow other * processes read and write access respectively. */ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) { struct fd f = fdget(fd); struct file_lock *lock; int can_sleep, unlock; int error; error = -EBADF; if (!f.file) goto out; can_sleep = !(cmd & LOCK_NB); cmd &= ~LOCK_NB; unlock = (cmd == LOCK_UN); if (!unlock && !(cmd & LOCK_MAND) && !(f.file->f_mode & (FMODE_READ|FMODE_WRITE))) goto out_putf; lock = flock_make_lock(f.file, cmd, NULL); if (IS_ERR(lock)) { error = PTR_ERR(lock); goto out_putf; } if (can_sleep) lock->fl_flags |= FL_SLEEP; error = security_file_lock(f.file, lock->fl_type); if (error) goto out_free; if (f.file->f_op->flock) error = f.file->f_op->flock(f.file, (can_sleep) ? F_SETLKW : F_SETLK, lock); else error = locks_lock_file_wait(f.file, lock); out_free: locks_free_lock(lock); out_putf: fdput(f); out: return error; } /** * vfs_test_lock - test file byte range lock * @filp: The file to test lock for * @fl: The lock to test; also used to hold result * * Returns -ERRNO on failure. Indicates presence of conflicting lock by * setting conf->fl_type to something other than F_UNLCK. */ int vfs_test_lock(struct file *filp, struct file_lock *fl) { if (filp->f_op->lock) return filp->f_op->lock(filp, F_GETLK, fl); posix_test_lock(filp, fl); return 0; } EXPORT_SYMBOL_GPL(vfs_test_lock); /** * locks_translate_pid - translate a file_lock's fl_pid number into a namespace * @fl: The file_lock who's fl_pid should be translated * @ns: The namespace into which the pid should be translated * * Used to tranlate a fl_pid into a namespace virtual pid number */ static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns) { pid_t vnr; struct pid *pid; if (IS_OFDLCK(fl)) return -1; if (IS_REMOTELCK(fl)) return fl->fl_pid; /* * If the flock owner process is dead and its pid has been already * freed, the translation below won't work, but we still want to show * flock owner pid number in init pidns. */ if (ns == &init_pid_ns) return (pid_t)fl->fl_pid; rcu_read_lock(); pid = find_pid_ns(fl->fl_pid, &init_pid_ns); vnr = pid_nr_ns(pid, ns); rcu_read_unlock(); return vnr; } static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) { flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current)); #if BITS_PER_LONG == 32 /* * Make sure we can represent the posix lock via * legacy 32bit flock. */ if (fl->fl_start > OFFT_OFFSET_MAX) return -EOVERFLOW; if (fl->fl_end != OFFSET_MAX && fl->fl_end > OFFT_OFFSET_MAX) return -EOVERFLOW; #endif flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; flock->l_whence = 0; flock->l_type = fl->fl_type; return 0; } #if BITS_PER_LONG == 32 static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) { flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current)); flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; flock->l_whence = 0; flock->l_type = fl->fl_type; } #endif /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock *fl; int error; fl = locks_alloc_lock(); if (fl == NULL) return -ENOMEM; error = -EINVAL; if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; error = flock_to_posix_lock(filp, fl, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_GETLK; fl->fl_flags |= FL_OFDLCK; fl->fl_owner = filp; } error = vfs_test_lock(filp, fl); if (error) goto out; flock->l_type = fl->fl_type; if (fl->fl_type != F_UNLCK) { error = posix_lock_to_flock(flock, fl); if (error) goto out; } out: locks_free_lock(fl); return error; } /** * vfs_lock_file - file byte range lock * @filp: The file to apply the lock to * @cmd: type of locking operation (F_SETLK, F_GETLK, etc.) * @fl: The lock to be applied * @conf: Place to return a copy of the conflicting lock, if found. * * A caller that doesn't care about the conflicting lock may pass NULL * as the final argument. * * If the filesystem defines a private ->lock() method, then @conf will * be left unchanged; so a caller that cares should initialize it to * some acceptable default. * * To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX * locks, the ->lock() interface may return asynchronously, before the lock has * been granted or denied by the underlying filesystem, if (and only if) * lm_grant is set. Callers expecting ->lock() to return asynchronously * will only use F_SETLK, not F_SETLKW; they will set FL_SLEEP if (and only if) * the request is for a blocking lock. When ->lock() does return asynchronously, * it must return FILE_LOCK_DEFERRED, and call ->lm_grant() when the lock * request completes. * If the request is for non-blocking lock the file system should return * FILE_LOCK_DEFERRED then try to get the lock and call the callback routine * with the result. If the request timed out the callback routine will return a * nonzero return code and the file system should release the lock. The file * system is also responsible to keep a corresponding posix lock when it * grants a lock so the VFS can find out which locks are locally held and do * the correct lock cleanup when required. * The underlying filesystem must not drop the kernel lock or call * ->lm_grant() before returning to the caller with a FILE_LOCK_DEFERRED * return code. */ int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { if (filp->f_op->lock) return filp->f_op->lock(filp, cmd, fl); else return posix_lock_file(filp, fl, conf); } EXPORT_SYMBOL_GPL(vfs_lock_file); static int do_lock_file_wait(struct file *filp, unsigned int cmd, struct file_lock *fl) { int error; error = security_file_lock(filp, fl->fl_type); if (error) return error; for (;;) { error = vfs_lock_file(filp, cmd, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; error = wait_event_interruptible(fl->fl_wait, list_empty(&fl->fl_blocked_member)); if (error) break; } locks_delete_block(fl); return error; } /* Ensure that fl->fl_file has compatible f_mode for F_SETLK calls */ static int check_fmode_for_setlk(struct file_lock *fl) { switch (fl->fl_type) { case F_RDLCK: if (!(fl->fl_file->f_mode & FMODE_READ)) return -EBADF; break; case F_WRLCK: if (!(fl->fl_file->f_mode & FMODE_WRITE)) return -EBADF; } return 0; } /* Apply the lock described by l to an open file descriptor. * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock *file_lock = locks_alloc_lock(); struct inode *inode = locks_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; /* Don't allow mandatory locks on files that may be memory mapped * and shared. */ if (mandatory_lock(inode) && mapping_writably_mapped(filp->f_mapping)) { error = -EAGAIN; goto out; } error = flock_to_posix_lock(filp, file_lock, flock); if (error) goto out; error = check_fmode_for_setlk(file_lock); if (error) goto out; /* * If the cmd is requesting file-private locks, then set the * FL_OFDLCK flag and override the owner. */ switch (cmd) { case F_OFD_SETLK: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLK; file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = filp; break; case F_OFD_SETLKW: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLKW; file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = filp; fallthrough; case F_SETLKW: file_lock->fl_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); /* * Detect close/fcntl races and recover by zapping all POSIX locks * associated with this file and our files_struct, just like on * filp_flush(). There is no need to do that when we're * unlocking though, or for OFD locks. */ if (!error && file_lock->fl_type != F_UNLCK && !(file_lock->fl_flags & FL_OFDLCK)) { struct files_struct *files = current->files; /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in * close(). rcu_read_lock() wouldn't do. */ spin_lock(&files->file_lock); f = files_lookup_fd_locked(files, fd); spin_unlock(&files->file_lock); if (f != filp) { locks_remove_posix(filp, files); error = -EBADF; } } out: trace_fcntl_setlk(inode, file_lock, error); locks_free_lock(file_lock); return error; } #if BITS_PER_LONG == 32 /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock *fl; int error; fl = locks_alloc_lock(); if (fl == NULL) return -ENOMEM; error = -EINVAL; if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; error = flock64_to_posix_lock(filp, fl, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_GETLK64; fl->fl_flags |= FL_OFDLCK; fl->fl_owner = filp; } error = vfs_test_lock(filp, fl); if (error) goto out; flock->l_type = fl->fl_type; if (fl->fl_type != F_UNLCK) posix_lock_to_flock64(flock, fl); out: locks_free_lock(fl); return error; } /* Apply the lock described by l to an open file descriptor. * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock *file_lock = locks_alloc_lock(); struct inode *inode = locks_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; /* Don't allow mandatory locks on files that may be memory mapped * and shared. */ if (mandatory_lock(inode) && mapping_writably_mapped(filp->f_mapping)) { error = -EAGAIN; goto out; } error = flock64_to_posix_lock(filp, file_lock, flock); if (error) goto out; error = check_fmode_for_setlk(file_lock); if (error) goto out; /* * If the cmd is requesting file-private locks, then set the * FL_OFDLCK flag and override the owner. */ switch (cmd) { case F_OFD_SETLK: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLK64; file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = filp; break; case F_OFD_SETLKW: error = -EINVAL; if (flock->l_pid != 0) goto out; cmd = F_SETLKW64; file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = filp; fallthrough; case F_SETLKW64: file_lock->fl_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); /* * Detect close/fcntl races and recover by zapping all POSIX locks * associated with this file and our files_struct, just like on * filp_flush(). There is no need to do that when we're * unlocking though, or for OFD locks. */ if (!error && file_lock->fl_type != F_UNLCK && !(file_lock->fl_flags & FL_OFDLCK)) { struct files_struct *files = current->files; /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in * close(). rcu_read_lock() wouldn't do. */ spin_lock(&files->file_lock); f = files_lookup_fd_locked(files, fd); spin_unlock(&files->file_lock); if (f != filp) { locks_remove_posix(filp, files); error = -EBADF; } } out: locks_free_lock(file_lock); return error; } #endif /* BITS_PER_LONG == 32 */ /* * This function is called when the file is being removed * from the task's fd array. POSIX locks belonging to this task * are deleted at this time. */ void locks_remove_posix(struct file *filp, fl_owner_t owner) { int error; struct inode *inode = locks_inode(filp); struct file_lock lock; struct file_lock_context *ctx; /* * If there are no locks held on this file, we don't need to call * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ ctx = locks_inode_context(inode); if (!ctx || list_empty(&ctx->flc_posix)) return; locks_init_lock(&lock); lock.fl_type = F_UNLCK; lock.fl_flags = FL_POSIX | FL_CLOSE; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; lock.fl_owner = owner; lock.fl_pid = current->tgid; lock.fl_file = filp; lock.fl_ops = NULL; lock.fl_lmops = NULL; error = vfs_lock_file(filp, F_SETLK, &lock, NULL); if (lock.fl_ops && lock.fl_ops->fl_release_private) lock.fl_ops->fl_release_private(&lock); trace_locks_remove_posix(inode, &lock, error); } EXPORT_SYMBOL(locks_remove_posix); /* The i_flctx must be valid when calling into here */ static void locks_remove_flock(struct file *filp, struct file_lock_context *flctx) { struct file_lock fl; struct inode *inode = locks_inode(filp); if (list_empty(&flctx->flc_flock)) return; flock_make_lock(filp, LOCK_UN, &fl); fl.fl_flags |= FL_CLOSE; if (filp->f_op->flock) filp->f_op->flock(filp, F_SETLKW, &fl); else flock_lock_inode(inode, &fl); if (fl.fl_ops && fl.fl_ops->fl_release_private) fl.fl_ops->fl_release_private(&fl); } /* The i_flctx must be valid when calling into here */ static void locks_remove_lease(struct file *filp, struct file_lock_context *ctx) { struct file_lock *fl, *tmp; LIST_HEAD(dispose); if (list_empty(&ctx->flc_lease)) return; percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) if (filp == fl->fl_file) lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } /* * This function is called on the last close of an open file. */ void locks_remove_file(struct file *filp) { struct file_lock_context *ctx; ctx = locks_inode_context(locks_inode(filp)); if (!ctx) return; /* remove any OFD locks */ locks_remove_posix(filp, filp); /* remove flock locks */ locks_remove_flock(filp, ctx); /* remove any leases */ locks_remove_lease(filp, ctx); spin_lock(&ctx->flc_lock); locks_check_ctx_file_list(filp, &ctx->flc_posix, "POSIX"); locks_check_ctx_file_list(filp, &ctx->flc_flock, "FLOCK"); locks_check_ctx_file_list(filp, &ctx->flc_lease, "LEASE"); spin_unlock(&ctx->flc_lock); } /** * vfs_cancel_lock - file byte range unblock lock * @filp: The file to apply the unblock to * @fl: The lock to be unblocked * * Used by lock managers to cancel blocked requests */ int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { if (filp->f_op->lock) return filp->f_op->lock(filp, F_CANCELLK, fl); return 0; } EXPORT_SYMBOL_GPL(vfs_cancel_lock); /** * vfs_inode_has_locks - are any file locks held on @inode? * @inode: inode to check for locks * * Return true if there are any FL_POSIX or FL_FLOCK locks currently * set on @inode. */ bool vfs_inode_has_locks(struct inode *inode) { struct file_lock_context *ctx; bool ret; ctx = locks_inode_context(inode); if (!ctx) return false; spin_lock(&ctx->flc_lock); ret = !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_flock); spin_unlock(&ctx->flc_lock); return ret; } EXPORT_SYMBOL_GPL(vfs_inode_has_locks); #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> struct locks_iterator { int li_cpu; loff_t li_pos; }; static void lock_get_status(struct seq_file *f, struct file_lock *fl, loff_t id, char *pfx) { struct inode *inode = NULL; unsigned int fl_pid; struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); fl_pid = locks_translate_pid(fl, proc_pidns); /* * If lock owner is dead (and pid is freed) or not visible in current * pidns, zero is shown as a pid value. Check lock info from * init_pid_ns to get saved lock pid value. */ if (fl->fl_file != NULL) inode = locks_inode(fl->fl_file); seq_printf(f, "%lld:%s ", id, pfx); if (IS_POSIX(fl)) { if (fl->fl_flags & FL_ACCESS) seq_puts(f, "ACCESS"); else if (IS_OFDLCK(fl)) seq_puts(f, "OFDLCK"); else seq_puts(f, "POSIX "); seq_printf(f, " %s ", (inode == NULL) ? "*NOINODE*" : mandatory_lock(inode) ? "MANDATORY" : "ADVISORY "); } else if (IS_FLOCK(fl)) { if (fl->fl_type & LOCK_MAND) { seq_puts(f, "FLOCK MSNFS "); } else { seq_puts(f, "FLOCK ADVISORY "); } } else if (IS_LEASE(fl)) { if (fl->fl_flags & FL_DELEG) seq_puts(f, "DELEG "); else seq_puts(f, "LEASE "); if (lease_breaking(fl)) seq_puts(f, "BREAKING "); else if (fl->fl_file) seq_puts(f, "ACTIVE "); else seq_puts(f, "BREAKER "); } else { seq_puts(f, "UNKNOWN UNKNOWN "); } if (fl->fl_type & LOCK_MAND) { seq_printf(f, "%s ", (fl->fl_type & LOCK_READ) ? (fl->fl_type & LOCK_WRITE) ? "RW " : "READ " : (fl->fl_type & LOCK_WRITE) ? "WRITE" : "NONE "); } else { int type = IS_LEASE(fl) ? target_leasetype(fl) : fl->fl_type; seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" : (type == F_RDLCK) ? "READ" : "UNLCK"); } if (inode) { /* userspace relies on this representation of dev_t */ seq_printf(f, "%d %02x:%02x:%lu ", fl_pid, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); } else { seq_printf(f, "%d <none>:0 ", fl_pid); } if (IS_POSIX(fl)) { if (fl->fl_end == OFFSET_MAX) seq_printf(f, "%Ld EOF\n", fl->fl_start); else seq_printf(f, "%Ld %Ld\n", fl->fl_start, fl->fl_end); } else { seq_puts(f, "0 EOF\n"); } } static int locks_show(struct seq_file *f, void *v) { struct locks_iterator *iter = f->private; struct file_lock *fl, *bfl; struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); fl = hlist_entry(v, struct file_lock, fl_link); if (locks_translate_pid(fl, proc_pidns) == 0) return 0; lock_get_status(f, fl, iter->li_pos, ""); list_for_each_entry(bfl, &fl->fl_blocked_requests, fl_blocked_member) lock_get_status(f, bfl, iter->li_pos, " ->"); return 0; } static void __show_fd_locks(struct seq_file *f, struct list_head *head, int *id, struct file *filp, struct files_struct *files) { struct file_lock *fl; list_for_each_entry(fl, head, fl_list) { if (filp != fl->fl_file) continue; if (fl->fl_owner != files && fl->fl_owner != filp) continue; (*id)++; seq_puts(f, "lock:\t"); lock_get_status(f, fl, *id, ""); } } void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) { struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; int id = 0; ctx = locks_inode_context(inode); if (!ctx) return; spin_lock(&ctx->flc_lock); __show_fd_locks(f, &ctx->flc_flock, &id, filp, files); __show_fd_locks(f, &ctx->flc_posix, &id, filp, files); __show_fd_locks(f, &ctx->flc_lease, &id, filp, files); spin_unlock(&ctx->flc_lock); } static void *locks_start(struct seq_file *f, loff_t *pos) __acquires(&blocked_lock_lock) { struct locks_iterator *iter = f->private; iter->li_pos = *pos + 1; percpu_down_write(&file_rwsem); spin_lock(&blocked_lock_lock); return seq_hlist_start_percpu(&file_lock_list.hlist, &iter->li_cpu, *pos); } static void *locks_next(struct seq_file *f, void *v, loff_t *pos) { struct locks_iterator *iter = f->private; ++iter->li_pos; return seq_hlist_next_percpu(v, &file_lock_list.hlist, &iter->li_cpu, pos); } static void locks_stop(struct seq_file *f, void *v) __releases(&blocked_lock_lock) { spin_unlock(&blocked_lock_lock); percpu_up_write(&file_rwsem); } static const struct seq_operations locks_seq_operations = { .start = locks_start, .next = locks_next, .stop = locks_stop, .show = locks_show, }; static int __init proc_locks_init(void) { proc_create_seq_private("locks", 0, NULL, &locks_seq_operations, sizeof(struct locks_iterator), NULL); return 0; } fs_initcall(proc_locks_init); #endif static int __init filelock_init(void) { int i; flctx_cache = kmem_cache_create("file_lock_ctx", sizeof(struct file_lock_context), 0, SLAB_PANIC, NULL); filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); for_each_possible_cpu(i) { struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i); spin_lock_init(&fll->lock); INIT_HLIST_HEAD(&fll->hlist); } lease_notifier_chain_init(); return 0; } core_initcall(filelock_init); |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGETLB_INLINE_H #define _LINUX_HUGETLB_INLINE_H #ifdef CONFIG_HUGETLB_PAGE #include <linux/mm.h> static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma) { return !!(vma->vm_flags & VM_HUGETLB); } #else static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma) { return false; } #endif #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/dcache.c * * Complete reimplementation * (C) 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ /* * Notes on the allocation strategy: * * The dcache is a master of the icache - whenever a dcache entry * exists, the inode will always exist. "iput()" is done either when * the dcache entry is deleted or garbage collected. */ #include <linux/ratelimit.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/cache.h> #include <linux/export.h> #include <linux/security.h> #include <linux/seqlock.h> #include <linux/memblock.h> #include <linux/bit_spinlock.h> #include <linux/rculist_bl.h> #include <linux/list_lru.h> #include "internal.h" #include "mount.h" /* * Usage: * dcache->d_inode->i_lock protects: * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_roots bl list spinlock protects: * - the s_roots list (see __d_drop) * dentry->d_sb->s_dentry_lru_lock protects: * - the dcache lru lists and counters * d_lock protects: * - d_flags * - d_name * - d_lru * - d_count * - d_unhashed() * - d_parent and d_subdirs * - childrens' d_child and d_parent * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock * dentry->d_lock * dentry->d_sb->s_dentry_lru_lock * dcache_hash_bucket lock * s_roots lock * * If there is an ancestor relationship: * dentry->d_parent->...->d_parent->d_lock * ... * dentry->d_parent->d_lock * dentry->d_lock * * If no ancestor relationship: * arbitrary, since it's serialized on rename_lock */ int sysctl_vfs_cache_pressure __read_mostly = 100; EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __read_mostly; const struct qstr empty_name = QSTR_INIT("", 0); EXPORT_SYMBOL(empty_name); const struct qstr slash_name = QSTR_INIT("/", 1); EXPORT_SYMBOL(slash_name); /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try * to make this good - I've just made it work. * * This hash-function tries to avoid losing too many bits of hash * information, yet avoid using a prime hash-size or similar. */ static unsigned int d_hash_shift __read_mostly; static struct hlist_bl_head *dentry_hashtable __read_mostly; static inline struct hlist_bl_head *d_hash(unsigned int hash) { return dentry_hashtable + (hash >> d_hash_shift); } #define IN_LOOKUP_SHIFT 10 static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT]; static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); } /* Statistics gathering. */ struct dentry_stat_t dentry_stat = { .age_limit = 45, }; static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* * Here we resort to our own counters instead of using generic per-cpu counters * for consistency with what the vfs inode code does. We are expected to harvest * better code and performance by having our own specialized counters. * * Please note that the loop is done over all possible CPUs, not over all online * CPUs. The reason for this is that we don't want to play games with CPUs going * on and off. If one of them goes off, we will just keep their counters. * * glommer: See cffbc8a for details, and if you ever intend to change this, * please update all vfs counters to match. */ static long get_nr_dentry(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_unused, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_negative(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_negative, i); return sum < 0 ? 0 : sum; } int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif /* * Compare 2 name strings, return 0 if they match, otherwise non-zero. * The strings are both count bytes long, and count is non-zero. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> /* * NOTE! 'cs' and 'scount' come from a dentry, so it has a * aligned allocation for this particular component. We don't * strictly need the load_unaligned_zeropad() safety, but it * doesn't hurt either. * * In contrast, 'ct' and 'tcount' can be from a pathname, and do * need the careful unaligned handling. */ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { unsigned long a,b,mask; for (;;) { a = read_word_at_a_time(cs); b = load_unaligned_zeropad(ct); if (tcount < sizeof(unsigned long)) break; if (unlikely(a != b)) return 1; cs += sizeof(unsigned long); ct += sizeof(unsigned long); tcount -= sizeof(unsigned long); if (!tcount) return 0; } mask = bytemask_from_count(tcount); return unlikely(!!((a ^ b) & mask)); } #else static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { do { if (*cs != *ct) return 1; cs++; ct++; tcount--; } while (tcount); return 0; } #endif static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) { /* * Be careful about RCU walk racing with rename: * use 'READ_ONCE' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The * RCU walk will check the sequence count eventually, * and catch it. And we won't overrun the buffer, * because we're reading the name pointer atomically, * and a dentry name is guaranteed to be properly * terminated with a NUL byte. * * End result: even if 'len' is wrong, we'll exit * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ const unsigned char *cs = READ_ONCE(dentry->d_name.name); return dentry_string_cmp(cs, ct, tcount); } struct external_name { union { atomic_t count; struct rcu_head head; } u; unsigned char name[]; }; static inline struct external_name *external_name(struct dentry *dentry) { return container_of(dentry->d_name.name, struct external_name, name[0]); } static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kmem_cache_free(dentry_cache, dentry); } static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); } static inline int dname_external(const struct dentry *dentry) { return dentry->d_name.name != dentry->d_iname; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { spin_lock(&dentry->d_lock); name->name = dentry->d_name; if (unlikely(dname_external(dentry))) { atomic_inc(&external_name(dentry)->u.count); } else { memcpy(name->inline_name, dentry->d_iname, dentry->d_name.len + 1); name->name.name = name->inline_name; } spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { if (unlikely(name->name.name != name->inline_name)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->u.count))) kfree_rcu(p, u.head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) { unsigned flags; dentry->d_inode = inode; flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); flags |= type_flags; smp_store_release(&dentry->d_flags, flags); } static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; /* * The negative counter only tracks dentries on the LRU. Don't inc if * d_lru is on another list. */ if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) { WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); if (likely(atomic_dec_and_test(&p->u.count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external); return; } } /* if dentry was never visible to RCU, immediate free is OK */ if (dentry->d_flags & DCACHE_NORCU) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. */ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_lock) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) fsnotify_inoderemove(inode); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else iput(inode); } /* * The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry * is in use - which includes both the "real" per-superblock * LRU list _and_ the DCACHE_SHRINK_LIST use. * * The DCACHE_SHRINK_LIST bit is set whenever the dentry is * on the shrink list (ie not on the superblock LRU list). * * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * * The per-cpu "nr_dentry_negative" counters are only updated * when deleted from or added to the per-superblock LRU list, not * from/to the shrink list. That is to avoid an unneeded dec/inc * pair when moving from LRU to shrink list in select_collect(). * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ #define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x)) static void d_lru_add(struct dentry *dentry) { D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_lru_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_shrink_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); list_del_init(&dentry->d_lru); dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); this_cpu_dec(nr_dentry_unused); } static void d_shrink_add(struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, 0); list_add(&dentry->d_lru, list); dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); } /* * These can only be called under the global LRU lock, ie during the * callback for freeing the LRU list. "isolate" removes it from the * LRU lists entirely, while shrink_move moves it to the indicated * private list. */ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } /** * d_drop - drop a dentry * @dentry: dentry to drop * * d_drop() unhashes the entry from the parent dentry hashes, so that it won't * be found through a VFS lookup any more. Note that this is different from * deleting the dentry - d_delete will try to mark the dentry negative if * possible, giving a successful _negative_ lookup, while d_drop will * just make the cache lookup fail. * * d_drop() is used mainly for stuff that wants to invalidate a dentry for some * reason (NFS timeouts or autofs deletes). * * __d_drop requires dentry->d_lock * ___d_drop doesn't mark dentry as "unhashed" * (dentry->d_hash.pprev will be LIST_POISON2, not NULL). */ static void ___d_drop(struct dentry *dentry) { struct hlist_bl_head *b; /* * Hashed dentries are normally on the dentry hashtable, * with the exception of those newly allocated by * d_obtain_root, which are always IS_ROOT: */ if (unlikely(IS_ROOT(dentry))) b = &dentry->d_sb->s_roots; else b = d_hash(dentry->d_name.hash); hlist_bl_lock(b); __hlist_bl_del(&dentry->d_hash); hlist_bl_unlock(b); } void __d_drop(struct dentry *dentry) { if (!d_unhashed(dentry)) { ___d_drop(dentry); dentry->d_hash.pprev = NULL; write_seqcount_invalidate(&dentry->d_seq); } } EXPORT_SYMBOL(__d_drop); void d_drop(struct dentry *dentry) { spin_lock(&dentry->d_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_drop); static inline void dentry_unlist(struct dentry *dentry, struct dentry *parent) { struct dentry *next; /* * Inform d_walk() and shrink_dentry_list() that we are no longer * attached to the dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; if (unlikely(list_empty(&dentry->d_child))) return; __list_del_entry(&dentry->d_child); /* * Cursors can move around the list of children. While we'd been * a normal list member, it didn't matter - ->d_child.next would've * been updated. However, from now on it won't be and for the * things like d_walk() it might end up with a nasty surprise. * Normally d_walk() doesn't care about cursors moving around - * ->d_lock on parent prevents that and since a cursor has no children * of its own, we get through it without ever unlocking the parent. * There is one exception, though - if we ascend from a child that * gets killed as soon as we unlock it, the next sibling is found * using the value left in its ->d_child.next. And if _that_ * pointed to a cursor, and cursor got moved (e.g. by lseek()) * before d_walk() regains parent->d_lock, we'll end up skipping * everything the cursor had been moved past. * * Solution: make sure that the pointer left behind in ->d_child.next * points to something that won't be moving around. I.e. skip the * cursors. */ while (dentry->d_child.next != &parent->d_subdirs) { next = list_entry(dentry->d_child.next, struct dentry, d_child); if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) break; dentry->d_child.next = next->d_child.next; } } static void __dentry_kill(struct dentry *dentry) { struct dentry *parent = NULL; bool can_free = true; if (!IS_ROOT(dentry)) parent = dentry->d_parent; /* * The dentry is now unrecoverably dead to the world. */ lockref_mark_dead(&dentry->d_lockref); /* * inform the fs via d_prune that this dentry is about to be * unhashed and destroyed. */ if (dentry->d_flags & DCACHE_OP_PRUNE) dentry->d_op->d_prune(dentry); if (dentry->d_flags & DCACHE_LRU_LIST) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) d_lru_del(dentry); } /* if it was on the hash then remove it */ __d_drop(dentry); dentry_unlist(dentry, parent); if (parent) spin_unlock(&parent->d_lock); if (dentry->d_inode) dentry_unlink_inode(dentry); else spin_unlock(&dentry->d_lock); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); spin_lock(&dentry->d_lock); if (dentry->d_flags & DCACHE_SHRINK_LIST) { dentry->d_flags |= DCACHE_MAY_FREE; can_free = false; } spin_unlock(&dentry->d_lock); if (likely(can_free)) dentry_free(dentry); cond_resched(); } static struct dentry *__lock_parent(struct dentry *dentry) { struct dentry *parent; rcu_read_lock(); spin_unlock(&dentry->d_lock); again: parent = READ_ONCE(dentry->d_parent); spin_lock(&parent->d_lock); /* * We can't blindly lock dentry until we are sure * that we won't violate the locking order. * Any changes of dentry->d_parent must have * been done with parent->d_lock held, so * spin_lock() above is enough of a barrier * for checking if it's still our child. */ if (unlikely(parent != dentry->d_parent)) { spin_unlock(&parent->d_lock); goto again; } rcu_read_unlock(); if (parent != dentry) spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); else parent = NULL; return parent; } static inline struct dentry *lock_parent(struct dentry *dentry) { struct dentry *parent = dentry->d_parent; if (IS_ROOT(dentry)) return NULL; if (likely(spin_trylock(&parent->d_lock))) return parent; return __lock_parent(dentry); } static inline bool retain_dentry(struct dentry *dentry) { WARN_ON(d_in_lookup(dentry)); /* Unreachable? Get rid of it */ if (unlikely(d_unhashed(dentry))) return false; if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED)) return false; if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) { if (dentry->d_op->d_delete(dentry)) return false; } if (unlikely(dentry->d_flags & DCACHE_DONTCACHE)) return false; /* retain; LRU fodder */ dentry->d_lockref.count--; if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST))) d_lru_add(dentry); else if (unlikely(!(dentry->d_flags & DCACHE_REFERENCED))) dentry->d_flags |= DCACHE_REFERENCED; return true; } void d_mark_dontcache(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); hlist_for_each_entry(de, &inode->i_dentry, d_u.d_alias) { spin_lock(&de->d_lock); de->d_flags |= DCACHE_DONTCACHE; spin_unlock(&de->d_lock); } inode->i_state |= I_DONTCACHE; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_mark_dontcache); /* * Finish off a dentry we've decided to kill. * dentry->d_lock must be held, returns with it unlocked. * Returns dentry requiring refcount drop, or NULL if we're done. */ static struct dentry *dentry_kill(struct dentry *dentry) __releases(dentry->d_lock) { struct inode *inode = dentry->d_inode; struct dentry *parent = NULL; if (inode && unlikely(!spin_trylock(&inode->i_lock))) goto slow_positive; if (!IS_ROOT(dentry)) { parent = dentry->d_parent; if (unlikely(!spin_trylock(&parent->d_lock))) { parent = __lock_parent(dentry); if (likely(inode || !dentry->d_inode)) goto got_locks; /* negative that became positive */ if (parent) spin_unlock(&parent->d_lock); inode = dentry->d_inode; goto slow_positive; } } __dentry_kill(dentry); return parent; slow_positive: spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); parent = lock_parent(dentry); got_locks: if (unlikely(dentry->d_lockref.count != 1)) { dentry->d_lockref.count--; } else if (likely(!retain_dentry(dentry))) { __dentry_kill(dentry); return parent; } /* we are keeping it, after all */ if (inode) spin_unlock(&inode->i_lock); if (parent) spin_unlock(&parent->d_lock); spin_unlock(&dentry->d_lock); return NULL; } /* * Try to do a lockless dput(), and return whether that was successful. * * If unsuccessful, we return false, having already taken the dentry lock. * * The caller needs to hold the RCU read lock, so that the dentry is * guaranteed to stay around even if the refcount goes down to zero! */ static inline bool fast_dput(struct dentry *dentry) { int ret; unsigned int d_flags; /* * If we have a d_op->d_delete() operation, we sould not * let the dentry count go to zero, so use "put_or_lock". */ if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) return lockref_put_or_lock(&dentry->d_lockref); /* * .. otherwise, we can try to just decrement the * lockref optimistically. */ ret = lockref_put_return(&dentry->d_lockref); /* * If the lockref_put_return() failed due to the lock being held * by somebody else, the fast path has failed. We will need to * get the lock, and then check the count again. */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } dentry->d_lockref.count--; goto locked; } /* * If we weren't the last ref, we're done. */ if (ret) return true; /* * Careful, careful. The reference count went down * to zero, but we don't hold the dentry lock, so * somebody else could get it again, and do another * dput(), and we need to not race with that. * * However, there is a very special and common case * where we don't care, because there is nothing to * do: the dentry is still hashed, it does not have * a 'delete' op, and it's referenced and already on * the LRU list. * * NOTE! Since we aren't locked, these values are * not "stable". However, it is sufficient that at * some point after we dropped the reference the * dentry was hashed and the flags had the proper * value. Other dentry users may have re-gotten * a reference to the dentry and change that, but * our work is done - we can leave the dentry * around with a zero refcount. */ smp_rmb(); d_flags = READ_ONCE(dentry->d_flags); d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED; /* Nothing to do? Dropping the reference was all we needed? */ if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry)) return true; /* * Not the fast normal case? Get the lock. We've already decremented * the refcount, but we'll need to re-check the situation after * getting the lock. */ spin_lock(&dentry->d_lock); /* * Did somebody else grab a reference to it in the meantime, and * we're no longer the last user after all? Alternatively, somebody * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ locked: if (dentry->d_lockref.count) { spin_unlock(&dentry->d_lock); return true; } /* * Re-get the reference we optimistically dropped. We hold the * lock, and we just tested that it was zero, so we can just * set it to 1. */ dentry->d_lockref.count = 1; return false; } /* * This is dput * * This is complicated by the fact that we do not want to put * dentries that are no longer on any hash chain on the unused * list: we'd much rather just get rid of them immediately. * * However, that implies that we have to traverse the dentry * tree upwards to the parents which might _also_ now be * scheduled for deletion (it may have been only waiting for * its last child to go away). * * This tail recursion is done by hand as we don't want to depend * on the compiler to always get this right (gcc generally doesn't). * Real recursion would eat up our stack space. */ /* * dput - release a dentry * @dentry: dentry to release * * Release a dentry. This will drop the usage count and if appropriate * call the dentry unlink method as well as removing it from the queues and * releasing its resources. If the parent dentries were scheduled for release * they too may now get deleted. */ void dput(struct dentry *dentry) { while (dentry) { might_sleep(); rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } /* Slow case: now with the dentry lock held */ rcu_read_unlock(); if (likely(retain_dentry(dentry))) { spin_unlock(&dentry->d_lock); return; } dentry = dentry_kill(dentry); } } EXPORT_SYMBOL(dput); static void __dput_to_list(struct dentry *dentry, struct list_head *list) __must_hold(&dentry->d_lock) { if (dentry->d_flags & DCACHE_SHRINK_LIST) { /* let the owner of the list it's on deal with it */ --dentry->d_lockref.count; } else { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); if (!--dentry->d_lockref.count) d_shrink_add(dentry, list); } } void dput_to_list(struct dentry *dentry, struct list_head *list) { rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } rcu_read_unlock(); if (!retain_dentry(dentry)) __dput_to_list(dentry, list); spin_unlock(&dentry->d_lock); } /* This must be called with d_lock held */ static inline void __dget_dlock(struct dentry *dentry) { dentry->d_lockref.count++; } static inline void __dget(struct dentry *dentry) { lockref_get(&dentry->d_lockref); } struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; unsigned seq; /* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); } repeat: /* * Don't need rcu_dereference because we re-check it was correct under * the lock. */ rcu_read_lock(); ret = dentry->d_parent; spin_lock(&ret->d_lock); if (unlikely(ret != dentry->d_parent)) { spin_unlock(&ret->d_lock); rcu_read_unlock(); goto repeat; } rcu_read_unlock(); BUG_ON(!ret->d_lockref.count); ret->d_lockref.count++; spin_unlock(&ret->d_lock); return ret; } EXPORT_SYMBOL(dget_parent); static struct dentry * __d_find_any_alias(struct inode *inode) { struct dentry *alias; if (hlist_empty(&inode->i_dentry)) return NULL; alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); __dget(alias); return alias; } /** * d_find_any_alias - find any alias for a given inode * @inode: inode to find an alias for * * If any aliases exist for the given inode, take and return a * reference for one of them. If no aliases exist, return %NULL. */ struct dentry *d_find_any_alias(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); de = __d_find_any_alias(inode); spin_unlock(&inode->i_lock); return de; } EXPORT_SYMBOL(d_find_any_alias); /** * d_find_alias - grab a hashed alias of inode * @inode: inode in question * * If inode has a hashed alias, or is a directory and has any alias, * acquire the reference to alias and return it. Otherwise return NULL. * Notice that if inode is a directory there can be only one alias and * it can be unhashed only if it has no children, or if it is the root * of a filesystem, or if the directory was renamed and d_revalidate * was the first vfs operation to notice. * * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer * any other hashed alias over that one. */ static struct dentry *__d_find_alias(struct inode *inode) { struct dentry *alias; if (S_ISDIR(inode->i_mode)) return __d_find_any_alias(inode); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { __dget_dlock(alias); spin_unlock(&alias->d_lock); return alias; } spin_unlock(&alias->d_lock); } return NULL; } struct dentry *d_find_alias(struct inode *inode) { struct dentry *de = NULL; if (!hlist_empty(&inode->i_dentry)) { spin_lock(&inode->i_lock); de = __d_find_alias(inode); spin_unlock(&inode->i_lock); } return de; } EXPORT_SYMBOL(d_find_alias); /* * Try to kill dentries associated with this inode. * WARNING: you must own a reference to inode. */ void d_prune_aliases(struct inode *inode) { struct dentry *dentry; restart: spin_lock(&inode->i_lock); hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) { struct dentry *parent = lock_parent(dentry); if (likely(!dentry->d_lockref.count)) { __dentry_kill(dentry); dput(parent); goto restart; } if (parent) spin_unlock(&parent->d_lock); } spin_unlock(&dentry->d_lock); } spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_prune_aliases); /* * Lock a dentry from shrink list. * Called under rcu_read_lock() and dentry->d_lock; the former * guarantees that nothing we access will be freed under us. * Note that dentry is *not* protected from concurrent dentry_kill(), * d_delete(), etc. * * Return false if dentry has been disrupted or grabbed, leaving * the caller to kick it off-list. Otherwise, return true and have * that dentry's inode and parent both locked. */ static bool shrink_lock_dentry(struct dentry *dentry) { struct inode *inode; struct dentry *parent; if (dentry->d_lockref.count) return false; inode = dentry->d_inode; if (inode && unlikely(!spin_trylock(&inode->i_lock))) { spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); if (unlikely(dentry->d_lockref.count)) goto out; /* changed inode means that somebody had grabbed it */ if (unlikely(inode != dentry->d_inode)) goto out; } parent = dentry->d_parent; if (IS_ROOT(dentry) || likely(spin_trylock(&parent->d_lock))) return true; spin_unlock(&dentry->d_lock); spin_lock(&parent->d_lock); if (unlikely(parent != dentry->d_parent)) { spin_unlock(&parent->d_lock); spin_lock(&dentry->d_lock); goto out; } spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); if (likely(!dentry->d_lockref.count)) return true; spin_unlock(&parent->d_lock); out: if (inode) spin_unlock(&inode->i_lock); return false; } void shrink_dentry_list(struct list_head *list) { while (!list_empty(list)) { struct dentry *dentry, *parent; dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); rcu_read_lock(); if (!shrink_lock_dentry(dentry)) { bool can_free = false; rcu_read_unlock(); d_shrink_del(dentry); if (dentry->d_lockref.count < 0) can_free = dentry->d_flags & DCACHE_MAY_FREE; spin_unlock(&dentry->d_lock); if (can_free) dentry_free(dentry); continue; } rcu_read_unlock(); d_shrink_del(dentry); parent = dentry->d_parent; if (parent != dentry) __dput_to_list(parent, list); __dentry_kill(dentry); } } static enum lru_status dentry_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; /* * Referenced dentries are still in use. If they have active * counts, just remove them from the LRU. Otherwise give them * another pass through the LRU. */ if (dentry->d_lockref.count) { d_lru_isolate(lru, dentry); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } if (dentry->d_flags & DCACHE_REFERENCED) { dentry->d_flags &= ~DCACHE_REFERENCED; spin_unlock(&dentry->d_lock); /* * The list move itself will be made by the common LRU code. At * this point, we've dropped the dentry->d_lock but keep the * lru lock. This is safe to do, since every list movement is * protected by the lru lock even if both locks are held. * * This is guaranteed by the fact that all LRU management * functions are intermediated by the LRU API calls like * list_lru_add and list_lru_del. List movement in this file * only ever occur through this functions or through callbacks * like this one, that are called from the LRU API. * * The only exceptions to this are functions like * shrink_dentry_list, and code that first checks for the * DCACHE_SHRINK_LIST flag. Those are guaranteed to be * operating only with stack provided lists after they are * properly isolated from the main list. It is thus, always a * local access. */ return LRU_ROTATE; } d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * prune_dcache_sb - shrink the dcache * @sb: superblock * @sc: shrink control, passed to list_lru_shrink_walk() * * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This * is done when we need more memory and called from the superblock shrinker * function. * * This function may fail to free any resources if all the dentries are in * use. */ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(dispose); long freed; freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc, dentry_lru_isolate, &dispose); shrink_dentry_list(&dispose); return freed; } static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock * * Shrink the dcache for the specified super block. This is used to free * the dcache before unmounting a file system. */ void shrink_dcache_sb(struct super_block *sb) { do { LIST_HEAD(dispose); list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); /** * enum d_walk_ret - action to talke during tree walk * @D_WALK_CONTINUE: contrinue walk * @D_WALK_QUIT: quit walk * @D_WALK_NORETRY: quit when retry is needed * @D_WALK_SKIP: skip this dentry and its children */ enum d_walk_ret { D_WALK_CONTINUE, D_WALK_QUIT, D_WALK_NORETRY, D_WALK_SKIP, }; /** * d_walk - walk the dentry tree * @parent: start of walk * @data: data passed to @enter() and @finish() * @enter: callback when first entering the dentry * * The @enter() callbacks are called with d_lock held. */ static void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { struct dentry *this_parent; struct list_head *next; unsigned seq = 0; enum d_walk_ret ret; bool retry = true; again: read_seqbegin_or_lock(&rename_lock, &seq); this_parent = parent; spin_lock(&this_parent->d_lock); ret = enter(data, this_parent); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: case D_WALK_SKIP: goto out_unlock; case D_WALK_NORETRY: retry = false; break; } repeat: next = this_parent->d_subdirs.next; resume: while (next != &this_parent->d_subdirs) { struct list_head *tmp = next; struct dentry *dentry = list_entry(tmp, struct dentry, d_child); next = tmp->next; if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); ret = enter(data, dentry); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: spin_unlock(&dentry->d_lock); goto out_unlock; case D_WALK_NORETRY: retry = false; break; case D_WALK_SKIP: spin_unlock(&dentry->d_lock); continue; } if (!list_empty(&dentry->d_subdirs)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); this_parent = dentry; spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } spin_unlock(&dentry->d_lock); } /* * All done at this level ... ascend and resume the search. */ rcu_read_lock(); ascend: if (this_parent != parent) { struct dentry *child = this_parent; this_parent = child->d_parent; spin_unlock(&child->d_lock); spin_lock(&this_parent->d_lock); /* might go back up the wrong parent if we have had a rename. */ if (need_seqretry(&rename_lock, seq)) goto rename_retry; /* go into the first sibling still alive */ do { next = child->d_child.next; if (next == &this_parent->d_subdirs) goto ascend; child = list_entry(next, struct dentry, d_child); } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); rcu_read_unlock(); goto resume; } if (need_seqretry(&rename_lock, seq)) goto rename_retry; rcu_read_unlock(); out_unlock: spin_unlock(&this_parent->d_lock); done_seqretry(&rename_lock, seq); return; rename_retry: spin_unlock(&this_parent->d_lock); rcu_read_unlock(); BUG_ON(seq & 1); if (!retry) return; seq = 1; goto again; } struct check_mount { struct vfsmount *mnt; unsigned int mounted; }; static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry) { struct check_mount *info = data; struct path path = { .mnt = info->mnt, .dentry = dentry }; if (likely(!d_mountpoint(dentry))) return D_WALK_CONTINUE; if (__path_is_mountpoint(&path)) { info->mounted = 1; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * path_has_submounts - check for mounts over a dentry in the * current namespace. * @parent: path to check. * * Return true if the parent or its subdirectories contain * a mount point in the current namespace. */ int path_has_submounts(const struct path *parent) { struct check_mount data = { .mnt = parent->mnt, .mounted = 0 }; read_seqlock_excl(&mount_lock); d_walk(parent->dentry, &data, path_check_mount); read_sequnlock_excl(&mount_lock); return data.mounted; } EXPORT_SYMBOL(path_has_submounts); /* * Called by mount code to set a mountpoint and check if the mountpoint is * reachable (e.g. NFS can unhash a directory dentry and then the complete * subtree can become unreachable). * * Only one of d_invalidate() and d_set_mounted() must succeed. For * this reason take rename_lock and d_lock on dentry and ancestors. */ int d_set_mounted(struct dentry *dentry) { struct dentry *p; int ret = -ENOENT; write_seqlock(&rename_lock); for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) { /* Need exclusion wrt. d_invalidate() */ spin_lock(&p->d_lock); if (unlikely(d_unhashed(p))) { spin_unlock(&p->d_lock); goto out; } spin_unlock(&p->d_lock); } spin_lock(&dentry->d_lock); if (!d_unlinked(dentry)) { ret = -EBUSY; if (!d_mountpoint(dentry)) { dentry->d_flags |= DCACHE_MOUNTED; ret = 0; } } spin_unlock(&dentry->d_lock); out: write_sequnlock(&rename_lock); return ret; } /* * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level * whenever the d_subdirs list is non-empty and continue * searching. * * It returns zero iff there are no unused children, * otherwise it returns the number of children moved to * the end of the unused list. This may not be the total * number of unused children, because select_parent can * drop the lock and return early due to latency * constraints. */ struct select_data { struct dentry *start; union { long found; struct dentry *victim; }; struct list_head dispose; }; static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { data->found++; } else { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); if (!dentry->d_lockref.count) { d_shrink_add(dentry, &data->dispose); data->found++; } } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { if (!dentry->d_lockref.count) { rcu_read_lock(); data->victim = dentry; return D_WALK_QUIT; } } else { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); if (!dentry->d_lockref.count) d_shrink_add(dentry, &data->dispose); } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } /** * shrink_dcache_parent - prune dcache * @parent: parent of entries to prune * * Prune the dcache to remove unused children of the parent dentry. */ void shrink_dcache_parent(struct dentry *parent) { for (;;) { struct select_data data = {.start = parent}; INIT_LIST_HEAD(&data.dispose); d_walk(parent, &data, select_collect); if (!list_empty(&data.dispose)) { shrink_dentry_list(&data.dispose); continue; } cond_resched(); if (!data.found) break; data.victim = NULL; d_walk(parent, &data, select_collect2); if (data.victim) { struct dentry *parent; spin_lock(&data.victim->d_lock); if (!shrink_lock_dentry(data.victim)) { spin_unlock(&data.victim->d_lock); rcu_read_unlock(); } else { rcu_read_unlock(); parent = data.victim->d_parent; if (parent != data.victim) __dput_to_list(parent, &data.dispose); __dentry_kill(data.victim); } } if (!list_empty(&data.dispose)) shrink_dentry_list(&data.dispose); } } EXPORT_SYMBOL(shrink_dcache_parent); static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { /* it has busy descendents; complain about those instead */ if (!list_empty(&dentry->d_subdirs)) return D_WALK_CONTINUE; /* root with refcount 1 is fine */ if (dentry == _data && dentry->d_lockref.count == 1) return D_WALK_CONTINUE; printk(KERN_ERR "BUG: Dentry %p{i=%lx,n=%pd} " " still in use (%d) [unmount of %s %s]\n", dentry, dentry->d_inode ? dentry->d_inode->i_ino : 0UL, dentry, dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); WARN_ON(1); return D_WALK_CONTINUE; } static void do_one_tree(struct dentry *dentry) { shrink_dcache_parent(dentry); d_walk(dentry, dentry, umount_check); d_drop(dentry); dput(dentry); } /* * destroy the dentries attached to a superblock on unmounting */ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; WARN(down_read_trylock(&sb->s_umount), "s_umount should've been locked"); dentry = sb->s_root; sb->s_root = NULL; do_one_tree(dentry); while (!hlist_bl_empty(&sb->s_roots)) { dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash)); do_one_tree(dentry); } } static enum d_walk_ret find_submount(void *_data, struct dentry *dentry) { struct dentry **victim = _data; if (d_mountpoint(dentry)) { __dget_dlock(dentry); *victim = dentry; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * d_invalidate - detach submounts, prune dcache, and drop * @dentry: dentry to invalidate (aka detach, prune and drop) */ void d_invalidate(struct dentry *dentry) { bool had_submounts = false; spin_lock(&dentry->d_lock); if (d_unhashed(dentry)) { spin_unlock(&dentry->d_lock); return; } __d_drop(dentry); spin_unlock(&dentry->d_lock); /* Negative dentries can be dropped without further checks */ if (!dentry->d_inode) return; shrink_dcache_parent(dentry); for (;;) { struct dentry *victim = NULL; d_walk(dentry, &victim, find_submount); if (!victim) { if (had_submounts) shrink_dcache_parent(dentry); return; } had_submounts = true; detach_mounts(victim); dput(victim); } } EXPORT_SYMBOL(d_invalidate); /** * __d_alloc - allocate a dcache entry * @sb: filesystem it will belong to * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { struct dentry *dentry; char *dname; int err; dentry = kmem_cache_alloc(dentry_cache, GFP_KERNEL); if (!dentry) return NULL; /* * We guarantee that the inline name is always NUL-terminated. * This way the memcpy() done by the name switching in rename * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; dname = dentry->d_iname; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT | __GFP_RECLAIMABLE); if (!p) { kmem_cache_free(dentry_cache, dentry); return NULL; } atomic_set(&p->u.count, 1); dname = p->name; } else { dname = dentry->d_iname; } dentry->d_name.len = name->len; dentry->d_name.hash = name->hash; memcpy(dname, name->name, name->len); dname[name->len] = 0; /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->d_name.name, dname); /* ^^^ */ dentry->d_lockref.count = 1; dentry->d_flags = 0; spin_lock_init(&dentry->d_lock); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; dentry->d_sb = sb; dentry->d_op = NULL; dentry->d_fsdata = NULL; INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_LIST_HEAD(&dentry->d_subdirs); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_child); d_set_d_op(dentry, dentry->d_sb->s_d_op); if (dentry->d_op && dentry->d_op->d_init) { err = dentry->d_op->d_init(dentry); if (err) { if (dname_external(dentry)) kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); return NULL; } } this_cpu_inc(nr_dentry); return dentry; } /** * d_alloc - allocate a dcache entry * @parent: parent of entry to allocate * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) { struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject * to concurrency here */ __dget_dlock(parent); dentry->d_parent = parent; list_add(&dentry->d_child, &parent->d_subdirs); spin_unlock(&parent->d_lock); return dentry; } EXPORT_SYMBOL(d_alloc); struct dentry *d_alloc_anon(struct super_block *sb) { return __d_alloc(sb, NULL); } EXPORT_SYMBOL(d_alloc_anon); struct dentry *d_alloc_cursor(struct dentry * parent) { struct dentry *dentry = d_alloc_anon(parent->d_sb); if (dentry) { dentry->d_flags |= DCACHE_DENTRY_CURSOR; dentry->d_parent = dget(parent); } return dentry; } /** * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems) * @sb: the superblock * @name: qstr of the name * * For a filesystem that just pins its dentries in memory and never * performs lookups at all, return an unhashed IS_ROOT dentry. * This is used for pipes, sockets et.al. - the stuff that should * never be anyone's children or parents. Unlike all other * dentries, these will not have RCU delay between dropping the * last reference and freeing them. * * The only user is alloc_file_pseudo() and that's what should * be considered a public interface. Don't use directly. */ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name) { struct dentry *dentry = __d_alloc(sb, name); if (likely(dentry)) dentry->d_flags |= DCACHE_NORCU; return dentry; } struct dentry *d_alloc_name(struct dentry *parent, const char *name) { struct qstr q; q.name = name; q.hash_len = hashlen_string(parent, name); return d_alloc(parent, &q); } EXPORT_SYMBOL(d_alloc_name); void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) { WARN_ON_ONCE(dentry->d_op); WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH | DCACHE_OP_COMPARE | DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | DCACHE_OP_REAL)); dentry->d_op = op; if (!op) return; if (op->d_hash) dentry->d_flags |= DCACHE_OP_HASH; if (op->d_compare) dentry->d_flags |= DCACHE_OP_COMPARE; if (op->d_revalidate) dentry->d_flags |= DCACHE_OP_REVALIDATE; if (op->d_weak_revalidate) dentry->d_flags |= DCACHE_OP_WEAK_REVALIDATE; if (op->d_delete) dentry->d_flags |= DCACHE_OP_DELETE; if (op->d_prune) dentry->d_flags |= DCACHE_OP_PRUNE; if (op->d_real) dentry->d_flags |= DCACHE_OP_REAL; } EXPORT_SYMBOL(d_set_d_op); /* * d_set_fallthru - Mark a dentry as falling through to a lower layer * @dentry - The dentry to mark * * Mark a dentry as falling through to the lower layer (as set with * d_pin_lower()). This flag may be recorded on the medium. */ void d_set_fallthru(struct dentry *dentry) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_FALLTHRU; spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_set_fallthru); static unsigned d_flags_for_inode(struct inode *inode) { unsigned add_flags = DCACHE_REGULAR_TYPE; if (!inode) return DCACHE_MISS_TYPE; if (S_ISDIR(inode->i_mode)) { add_flags = DCACHE_DIRECTORY_TYPE; if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) { if (unlikely(!inode->i_op->lookup)) add_flags = DCACHE_AUTODIR_TYPE; else inode->i_opflags |= IOP_LOOKUP; } goto type_determined; } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } inode->i_opflags |= IOP_NOFOLLOW; } if (unlikely(!S_ISREG(inode->i_mode))) add_flags = DCACHE_SPECIAL_TYPE; type_determined: if (unlikely(IS_AUTOMOUNT(inode))) add_flags |= DCACHE_NEED_AUTOMOUNT; return add_flags; } static void __d_instantiate(struct dentry *dentry, struct inode *inode) { unsigned add_flags = d_flags_for_inode(inode); WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); /* * The negative counter only tracks dentries on the LRU. Don't dec if * d_lru is on another list. */ if ((dentry->d_flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); spin_unlock(&dentry->d_lock); } /** * d_instantiate - fill in inode information for a dentry * @entry: dentry to complete * @inode: inode to attach to this dentry * * Fill in inode information in the entry. * * This turns negative dentries into productive full members * of society. * * NOTE! This assumes that the inode count has been incremented * (or otherwise set) by the caller to indicate that it is now * in use by the dcache. */ void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_instantiate); /* * This should be equivalent to d_instantiate() + unlock_new_inode(), * with lockdep-related part of unlock_new_inode() done before * anything else. Use that instead of open-coding d_instantiate()/ * unlock_new_inode() combinations. */ void d_instantiate_new(struct dentry *entry, struct inode *inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); BUG_ON(!inode); lockdep_annotate_inode_mutex_key(inode); security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); struct dentry *d_make_root(struct inode *root_inode) { struct dentry *res = NULL; if (root_inode) { res = d_alloc_anon(root_inode->i_sb); if (res) d_instantiate(res, root_inode); else iput(root_inode); } return res; } EXPORT_SYMBOL(d_make_root); static struct dentry *__d_instantiate_anon(struct dentry *dentry, struct inode *inode, bool disconnected) { struct dentry *res; unsigned add_flags; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); res = __d_find_any_alias(inode); if (res) { spin_unlock(&inode->i_lock); dput(dentry); goto out_iput; } /* attach a disconnected dentry */ add_flags = d_flags_for_inode(inode); if (disconnected) add_flags |= DCACHE_DISCONNECTED; spin_lock(&dentry->d_lock); __d_set_inode_and_type(dentry, inode, add_flags); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); if (!disconnected) { hlist_bl_lock(&dentry->d_sb->s_roots); hlist_bl_add_head(&dentry->d_hash, &dentry->d_sb->s_roots); hlist_bl_unlock(&dentry->d_sb->s_roots); } spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); return dentry; out_iput: iput(inode); return res; } struct dentry *d_instantiate_anon(struct dentry *dentry, struct inode *inode) { return __d_instantiate_anon(dentry, inode, true); } EXPORT_SYMBOL(d_instantiate_anon); static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected) { struct dentry *tmp; struct dentry *res; if (!inode) return ERR_PTR(-ESTALE); if (IS_ERR(inode)) return ERR_CAST(inode); res = d_find_any_alias(inode); if (res) goto out_iput; tmp = d_alloc_anon(inode->i_sb); if (!tmp) { res = ERR_PTR(-ENOMEM); goto out_iput; } return __d_instantiate_anon(tmp, inode, disconnected); out_iput: iput(inode); return res; } /** * d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain a dentry for an inode resulting from NFS filehandle conversion or * similar open by handle operations. The returned dentry may be anonymous, * or may have a full name (if the inode was already in the cache). * * When called on a directory inode, we must ensure that the inode only ever * has one dentry. If a dentry is found, that is returned instead of * allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is released. * To make it easier to use in export operations a %NULL or IS_ERR inode may * be passed in and the error will be propagated to the return value, * with a %NULL @inode replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_alias(struct inode *inode) { return __d_obtain_alias(inode, true); } EXPORT_SYMBOL(d_obtain_alias); /** * d_obtain_root - find or allocate a dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain an IS_ROOT dentry for the root of a filesystem. * * We must ensure that directory inodes only ever have one dentry. If a * dentry is found, that is returned instead of allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is * released. A %NULL or IS_ERR inode may be passed in and will be the * error will be propagate to the return value, with a %NULL @inode * replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_root(struct inode *inode) { return __d_obtain_alias(inode, false); } EXPORT_SYMBOL(d_obtain_root); /** * d_add_ci - lookup or allocate new dentry with case-exact name * @inode: the inode case-insensitive lookup has found * @dentry: the negative dentry that was passed to the parent's lookup func * @name: the case-exact name to be associated with the returned dentry * * This is to avoid filling the dcache with case-insensitive names to the * same inode, only the actual correct case is stored in the dcache for * case-insensitive filesystems. * * For a case-insensitive lookup match and if the the case-exact dentry * already exists in in the dcache, use it and return it. * * If no entry exists with the exact case name, allocate new dentry with * the exact case, and return the spliced entry. */ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, struct qstr *name) { struct dentry *found, *res; /* * First check if a dentry matching the name already exists, * if not go ahead and create it now. */ found = d_hash_and_lookup(dentry->d_parent, name); if (found) { iput(inode); return found; } if (d_in_lookup(dentry)) { found = d_alloc_parallel(dentry->d_parent, name, dentry->d_wait); if (IS_ERR(found) || !d_in_lookup(found)) { iput(inode); return found; } } else { found = d_alloc(dentry->d_parent, name); if (!found) { iput(inode); return ERR_PTR(-ENOMEM); } } res = d_splice_alias(inode, found); if (res) { dput(found); return res; } return found; } EXPORT_SYMBOL(d_add_ci); static inline bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name) { if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) { if (dentry->d_name.len != name->len) return false; return dentry_cmp(dentry, name->name, name->len) == 0; } return parent->d_op->d_compare(dentry, dentry->d_name.len, dentry->d_name.name, name) == 0; } /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry * @name: qstr of name we wish to find * @seqp: returns d_seq value at the point where the dentry was found * Returns: dentry, or NULL * * __d_lookup_rcu is the dcache lookup function for rcu-walk name * resolution (store-free path walking) design described in * Documentation/filesystems/path-lookup.txt. * * This is not to be used outside core vfs. * * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock * held, and rcu_read_lock held. The returned dentry must not be stored into * without taking d_lock and checking d_seq sequence count against @seq * returned here. * * A refcount may be taken on the found dentry with the d_rcu_to_refcount * function. * * Alternatively, __d_lookup_rcu may be called again to look up the child of * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks * is formed, giving integrity down the path walk. * * NOTE! The caller *has* to check the resulting dentry against the sequence * number we've returned before using any of the resulting dentry state! */ struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; const unsigned char *str = name->name; struct hlist_bl_head *b = d_hash(hashlen_hash(hashlen)); struct hlist_bl_node *node; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Carefully use d_seq when comparing a candidate dentry, to avoid * races with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; seqretry: /* * The dentry sequence count protects us from concurrent * renames, and thus protects parent and name fields. * * The caller must perform a seqcount check in order * to do anything useful with the returned dentry. * * NOTE! We do a "raw" seqcount_begin here. That means that * we don't wait for the sequence count to stabilize if it * is in the middle of a sequence change. If we do the slow * dentry compare, we will do seqretries until it is stable, * and if we end up with a successful lookup, we actually * want to exit RCU lookup anyway. * * Note that raw_seqcount_begin still *does* smp_rmb(), so * we are still guaranteed NUL-termination of ->d_name.name. */ seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) { int tlen; const char *tname; if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; tlen = dentry->d_name.len; tname = dentry->d_name.name; /* we want a consistent (name,len) pair */ if (read_seqcount_retry(&dentry->d_seq, seq)) { cpu_relax(); goto seqretry; } if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0) continue; } else { if (dentry->d_name.hash_len != hashlen) continue; if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) continue; } *seqp = seq; return dentry; } return NULL; } /** * d_lookup - search for a dentry * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * d_lookup searches the children of the parent dentry for the name in * question. If the dentry is found its reference count is incremented and the * dentry is returned. The caller must use dput to free the entry when it has * finished using it. %NULL is returned if the dentry does not exist. */ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name) { struct dentry *dentry; unsigned seq; do { seq = read_seqbegin(&rename_lock); dentry = __d_lookup(parent, name); if (dentry) break; } while (read_seqretry(&rename_lock, seq)); return dentry; } EXPORT_SYMBOL(d_lookup); /** * __d_lookup - search for a dentry (racy) * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * __d_lookup is like d_lookup, however it may (rarely) return a * false-negative result due to unrelated rename activity. * * __d_lookup is slightly faster by avoiding rename_lock read seqlock, * however it must be used carefully, eg. with a following d_lookup in * the case of failure. * * __d_lookup callers must be commented. */ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) { unsigned int hash = name->hash; struct hlist_bl_head *b = d_hash(hash); struct hlist_bl_node *node; struct dentry *found = NULL; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Take d_lock when comparing a candidate dentry, to avoid races * with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { if (dentry->d_name.hash != hash) continue; spin_lock(&dentry->d_lock); if (dentry->d_parent != parent) goto next; if (d_unhashed(dentry)) goto next; if (!d_same_name(dentry, parent, name)) goto next; dentry->d_lockref.count++; found = dentry; spin_unlock(&dentry->d_lock); break; next: spin_unlock(&dentry->d_lock); } rcu_read_unlock(); return found; } /** * d_hash_and_lookup - hash the qstr then search for a dentry * @dir: Directory to search in * @name: qstr of name we wish to find * * On lookup failure NULL is returned; on bad name - ERR_PTR(-error) */ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) { /* * Check for a fs-specific hash function. Note that we must * calculate the standard hash first, as the d_op->d_hash() * routine may choose to leave the hash value unchanged. */ name->hash = full_name_hash(dir, name->name, name->len); if (dir->d_flags & DCACHE_OP_HASH) { int err = dir->d_op->d_hash(dir, name); if (unlikely(err < 0)) return ERR_PTR(err); } return d_lookup(dir, name); } EXPORT_SYMBOL(d_hash_and_lookup); /* * When a file is deleted, we have two options: * - turn this dentry into a negative dentry * - unhash this dentry and free it. * * Usually, we want to just turn this into * a negative dentry, but if anybody else is * currently using the dentry or the inode * we can't do that and we fall back on removing * it from the hash queues and waiting for * it to be deleted later when it has no users */ /** * d_delete - delete a dentry * @dentry: The dentry to delete * * Turn the dentry into a negative dentry if possible, otherwise * remove it from the hash queues so it can be deleted later */ void d_delete(struct dentry * dentry) { struct inode *inode = dentry->d_inode; spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); /* * Are we the only user? */ if (dentry->d_lockref.count == 1) { dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_delete); static void __d_rehash(struct dentry *entry) { struct hlist_bl_head *b = d_hash(entry->d_name.hash); hlist_bl_lock(b); hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } /** * d_rehash - add an entry back to the hash * @entry: dentry to add to the hash * * Adds a dentry to the hash according to its name. */ void d_rehash(struct dentry * entry) { spin_lock(&entry->d_lock); __d_rehash(entry); spin_unlock(&entry->d_lock); } EXPORT_SYMBOL(d_rehash); static inline unsigned start_dir_add(struct inode *dir) { for (;;) { unsigned n = dir->i_dir_seq; if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) return n; cpu_relax(); } } static inline void end_dir_add(struct inode *dir, unsigned n) { smp_store_release(&dir->i_dir_seq, n + 2); } static void d_wait_lookup(struct dentry *dentry) { if (d_in_lookup(dentry)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(dentry->d_wait, &wait); do { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&dentry->d_lock); schedule(); spin_lock(&dentry->d_lock); } while (d_in_lookup(dentry)); } } struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, wait_queue_head_t *wq) { unsigned int hash = name->hash; struct hlist_bl_head *b = in_lookup_hash(parent, hash); struct hlist_bl_node *node; struct dentry *new = d_alloc(parent, name); struct dentry *dentry; unsigned seq, r_seq, d_seq; if (unlikely(!new)) return ERR_PTR(-ENOMEM); retry: rcu_read_lock(); seq = smp_load_acquire(&parent->d_inode->i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } if (read_seqcount_retry(&dentry->d_seq, d_seq)) { rcu_read_unlock(); dput(dentry); goto retry; } rcu_read_unlock(); dput(new); return dentry; } if (unlikely(read_seqretry(&rename_lock, r_seq))) { rcu_read_unlock(); goto retry; } if (unlikely(seq & 1)) { rcu_read_unlock(); goto retry; } hlist_bl_lock(b); if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; } /* * No changes for the parent since the beginning of d_lookup(). * Since all removals from the chain happen with hlist_bl_lock(), * any potential in-lookup matches are going to stay here until * we unlock the chain. All fields are stable in everything * we encounter. */ hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) { if (dentry->d_name.hash != hash) continue; if (dentry->d_parent != parent) continue; if (!d_same_name(dentry, parent, name)) continue; hlist_bl_unlock(b); /* now we can try to grab a reference */ if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } rcu_read_unlock(); /* * somebody is likely to be still doing lookup for it; * wait for them to finish */ spin_lock(&dentry->d_lock); d_wait_lookup(dentry); /* * it's not in-lookup anymore; in principle we should repeat * everything from dcache lookup, but it's likely to be what * d_lookup() would've found anyway. If it is, just return it; * otherwise we really have to repeat the whole thing. */ if (unlikely(dentry->d_name.hash != hash)) goto mismatch; if (unlikely(dentry->d_parent != parent)) goto mismatch; if (unlikely(d_unhashed(dentry))) goto mismatch; if (unlikely(!d_same_name(dentry, parent, name))) goto mismatch; /* OK, it *is* a hashed match; return it */ spin_unlock(&dentry->d_lock); dput(new); return dentry; } rcu_read_unlock(); /* we can't take ->d_lock here; it's OK, though. */ new->d_flags |= DCACHE_PAR_LOOKUP; new->d_wait = wq; hlist_bl_add_head_rcu(&new->d_u.d_in_lookup_hash, b); hlist_bl_unlock(b); return new; mismatch: spin_unlock(&dentry->d_lock); dput(dentry); goto retry; } EXPORT_SYMBOL(d_alloc_parallel); void __d_lookup_done(struct dentry *dentry) { struct hlist_bl_head *b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash); hlist_bl_lock(b); dentry->d_flags &= ~DCACHE_PAR_LOOKUP; __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); wake_up_all(dentry->d_wait); dentry->d_wait = NULL; hlist_bl_unlock(b); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_lru); } EXPORT_SYMBOL(__d_lookup_done); /* inode->i_lock held if inode is non-NULL */ static inline void __d_add(struct dentry *dentry, struct inode *inode) { struct inode *dir = NULL; unsigned n; spin_lock(&dentry->d_lock); if (unlikely(d_in_lookup(dentry))) { dir = dentry->d_parent->d_inode; n = start_dir_add(dir); __d_lookup_done(dentry); } if (inode) { unsigned add_flags = d_flags_for_inode(inode); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); } __d_rehash(dentry); if (dir) end_dir_add(dir, n); spin_unlock(&dentry->d_lock); if (inode) spin_unlock(&inode->i_lock); } /** * d_add - add dentry to hash queues * @entry: dentry to add * @inode: The inode to attach to this dentry * * This adds the entry to the hash queues and initializes @inode. * The entry was actually filled in earlier during d_alloc(). */ void d_add(struct dentry *entry, struct inode *inode) { if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); } __d_add(entry, inode); } EXPORT_SYMBOL(d_add); /** * d_exact_alias - find and hash an exact unhashed alias * @entry: dentry to add * @inode: The inode to go with this dentry * * If an unhashed dentry with the same name/parent and desired * inode already exists, hash and return it. Otherwise, return * NULL. * * Parent directory should be locked. */ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) { struct dentry *alias; unsigned int hash = entry->d_name.hash; spin_lock(&inode->i_lock); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or * parent changes, because the parent inode i_mutex is held. */ if (alias->d_name.hash != hash) continue; if (alias->d_parent != entry->d_parent) continue; if (!d_same_name(alias, entry->d_parent, &entry->d_name)) continue; spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { spin_unlock(&alias->d_lock); alias = NULL; } else { __dget_dlock(alias); __d_rehash(alias); spin_unlock(&alias->d_lock); } spin_unlock(&inode->i_lock); return alias; } spin_unlock(&inode->i_lock); return NULL; } EXPORT_SYMBOL(d_exact_alias); static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { if (unlikely(dname_external(dentry))) { /* * Both external: swap the pointers */ swap(target->d_name.name, dentry->d_name.name); } else { /* * dentry:internal, target:external. Steal target's * storage and make target internal. */ memcpy(target->d_iname, dentry->d_name.name, dentry->d_name.len + 1); dentry->d_name.name = target->d_name.name; target->d_name.name = target->d_iname; } } else { if (unlikely(dname_external(dentry))) { /* * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ memcpy(dentry->d_iname, target->d_name.name, target->d_name.len + 1); target->d_name.name = dentry->d_name.name; dentry->d_name.name = dentry->d_iname; } else { /* * Both are internal. */ unsigned int i; BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long))); for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) { swap(((long *) &dentry->d_iname)[i], ((long *) &target->d_iname)[i]); } } } swap(dentry->d_name.hash_len, target->d_name.hash_len); } static void copy_name(struct dentry *dentry, struct dentry *target) { struct external_name *old_name = NULL; if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { atomic_inc(&external_name(target)->u.count); dentry->d_name = target->d_name; } else { memcpy(dentry->d_iname, target->d_name.name, target->d_name.len + 1); dentry->d_name.name = dentry->d_iname; dentry->d_name.hash_len = target->d_name.hash_len; } if (old_name && likely(atomic_dec_and_test(&old_name->u.count))) kfree_rcu(old_name, u.head); } /* * __d_move - move a dentry * @dentry: entry to move * @target: new dentry * @exchange: exchange the two dentries * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. Caller must hold * rename_lock, the i_mutex of the source and target directories, * and the sb->s_vfs_rename_mutex if they differ. See lock_rename(). */ static void __d_move(struct dentry *dentry, struct dentry *target, bool exchange) { struct dentry *old_parent, *p; struct inode *dir = NULL; unsigned n; WARN_ON(!dentry->d_inode); if (WARN_ON(dentry == target)) return; BUG_ON(d_ancestor(target, dentry)); old_parent = dentry->d_parent; p = d_ancestor(old_parent, target); if (IS_ROOT(dentry)) { BUG_ON(p); spin_lock(&target->d_parent->d_lock); } else if (!p) { /* target is not a descendent of dentry->d_parent */ spin_lock(&target->d_parent->d_lock); spin_lock_nested(&old_parent->d_lock, DENTRY_D_LOCK_NESTED); } else { BUG_ON(p == dentry); spin_lock(&old_parent->d_lock); if (p != target) spin_lock_nested(&target->d_parent->d_lock, DENTRY_D_LOCK_NESTED); } spin_lock_nested(&dentry->d_lock, 2); spin_lock_nested(&target->d_lock, 3); if (unlikely(d_in_lookup(target))) { dir = target->d_parent->d_inode; n = start_dir_add(dir); __d_lookup_done(target); } write_seqcount_begin(&dentry->d_seq); write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED); /* unhash both */ if (!d_unhashed(dentry)) ___d_drop(dentry); if (!d_unhashed(target)) ___d_drop(target); /* ... and switch them in the tree */ dentry->d_parent = target->d_parent; if (!exchange) { copy_name(dentry, target); target->d_hash.pprev = NULL; dentry->d_parent->d_lockref.count++; if (dentry != old_parent) /* wasn't IS_ROOT */ WARN_ON(!--old_parent->d_lockref.count); } else { target->d_parent = old_parent; swap_names(dentry, target); list_move(&target->d_child, &target->d_parent->d_subdirs); __d_rehash(target); fsnotify_update_flags(target); } list_move(&dentry->d_child, &dentry->d_parent->d_subdirs); __d_rehash(dentry); fsnotify_update_flags(dentry); fscrypt_handle_d_move(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); if (dir) end_dir_add(dir, n); if (dentry->d_parent != old_parent) spin_unlock(&dentry->d_parent->d_lock); if (dentry != old_parent) spin_unlock(&old_parent->d_lock); spin_unlock(&target->d_lock); spin_unlock(&dentry->d_lock); } /* * d_move - move a dentry * @dentry: entry to move * @target: new dentry * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. See the locking * requirements for __d_move. */ void d_move(struct dentry *dentry, struct dentry *target) { write_seqlock(&rename_lock); __d_move(dentry, target, false); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_move); /* * d_exchange - exchange two dentries * @dentry1: first dentry * @dentry2: second dentry */ void d_exchange(struct dentry *dentry1, struct dentry *dentry2) { write_seqlock(&rename_lock); WARN_ON(!dentry1->d_inode); WARN_ON(!dentry2->d_inode); WARN_ON(IS_ROOT(dentry1)); WARN_ON(IS_ROOT(dentry2)); __d_move(dentry1, dentry2, true); write_sequnlock(&rename_lock); } /** * d_ancestor - search for an ancestor * @p1: ancestor dentry * @p2: child dentry * * Returns the ancestor dentry of p2 which is a child of p1, if p1 is * an ancestor of p2, else NULL. */ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) { struct dentry *p; for (p = p2; !IS_ROOT(p); p = p->d_parent) { if (p->d_parent == p1) return p; } return NULL; } /* * This helper attempts to cope with remotely renamed directories * * It assumes that the caller is already holding * dentry->d_parent->d_inode->i_mutex, and rename_lock * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... */ static int __d_unalias(struct inode *inode, struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL; struct rw_semaphore *m2 = NULL; int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) goto out_unalias; /* See lock_rename() */ if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; if (!inode_trylock_shared(alias->d_parent->d_inode)) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: __d_move(alias, dentry, false); ret = 0; out_err: if (m2) up_read(m2); if (m1) mutex_unlock(m1); return ret; } /** * d_splice_alias - splice a disconnected dentry into the tree if one exists * @inode: the inode which may have a disconnected dentry * @dentry: a negative dentry which we want to point to the inode. * * If inode is a directory and has an IS_ROOT alias, then d_move that in * place of the given dentry and return it, else simply d_add the inode * to the dentry and return NULL. * * If a non-IS_ROOT directory is found, the filesystem is corrupt, and * we should error out: directories can't have multiple aliases. * * This is needed in the lookup routine of any filesystem that is exportable * (via knfsd) so that we can build dcache paths to directories effectively. * * If a dentry was found and moved, then it is returned. Otherwise NULL * is returned. This matches the expected return value of ->lookup. * * Cluster filesystems may call this function with a negative, hashed dentry. * In that case, we know that the inode will be a regular file, and also this * will only occur during atomic_open. So we need to check for the dentry * being already hashed only in the final case. */ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) { if (IS_ERR(inode)) return ERR_CAST(inode); BUG_ON(!d_unhashed(dentry)); if (!inode) goto out; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); if (unlikely(new)) { /* The reference to new ensures it remains an alias */ spin_unlock(&inode->i_lock); write_seqlock(&rename_lock); if (unlikely(d_ancestor(new, dentry))) { write_sequnlock(&rename_lock); dput(new); new = ERR_PTR(-ELOOP); pr_warn_ratelimited( "VFS: Lookup of '%s' in %s %s" " would have caused loop\n", dentry->d_name.name, inode->i_sb->s_type->name, inode->i_sb->s_id); } else if (!IS_ROOT(new)) { struct dentry *old_parent = dget(new->d_parent); int err = __d_unalias(inode, dentry, new); write_sequnlock(&rename_lock); if (err) { dput(new); new = ERR_PTR(err); } dput(old_parent); } else { __d_move(new, dentry, false); write_sequnlock(&rename_lock); } iput(inode); return new; } } out: __d_add(dentry, inode); return NULL; } EXPORT_SYMBOL(d_splice_alias); /* * Test whether new_dentry is a subdirectory of old_dentry. * * Trivially implemented using the dcache structure */ /** * is_subdir - is new dentry a subdirectory of old_dentry * @new_dentry: new dentry * @old_dentry: old dentry * * Returns true if new_dentry is a subdirectory of the parent (at any depth). * Returns false otherwise. * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { bool subdir; unsigned seq; if (new_dentry == old_dentry) return true; /* Access d_parent under rcu as d_move() may change it. */ rcu_read_lock(); seq = read_seqbegin(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); /* Try lockless once... */ if (read_seqretry(&rename_lock, seq)) { /* ...else acquire lock for progress even on deep chains. */ read_seqlock_excl(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); read_sequnlock_excl(&rename_lock); } rcu_read_unlock(); return subdir; } EXPORT_SYMBOL(is_subdir); static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry) { struct dentry *root = data; if (dentry != root) { if (d_unhashed(dentry) || !dentry->d_inode) return D_WALK_SKIP; if (!(dentry->d_flags & DCACHE_GENOCIDE)) { dentry->d_flags |= DCACHE_GENOCIDE; dentry->d_lockref.count--; } } return D_WALK_CONTINUE; } void d_genocide(struct dentry *parent) { d_walk(parent, parent, d_genocide_kill); } EXPORT_SYMBOL(d_genocide); void d_tmpfile(struct dentry *dentry, struct inode *inode) { inode_dec_link_count(inode); BUG_ON(dentry->d_name.name != dentry->d_iname || !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry->d_name.len = sprintf(dentry->d_iname, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); d_instantiate(dentry, inode); } EXPORT_SYMBOL(d_tmpfile); static __initdata unsigned long dhash_entries; static int __init set_dhash_entries(char *str) { if (!str) return 0; dhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_EARLY | HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; } static void __init dcache_init(void) { /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature * of the dcache. */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT, d_iname); /* Hash may have been set up in dcache_init_early */ if (!hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; } /* SLAB cache for __getname() consumers */ struct kmem_cache *names_cachep __read_mostly; EXPORT_SYMBOL(names_cachep); void __init vfs_caches_init_early(void) { int i; for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++) INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]); dcache_init_early(); inode_init_early(); } void __init vfs_caches_init(void) { names_cachep = kmem_cache_create_usercopy("names_cache", PATH_MAX, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, 0, PATH_MAX, NULL); dcache_init(); inode_init(); files_init(); files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* audit.h -- Auditing support * * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> */ #ifndef _LINUX_AUDIT_H_ #define _LINUX_AUDIT_H_ #include <linux/sched.h> #include <linux/ptrace.h> #include <uapi/linux/audit.h> #include <uapi/linux/netfilter/nf_tables.h> #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) struct audit_sig_info { uid_t uid; pid_t pid; char ctx[]; }; struct audit_buffer; struct audit_context; struct inode; struct netlink_skb_parms; struct path; struct linux_binprm; struct mq_attr; struct mqstat; struct audit_watch; struct audit_tree; struct sk_buff; struct audit_krule { u32 pflags; u32 flags; u32 listnr; u32 action; u32 mask[AUDIT_BITMASK_SIZE]; u32 buflen; /* for data alloc on list rules */ u32 field_count; char *filterkey; /* ties events to rules */ struct audit_field *fields; struct audit_field *arch_f; /* quick access to arch field */ struct audit_field *inode_f; /* quick access to an inode field */ struct audit_watch *watch; /* associated watch */ struct audit_tree *tree; /* associated watched tree */ struct audit_fsnotify_mark *exe; struct list_head rlist; /* entry in audit_{watch,tree}.rules list */ struct list_head list; /* for AUDIT_LIST* purposes only */ u64 prio; }; /* Flag to indicate legacy AUDIT_LOGINUID unset usage */ #define AUDIT_LOGINUID_LEGACY 0x1 struct audit_field { u32 type; union { u32 val; kuid_t uid; kgid_t gid; struct { char *lsm_str; void *lsm_rule; }; }; u32 op; }; enum audit_ntp_type { AUDIT_NTP_OFFSET, AUDIT_NTP_FREQ, AUDIT_NTP_STATUS, AUDIT_NTP_TAI, AUDIT_NTP_TICK, AUDIT_NTP_ADJUST, AUDIT_NTP_NVALS /* count */ }; #ifdef CONFIG_AUDITSYSCALL struct audit_ntp_val { long long oldval, newval; }; struct audit_ntp_data { struct audit_ntp_val vals[AUDIT_NTP_NVALS]; }; #else struct audit_ntp_data {}; #endif enum audit_nfcfgop { AUDIT_XT_OP_REGISTER, AUDIT_XT_OP_REPLACE, AUDIT_XT_OP_UNREGISTER, AUDIT_NFT_OP_TABLE_REGISTER, AUDIT_NFT_OP_TABLE_UNREGISTER, AUDIT_NFT_OP_CHAIN_REGISTER, AUDIT_NFT_OP_CHAIN_UNREGISTER, AUDIT_NFT_OP_RULE_REGISTER, AUDIT_NFT_OP_RULE_UNREGISTER, AUDIT_NFT_OP_SET_REGISTER, AUDIT_NFT_OP_SET_UNREGISTER, AUDIT_NFT_OP_SETELEM_REGISTER, AUDIT_NFT_OP_SETELEM_UNREGISTER, AUDIT_NFT_OP_GEN_REGISTER, AUDIT_NFT_OP_OBJ_REGISTER, AUDIT_NFT_OP_OBJ_UNREGISTER, AUDIT_NFT_OP_OBJ_RESET, AUDIT_NFT_OP_FLOWTABLE_REGISTER, AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, AUDIT_NFT_OP_INVALID, }; extern int is_audit_feature_set(int which); extern int __init audit_register_class(int class, unsigned *list); extern int audit_classify_syscall(int abi, unsigned syscall); extern int audit_classify_arch(int arch); /* only for compat system calls */ extern unsigned compat_write_class[]; extern unsigned compat_read_class[]; extern unsigned compat_dir_class[]; extern unsigned compat_chattr_class[]; extern unsigned compat_signal_class[]; extern int audit_classify_compat_syscall(int abi, unsigned syscall); /* audit_names->type values */ #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ #define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ #define AUDIT_TYPE_PARENT 2 /* a parent audit record */ #define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ /* maximized args number that audit_socketcall can process */ #define AUDITSC_ARGS 6 /* bit values for ->signal->audit_tty */ #define AUDIT_TTY_ENABLE BIT(0) #define AUDIT_TTY_LOG_PASSWD BIT(1) struct filename; #define AUDIT_OFF 0 #define AUDIT_ON 1 #define AUDIT_LOCKED 2 #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ extern __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...); extern struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type); extern __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...); extern void audit_log_end(struct audit_buffer *ab); extern bool audit_string_contains_control(const char *string, size_t len); extern void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len); extern void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n); extern void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n); extern void audit_log_untrustedstring(struct audit_buffer *ab, const char *string); extern void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path); extern void audit_log_key(struct audit_buffer *ab, char *key); extern void audit_log_path_denied(int type, const char *operation); extern void audit_log_lost(const char *message); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ extern int audit_rule_change(int type, int seq, void *data, size_t datasz); extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); extern int audit_set_loginuid(kuid_t loginuid); static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return tsk->loginuid; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return tsk->sessionid; } extern u32 audit_enabled; extern int audit_signal_info(int sig, struct task_struct *t); #else /* CONFIG_AUDIT */ static inline __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { } static inline struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { return NULL; } static inline __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { } static inline void audit_log_end(struct audit_buffer *ab) { } static inline void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { } static inline void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n) { } static inline void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n) { } static inline void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { } static inline void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { } static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_path_denied(int type, const char *operation) { } static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; } static inline void audit_log_task_info(struct audit_buffer *ab) { } static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return INVALID_UID; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return AUDIT_SID_UNSET; } #define audit_enabled AUDIT_OFF static inline int audit_signal_info(int sig, struct task_struct *t) { return 0; } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC #define audit_is_compat(arch) (!((arch) & __AUDIT_ARCH_64BIT)) #else #define audit_is_compat(arch) false #endif #define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ #define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ #define AUDIT_INODE_NOEVAL 4 /* audit record incomplete */ #ifdef CONFIG_AUDITSYSCALL #include <asm/syscall.h> /* for syscall_get_arch() */ /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); extern void __audit_free(struct task_struct *task); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); extern struct filename *__audit_reusename(const __user char *uptr); extern void __audit_getname(struct filename *name); extern void __audit_getcwd(void); extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); extern void __audit_file(const struct file *); extern void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type); extern void audit_seccomp(unsigned long syscall, long signr, int code); extern void audit_seccomp_actions_logged(const char *names, const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { task->audit_context = ctx; } static inline struct audit_context *audit_context(void) { return current->audit_context; } static inline bool audit_dummy_context(void) { void *p = audit_context(); return !p || *(int *)p; } static inline void audit_free(struct task_struct *task) { if (unlikely(task->audit_context)) __audit_free(task); } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { if (unlikely(audit_context())) __audit_syscall_entry(major, a0, a1, a2, a3); } static inline void audit_syscall_exit(void *pt_regs) { if (unlikely(audit_context())) { int success = is_syscall_success(pt_regs); long return_code = regs_return_value(pt_regs); __audit_syscall_exit(success, return_code); } } static inline struct filename *audit_reusename(const __user char *name) { if (unlikely(!audit_dummy_context())) return __audit_reusename(name); return NULL; } static inline void audit_getname(struct filename *name) { if (unlikely(!audit_dummy_context())) __audit_getname(name); } static inline void audit_getcwd(void) { if (unlikely(audit_context())) __audit_getcwd(); } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, aflags); } static inline void audit_file(struct file *file) { if (unlikely(!audit_dummy_context())) __audit_file(file); } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, AUDIT_INODE_PARENT | AUDIT_INODE_HIDDEN); } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { if (unlikely(!audit_dummy_context())) __audit_inode_child(parent, dentry, type); } void audit_core_dumps(long signr); static inline void audit_ptrace(struct task_struct *t) { if (unlikely(!audit_dummy_context())) __audit_ptrace(t); } /* Private API (for audit.c only) */ extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern void __audit_bprm(struct linux_binprm *bprm); extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_log_kern_module(char *name); extern void __audit_fanotify(unsigned int response); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { if (unlikely(!audit_dummy_context())) __audit_ipc_obj(ipcp); } static inline void audit_fd_pair(int fd1, int fd2) { if (unlikely(!audit_dummy_context())) __audit_fd_pair(fd1, fd2); } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { if (unlikely(!audit_dummy_context())) __audit_ipc_set_perm(qbytes, uid, gid, mode); } static inline void audit_bprm(struct linux_binprm *bprm) { if (unlikely(!audit_dummy_context())) __audit_bprm(bprm); } static inline int audit_socketcall(int nargs, unsigned long *args) { if (unlikely(!audit_dummy_context())) return __audit_socketcall(nargs, args); return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { unsigned long a[AUDITSC_ARGS]; int i; if (audit_dummy_context()) return 0; for (i = 0; i < nargs; i++) a[i] = (unsigned long)args[i]; return __audit_socketcall(nargs, a); } static inline int audit_sockaddr(int len, void *addr) { if (unlikely(!audit_dummy_context())) return __audit_sockaddr(len, addr); return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { if (unlikely(!audit_dummy_context())) __audit_mq_open(oflag, mode, attr); } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { if (unlikely(!audit_dummy_context())) __audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout); } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { if (unlikely(!audit_dummy_context())) __audit_mq_notify(mqdes, notification); } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { if (unlikely(!audit_dummy_context())) __audit_mq_getsetattr(mqdes, mqstat); } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) return __audit_log_bprm_fcaps(bprm, new, old); return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) __audit_log_capset(new, old); } static inline void audit_mmap_fd(int fd, int flags) { if (unlikely(!audit_dummy_context())) __audit_mmap_fd(fd, flags); } static inline void audit_log_kern_module(char *name) { if (!audit_dummy_context()) __audit_log_kern_module(name); } static inline void audit_fanotify(unsigned int response) { if (!audit_dummy_context()) __audit_fanotify(response); } static inline void audit_tk_injoffset(struct timespec64 offset) { /* ignore no-op events */ if (offset.tv_sec == 0 && offset.tv_nsec == 0) return; if (!audit_dummy_context()) __audit_tk_injoffset(offset); } static inline void audit_ntp_init(struct audit_ntp_data *ad) { memset(ad, 0, sizeof(*ad)); } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].oldval = val; } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].newval = val; } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { if (!audit_dummy_context()) __audit_ntp_log(ad); } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { if (audit_enabled) __audit_log_nfcfg(name, af, nentries, op, gfp); } extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ static inline int audit_alloc(struct task_struct *task) { return 0; } static inline void audit_free(struct task_struct *task) { } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { } static inline void audit_syscall_exit(void *pt_regs) { } static inline bool audit_dummy_context(void) { return true; } static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { } static inline struct audit_context *audit_context(void) { return NULL; } static inline struct filename *audit_reusename(const __user char *name) { return NULL; } static inline void audit_getname(struct filename *name) { } static inline void audit_getcwd(void) { } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { } static inline void audit_file(struct file *file) { } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { } static inline void audit_core_dumps(long signr) { } static inline void audit_seccomp(unsigned long syscall, long signr, int code) { } static inline void audit_seccomp_actions_logged(const char *names, const char *old_names, int res) { } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { } static inline void audit_bprm(struct linux_binprm *bprm) { } static inline int audit_socketcall(int nargs, unsigned long *args) { return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { return 0; } static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) { return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { } static inline void audit_mmap_fd(int fd, int flags) { } static inline void audit_log_kern_module(char *name) { } static inline void audit_fanotify(unsigned int response) { } static inline void audit_tk_injoffset(struct timespec64 offset) { } static inline void audit_ntp_init(struct audit_ntp_data *ad) { } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { } static inline void audit_ptrace(struct task_struct *t) { } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { } #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ static inline bool audit_loginuid_set(struct task_struct *tsk) { return uid_valid(audit_get_loginuid(tsk)); } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef IOPRIO_H #define IOPRIO_H #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/iocontext.h> /* * Gives us 8 prio classes with 13-bits of data for each class */ #define IOPRIO_CLASS_SHIFT (13) #define IOPRIO_PRIO_MASK ((1UL << IOPRIO_CLASS_SHIFT) - 1) #define IOPRIO_PRIO_CLASS(mask) ((mask) >> IOPRIO_CLASS_SHIFT) #define IOPRIO_PRIO_DATA(mask) ((mask) & IOPRIO_PRIO_MASK) #define IOPRIO_PRIO_VALUE(class, data) (((class) << IOPRIO_CLASS_SHIFT) | data) #define ioprio_valid(mask) (IOPRIO_PRIO_CLASS((mask)) != IOPRIO_CLASS_NONE) /* * These are the io priority groups as implemented by CFQ. RT is the realtime * class, it always gets premium service. BE is the best-effort scheduling * class, the default for any process. IDLE is the idle scheduling class, it * is only served when no one else is using the disk. */ enum { IOPRIO_CLASS_NONE, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE, }; /* * 8 best effort priority levels are supported */ #define IOPRIO_BE_NR (8) enum { IOPRIO_WHO_PROCESS = 1, IOPRIO_WHO_PGRP, IOPRIO_WHO_USER, }; /* * Fallback BE priority */ #define IOPRIO_NORM (4) /* * if process has set io priority explicitly, use that. if not, convert * the cpu scheduler nice value to an io priority */ static inline int task_nice_ioprio(struct task_struct *task) { return (task_nice(task) + 20) / 5; } /* * This is for the case where the task hasn't asked for a specific IO class. * Check for idle and rt task process, and return appropriate IO class. */ static inline int task_nice_ioclass(struct task_struct *task) { if (task->policy == SCHED_IDLE) return IOPRIO_CLASS_IDLE; else if (task_is_realtime(task)) return IOPRIO_CLASS_RT; else return IOPRIO_CLASS_BE; } /* * If the calling process has set an I/O priority, use that. Otherwise, return * the default I/O priority. */ static inline int get_current_ioprio(void) { struct io_context *ioc = current->io_context; if (ioc) return ioc->ioprio; return IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); } /* * For inheritance, return the highest of the two given priorities */ extern int ioprio_best(unsigned short aprio, unsigned short bprio); extern int set_task_ioprio(struct task_struct *task, int ioprio); #ifdef CONFIG_BLOCK extern int ioprio_check_cap(int ioprio); #else static inline int ioprio_check_cap(int ioprio) { return -ENOTBLK; } #endif /* CONFIG_BLOCK */ #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 | /* * memfd_create system call and file sealing support * * Code was originally included in shmem.c, and broken out to facilitate * use by hugetlbfs as well as tmpfs. * * This file is released under the GPL. */ #include <linux/fs.h> #include <linux/vfs.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/khugepaged.h> #include <linux/syscalls.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <linux/memfd.h> #include <uapi/linux/memfd.h> /* * We need a tag: a new tag would expand every xa_node by 8 bytes, * so reuse a tag which we firmly believe is never set or cleared on tmpfs * or hugetlbfs because they are memory only filesystems. */ #define MEMFD_TAG_PINNED PAGECACHE_TAG_TOWRITE #define LAST_SCAN 4 /* about 150ms max */ static void memfd_tag_pins(struct xa_state *xas) { struct page *page; int latency = 0; int cache_count; lru_add_drain(); xas_lock_irq(xas); xas_for_each(xas, page, ULONG_MAX) { cache_count = 1; if (!xa_is_value(page) && PageTransHuge(page) && !PageHuge(page)) cache_count = HPAGE_PMD_NR; if (!xa_is_value(page) && page_count(page) - total_mapcount(page) != cache_count) xas_set_mark(xas, MEMFD_TAG_PINNED); if (cache_count != 1) xas_set(xas, page->index + cache_count); latency += cache_count; if (latency < XA_CHECK_SCHED) continue; latency = 0; xas_pause(xas); xas_unlock_irq(xas); cond_resched(); xas_lock_irq(xas); } xas_unlock_irq(xas); } /* * Setting SEAL_WRITE requires us to verify there's no pending writer. However, * via get_user_pages(), drivers might have some pending I/O without any active * user-space mappings (eg., direct-IO, AIO). Therefore, we look at all pages * and see whether it has an elevated ref-count. If so, we tag them and wait for * them to be dropped. * The caller must guarantee that no new user will acquire writable references * to those pages to avoid races. */ static int memfd_wait_for_pins(struct address_space *mapping) { XA_STATE(xas, &mapping->i_pages, 0); struct page *page; int error, scan; memfd_tag_pins(&xas); error = 0; for (scan = 0; scan <= LAST_SCAN; scan++) { int latency = 0; int cache_count; if (!xas_marked(&xas, MEMFD_TAG_PINNED)) break; if (!scan) lru_add_drain_all(); else if (schedule_timeout_killable((HZ << scan) / 200)) scan = LAST_SCAN; xas_set(&xas, 0); xas_lock_irq(&xas); xas_for_each_marked(&xas, page, ULONG_MAX, MEMFD_TAG_PINNED) { bool clear = true; cache_count = 1; if (!xa_is_value(page) && PageTransHuge(page) && !PageHuge(page)) cache_count = HPAGE_PMD_NR; if (!xa_is_value(page) && cache_count != page_count(page) - total_mapcount(page)) { /* * On the last scan, we clean up all those tags * we inserted; but make a note that we still * found pages pinned. */ if (scan == LAST_SCAN) error = -EBUSY; else clear = false; } if (clear) xas_clear_mark(&xas, MEMFD_TAG_PINNED); latency += cache_count; if (latency < XA_CHECK_SCHED) continue; latency = 0; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } return error; } unsigned int *memfd_file_seals_ptr(struct file *file) { if (shmem_file(file)) return &SHMEM_I(file_inode(file))->seals; #ifdef CONFIG_HUGETLBFS if (is_file_hugepages(file)) return &HUGETLBFS_I(file_inode(file))->seals; #endif return NULL; } #define F_ALL_SEALS (F_SEAL_SEAL | \ F_SEAL_SHRINK | \ F_SEAL_GROW | \ F_SEAL_WRITE | \ F_SEAL_FUTURE_WRITE) static int memfd_add_seals(struct file *file, unsigned int seals) { struct inode *inode = file_inode(file); unsigned int *file_seals; int error; /* * SEALING * Sealing allows multiple parties to share a tmpfs or hugetlbfs file * but restrict access to a specific subset of file operations. Seals * can only be added, but never removed. This way, mutually untrusted * parties can share common memory regions with a well-defined policy. * A malicious peer can thus never perform unwanted operations on a * shared object. * * Seals are only supported on special tmpfs or hugetlbfs files and * always affect the whole underlying inode. Once a seal is set, it * may prevent some kinds of access to the file. Currently, the * following seals are defined: * SEAL_SEAL: Prevent further seals from being set on this file * SEAL_SHRINK: Prevent the file from shrinking * SEAL_GROW: Prevent the file from growing * SEAL_WRITE: Prevent write access to the file * * As we don't require any trust relationship between two parties, we * must prevent seals from being removed. Therefore, sealing a file * only adds a given set of seals to the file, it never touches * existing seals. Furthermore, the "setting seals"-operation can be * sealed itself, which basically prevents any further seal from being * added. * * Semantics of sealing are only defined on volatile files. Only * anonymous tmpfs and hugetlbfs files support sealing. More * importantly, seals are never written to disk. Therefore, there's * no plan to support it on other file types. */ if (!(file->f_mode & FMODE_WRITE)) return -EPERM; if (seals & ~(unsigned int)F_ALL_SEALS) return -EINVAL; inode_lock(inode); file_seals = memfd_file_seals_ptr(file); if (!file_seals) { error = -EINVAL; goto unlock; } if (*file_seals & F_SEAL_SEAL) { error = -EPERM; goto unlock; } if ((seals & F_SEAL_WRITE) && !(*file_seals & F_SEAL_WRITE)) { error = mapping_deny_writable(file->f_mapping); if (error) goto unlock; error = memfd_wait_for_pins(file->f_mapping); if (error) { mapping_allow_writable(file->f_mapping); goto unlock; } } *file_seals |= seals; error = 0; unlock: inode_unlock(inode); return error; } static int memfd_get_seals(struct file *file) { unsigned int *seals = memfd_file_seals_ptr(file); return seals ? *seals : -EINVAL; } long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { long error; switch (cmd) { case F_ADD_SEALS: /* disallow upper 32bit */ if (arg > UINT_MAX) return -EINVAL; error = memfd_add_seals(file, arg); break; case F_GET_SEALS: error = memfd_get_seals(file); break; default: error = -EINVAL; break; } return error; } #define MFD_NAME_PREFIX "memfd:" #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1) #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN) #define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB) SYSCALL_DEFINE2(memfd_create, const char __user *, uname, unsigned int, flags) { unsigned int *file_seals; struct file *file; int fd, error; char *name; long len; if (!(flags & MFD_HUGETLB)) { if (flags & ~(unsigned int)MFD_ALL_FLAGS) return -EINVAL; } else { /* Allow huge page size encoding in flags. */ if (flags & ~(unsigned int)(MFD_ALL_FLAGS | (MFD_HUGE_MASK << MFD_HUGE_SHIFT))) return -EINVAL; } /* length includes terminating zero */ len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1); if (len <= 0) return -EFAULT; if (len > MFD_NAME_MAX_LEN + 1) return -EINVAL; name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_KERNEL); if (!name) return -ENOMEM; strcpy(name, MFD_NAME_PREFIX); if (copy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, len)) { error = -EFAULT; goto err_name; } /* terminating-zero may have changed after strnlen_user() returned */ if (name[len + MFD_NAME_PREFIX_LEN - 1]) { error = -EFAULT; goto err_name; } fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0); if (fd < 0) { error = fd; goto err_name; } if (flags & MFD_HUGETLB) { struct user_struct *user = NULL; file = hugetlb_file_setup(name, 0, VM_NORESERVE, &user, HUGETLB_ANONHUGE_INODE, (flags >> MFD_HUGE_SHIFT) & MFD_HUGE_MASK); } else file = shmem_file_setup(name, 0, VM_NORESERVE); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_fd; } file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; file->f_flags |= O_LARGEFILE; if (flags & MFD_ALLOW_SEALING) { file_seals = memfd_file_seals_ptr(file); if (file_seals) *file_seals &= ~F_SEAL_SEAL; } fd_install(fd, file); kfree(name); return fd; err_fd: put_unused_fd(fd); err_name: kfree(name); return error; } |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SEQLOCK_H #define __LINUX_SEQLOCK_H /* * seqcount_t / seqlock_t - a reader-writer consistency mechanism with * lockless readers (read-only retry loops), and no writer starvation. * * See Documentation/locking/seqlock.rst * * Copyrights: * - Based on x86_64 vsyscall gettimeofday: Keith Owens, Andrea Arcangeli * - Sequence counters with associated locks, (C) 2020 Linutronix GmbH */ #include <linux/compiler.h> #include <linux/kcsan-checks.h> #include <linux/lockdep.h> #include <linux/mutex.h> #include <linux/ww_mutex.h> #include <linux/preempt.h> #include <linux/spinlock.h> #include <asm/processor.h> /* * The seqlock seqcount_t interface does not prescribe a precise sequence of * read begin/retry/end. For readers, typically there is a call to * read_seqcount_begin() and read_seqcount_retry(), however, there are more * esoteric cases which do not follow this pattern. * * As a consequence, we take the following best-effort approach for raw usage * via seqcount_t under KCSAN: upon beginning a seq-reader critical section, * pessimistically mark the next KCSAN_SEQLOCK_REGION_MAX memory accesses as * atomics; if there is a matching read_seqcount_retry() call, no following * memory operations are considered atomic. Usage of the seqlock_t interface * is not affected. */ #define KCSAN_SEQLOCK_REGION_MAX 1000 /* * Sequence counters (seqcount_t) * * This is the raw counting mechanism, without any writer protection. * * Write side critical sections must be serialized and non-preemptible. * * If readers can be invoked from hardirq or softirq contexts, * interrupts or bottom halves must also be respectively disabled before * entering the write section. * * This mechanism can't be used if the protected data contains pointers, * as the writer can invalidate a pointer that a reader is following. * * If the write serialization mechanism is one of the common kernel * locking primitives, use a sequence counter with associated lock * (seqcount_LOCKNAME_t) instead. * * If it's desired to automatically handle the sequence counter writer * serialization and non-preemptibility requirements, use a sequential * lock (seqlock_t) instead. * * See Documentation/locking/seqlock.rst */ typedef struct seqcount { unsigned sequence; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif } seqcount_t; static inline void __seqcount_init(seqcount_t *s, const char *name, struct lock_class_key *key) { /* * Make sure we are not reinitializing a held lock: */ lockdep_init_map(&s->dep_map, name, key, 0); s->sequence = 0; } #ifdef CONFIG_DEBUG_LOCK_ALLOC # define SEQCOUNT_DEP_MAP_INIT(lockname) \ .dep_map = { .name = #lockname } /** * seqcount_init() - runtime initializer for seqcount_t * @s: Pointer to the seqcount_t instance */ # define seqcount_init(s) \ do { \ static struct lock_class_key __key; \ __seqcount_init((s), #s, &__key); \ } while (0) static inline void seqcount_lockdep_reader_access(const seqcount_t *s) { seqcount_t *l = (seqcount_t *)s; unsigned long flags; local_irq_save(flags); seqcount_acquire_read(&l->dep_map, 0, 0, _RET_IP_); seqcount_release(&l->dep_map, _RET_IP_); local_irq_restore(flags); } #else # define SEQCOUNT_DEP_MAP_INIT(lockname) # define seqcount_init(s) __seqcount_init(s, NULL, NULL) # define seqcount_lockdep_reader_access(x) #endif /** * SEQCNT_ZERO() - static initializer for seqcount_t * @name: Name of the seqcount_t instance */ #define SEQCNT_ZERO(name) { .sequence = 0, SEQCOUNT_DEP_MAP_INIT(name) } /* * Sequence counters with associated locks (seqcount_LOCKNAME_t) * * A sequence counter which associates the lock used for writer * serialization at initialization time. This enables lockdep to validate * that the write side critical section is properly serialized. * * For associated locks which do not implicitly disable preemption, * preemption protection is enforced in the write side function. * * Lockdep is never used in any for the raw write variants. * * See Documentation/locking/seqlock.rst */ /* * For PREEMPT_RT, seqcount_LOCKNAME_t write side critical sections cannot * disable preemption. It can lead to higher latencies, and the write side * sections will not be able to acquire locks which become sleeping locks * (e.g. spinlock_t). * * To remain preemptible while avoiding a possible livelock caused by the * reader preempting the writer, use a different technique: let the reader * detect if a seqcount_LOCKNAME_t writer is in progress. If that is the * case, acquire then release the associated LOCKNAME writer serialization * lock. This will allow any possibly-preempted writer to make progress * until the end of its writer serialization lock critical section. * * This lock-unlock technique must be implemented for all of PREEMPT_RT * sleeping locks. See Documentation/locking/locktypes.rst */ #if defined(CONFIG_LOCKDEP) || defined(CONFIG_PREEMPT_RT) #define __SEQ_LOCK(expr) expr #else #define __SEQ_LOCK(expr) #endif /* * typedef seqcount_LOCKNAME_t - sequence counter with LOCKNAME associated * @seqcount: The real sequence counter * @lock: Pointer to the associated lock * * A plain sequence counter with external writer synchronization by * LOCKNAME @lock. The lock is associated to the sequence counter in the * static initializer or init function. This enables lockdep to validate * that the write side critical section is properly serialized. * * LOCKNAME: raw_spinlock, spinlock, rwlock, mutex, or ww_mutex. */ /* * seqcount_LOCKNAME_init() - runtime initializer for seqcount_LOCKNAME_t * @s: Pointer to the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated lock */ #define seqcount_LOCKNAME_init(s, _lock, lockname) \ do { \ seqcount_##lockname##_t *____s = (s); \ seqcount_init(&____s->seqcount); \ __SEQ_LOCK(____s->lock = (_lock)); \ } while (0) #define seqcount_raw_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, raw_spinlock) #define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock) #define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock); #define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex); #define seqcount_ww_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, ww_mutex); /* * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers * seqprop_LOCKNAME_*() - Property accessors for seqcount_LOCKNAME_t * * @lockname: "LOCKNAME" part of seqcount_LOCKNAME_t * @locktype: LOCKNAME canonical C data type * @preemptible: preemptibility of above locktype * @lockmember: argument for lockdep_assert_held() * @lockbase: associated lock release function (prefix only) * @lock_acquire: associated lock acquisition function (full call) */ #define SEQCOUNT_LOCKNAME(lockname, locktype, preemptible, lockmember, lockbase, lock_acquire) \ typedef struct seqcount_##lockname { \ seqcount_t seqcount; \ __SEQ_LOCK(locktype *lock); \ } seqcount_##lockname##_t; \ \ static __always_inline seqcount_t * \ __seqprop_##lockname##_ptr(seqcount_##lockname##_t *s) \ { \ return &s->seqcount; \ } \ \ static __always_inline unsigned \ __seqprop_##lockname##_sequence(const seqcount_##lockname##_t *s) \ { \ unsigned seq = READ_ONCE(s->seqcount.sequence); \ \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return seq; \ \ if (preemptible && unlikely(seq & 1)) { \ __SEQ_LOCK(lock_acquire); \ __SEQ_LOCK(lockbase##_unlock(s->lock)); \ \ /* \ * Re-read the sequence counter since the (possibly \ * preempted) writer made progress. \ */ \ seq = READ_ONCE(s->seqcount.sequence); \ } \ \ return seq; \ } \ \ static __always_inline bool \ __seqprop_##lockname##_preemptible(const seqcount_##lockname##_t *s) \ { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ return preemptible; \ \ /* PREEMPT_RT relies on the above LOCK+UNLOCK */ \ return false; \ } \ \ static __always_inline void \ __seqprop_##lockname##_assert(const seqcount_##lockname##_t *s) \ { \ __SEQ_LOCK(lockdep_assert_held(lockmember)); \ } /* * __seqprop() for seqcount_t */ static inline seqcount_t *__seqprop_ptr(seqcount_t *s) { return s; } static inline unsigned __seqprop_sequence(const seqcount_t *s) { return READ_ONCE(s->sequence); } static inline bool __seqprop_preemptible(const seqcount_t *s) { return false; } static inline void __seqprop_assert(const seqcount_t *s) { lockdep_assert_preemption_disabled(); } #define __SEQ_RT IS_ENABLED(CONFIG_PREEMPT_RT) SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, s->lock, raw_spin, raw_spin_lock(s->lock)) SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, s->lock, spin, spin_lock(s->lock)) SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, s->lock, read, read_lock(s->lock)) SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock, mutex, mutex_lock(s->lock)) SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base, ww_mutex, ww_mutex_lock(s->lock, NULL)) /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t * @name: Name of the seqcount_LOCKNAME_t instance * @lock: Pointer to the associated LOCKNAME */ #define SEQCOUNT_LOCKNAME_ZERO(seq_name, assoc_lock) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ __SEQ_LOCK(.lock = (assoc_lock)) \ } #define SEQCNT_RAW_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_SPINLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_RWLOCK_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define SEQCNT_WW_MUTEX_ZERO(name, lock) SEQCOUNT_LOCKNAME_ZERO(name, lock) #define __seqprop_case(s, lockname, prop) \ seqcount_##lockname##_t: __seqprop_##lockname##_##prop((void *)(s)) #define __seqprop(s, prop) _Generic(*(s), \ seqcount_t: __seqprop_##prop((void *)(s)), \ __seqprop_case((s), raw_spinlock, prop), \ __seqprop_case((s), spinlock, prop), \ __seqprop_case((s), rwlock, prop), \ __seqprop_case((s), mutex, prop), \ __seqprop_case((s), ww_mutex, prop)) #define seqprop_ptr(s) __seqprop(s, ptr) #define seqprop_sequence(s) __seqprop(s, sequence) #define seqprop_preemptible(s) __seqprop(s, preemptible) #define seqprop_assert(s) __seqprop(s, assert) /** * __read_seqcount_begin() - begin a seqcount_t read section w/o barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * __read_seqcount_begin is like read_seqcount_begin, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is * provided before actually loading any of the variables that are to be * protected in this critical section. * * Use carefully, only in critical code, and comment how the barrier is * provided. * * Return: count to be passed to read_seqcount_retry() */ #define __read_seqcount_begin(s) \ ({ \ unsigned __seq; \ \ while ((__seq = seqprop_sequence(s)) & 1) \ cpu_relax(); \ \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** * raw_read_seqcount_begin() - begin a seqcount_t read section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount_begin(s) \ ({ \ unsigned _seq = __read_seqcount_begin(s); \ \ smp_rmb(); \ _seq; \ }) /** * read_seqcount_begin() - begin a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * Return: count to be passed to read_seqcount_retry() */ #define read_seqcount_begin(s) \ ({ \ seqcount_lockdep_reader_access(seqprop_ptr(s)); \ raw_read_seqcount_begin(s); \ }) /** * raw_read_seqcount() - read the raw seqcount_t counter value * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_read_seqcount opens a read critical section of the given * seqcount_t, without any lockdep checking, and without checking or * masking the sequence counter LSB. Calling code is responsible for * handling that. * * Return: count to be passed to read_seqcount_retry() */ #define raw_read_seqcount(s) \ ({ \ unsigned __seq = seqprop_sequence(s); \ \ smp_rmb(); \ kcsan_atomic_next(KCSAN_SEQLOCK_REGION_MAX); \ __seq; \ }) /** * raw_seqcount_begin() - begin a seqcount_t read critical section w/o * lockdep and w/o counter stabilization * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * raw_seqcount_begin opens a read critical section of the given * seqcount_t. Unlike read_seqcount_begin(), this function will not wait * for the count to stabilize. If a writer is active when it begins, it * will fail the read_seqcount_retry() at the end of the read critical * section instead of stabilizing at the beginning of it. * * Use this only in special kernel hot paths where the read section is * small and has a high probability of success through other external * means. It will save a single branching instruction. * * Return: count to be passed to read_seqcount_retry() */ #define raw_seqcount_begin(s) \ ({ \ /* \ * If the counter is odd, let read_seqcount_retry() fail \ * by decrementing the counter. \ */ \ raw_read_seqcount(s) & ~1; \ }) /** * __read_seqcount_retry() - end a seqcount_t read section w/o barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * __read_seqcount_retry is like read_seqcount_retry, but has no smp_rmb() * barrier. Callers should ensure that smp_rmb() or equivalent ordering is * provided before actually loading any of the variables that are to be * protected in this critical section. * * Use carefully, only in critical code, and comment how the barrier is * provided. * * Return: true if a read section retry is required, else false */ #define __read_seqcount_retry(s, start) \ do___read_seqcount_retry(seqprop_ptr(s), start) static inline int do___read_seqcount_retry(const seqcount_t *s, unsigned start) { kcsan_atomic_next(0); return unlikely(READ_ONCE(s->sequence) != start); } /** * read_seqcount_retry() - end a seqcount_t read critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @start: count, from read_seqcount_begin() * * read_seqcount_retry closes the read critical section of given * seqcount_t. If the critical section was invalid, it must be ignored * (and typically retried). * * Return: true if a read section retry is required, else false */ #define read_seqcount_retry(s, start) \ do_read_seqcount_retry(seqprop_ptr(s), start) static inline int do_read_seqcount_retry(const seqcount_t *s, unsigned start) { smp_rmb(); return do___read_seqcount_retry(s, start); } /** * raw_write_seqcount_begin() - start a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants */ #define raw_write_seqcount_begin(s) \ do { \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_raw_write_seqcount_begin(seqprop_ptr(s)); \ } while (0) static inline void do_raw_write_seqcount_begin(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); } /** * raw_write_seqcount_end() - end a seqcount_t write section w/o lockdep * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants */ #define raw_write_seqcount_end(s) \ do { \ do_raw_write_seqcount_end(seqprop_ptr(s)); \ \ if (seqprop_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void do_raw_write_seqcount_end(seqcount_t *s) { smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_begin_nested() - start a seqcount_t write section with * custom lockdep nesting level * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * @subclass: lockdep nesting level * * See Documentation/locking/lockdep-design.rst */ #define write_seqcount_begin_nested(s, subclass) \ do { \ seqprop_assert(s); \ \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_write_seqcount_begin_nested(seqprop_ptr(s), subclass); \ } while (0) static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass) { seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); do_raw_write_seqcount_begin(s); } /** * write_seqcount_begin() - start a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * write_seqcount_begin opens a write side critical section of the given * seqcount_t. * * Context: seqcount_t write side critical sections must be serialized and * non-preemptible. If readers can be invoked from hardirq or softirq * context, interrupts or bottom halves must be respectively disabled. */ #define write_seqcount_begin(s) \ do { \ seqprop_assert(s); \ \ if (seqprop_preemptible(s)) \ preempt_disable(); \ \ do_write_seqcount_begin(seqprop_ptr(s)); \ } while (0) static inline void do_write_seqcount_begin(seqcount_t *s) { do_write_seqcount_begin_nested(s, 0); } /** * write_seqcount_end() - end a seqcount_t write side critical section * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * The write section must've been opened with write_seqcount_begin(). */ #define write_seqcount_end(s) \ do { \ do_write_seqcount_end(seqprop_ptr(s)); \ \ if (seqprop_preemptible(s)) \ preempt_enable(); \ } while (0) static inline void do_write_seqcount_end(seqcount_t *s) { seqcount_release(&s->dep_map, _RET_IP_); do_raw_write_seqcount_end(s); } /** * raw_write_seqcount_barrier() - do a seqcount_t write barrier * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * This can be used to provide an ordering guarantee instead of the usual * consistency guarantee. It is one wmb cheaper, because it can collapse * the two back-to-back wmb()s. * * Note that writes surrounding the barrier should be declared atomic (e.g. * via WRITE_ONCE): a) to ensure the writes become visible to other threads * atomically, avoiding compiler optimizations; b) to document which writes are * meant to propagate to the reader critical section. This is necessary because * neither writes before and after the barrier are enclosed in a seq-writer * critical section that would ensure readers are aware of ongoing writes:: * * seqcount_t seq; * bool X = true, Y = false; * * void read(void) * { * bool x, y; * * do { * int s = read_seqcount_begin(&seq); * * x = X; y = Y; * * } while (read_seqcount_retry(&seq, s)); * * BUG_ON(!x && !y); * } * * void write(void) * { * WRITE_ONCE(Y, true); * * raw_write_seqcount_barrier(seq); * * WRITE_ONCE(X, false); * } */ #define raw_write_seqcount_barrier(s) \ do_raw_write_seqcount_barrier(seqprop_ptr(s)) static inline void do_raw_write_seqcount_barrier(seqcount_t *s) { kcsan_nestable_atomic_begin(); s->sequence++; smp_wmb(); s->sequence++; kcsan_nestable_atomic_end(); } /** * write_seqcount_invalidate() - invalidate in-progress seqcount_t read * side operations * @s: Pointer to seqcount_t or any of the seqcount_LOCKNAME_t variants * * After write_seqcount_invalidate, no seqcount_t read side operations * will complete successfully and see data older than this. */ #define write_seqcount_invalidate(s) \ do_write_seqcount_invalidate(seqprop_ptr(s)) static inline void do_write_seqcount_invalidate(seqcount_t *s) { smp_wmb(); kcsan_nestable_atomic_begin(); s->sequence+=2; kcsan_nestable_atomic_end(); } /* * Latch sequence counters (seqcount_latch_t) * * A sequence counter variant where the counter even/odd value is used to * switch between two copies of protected data. This allows the read path, * typically NMIs, to safely interrupt the write side critical section. * * As the write sections are fully preemptible, no special handling for * PREEMPT_RT is needed. */ typedef struct { seqcount_t seqcount; } seqcount_latch_t; /** * SEQCNT_LATCH_ZERO() - static initializer for seqcount_latch_t * @seq_name: Name of the seqcount_latch_t instance */ #define SEQCNT_LATCH_ZERO(seq_name) { \ .seqcount = SEQCNT_ZERO(seq_name.seqcount), \ } /** * seqcount_latch_init() - runtime initializer for seqcount_latch_t * @s: Pointer to the seqcount_latch_t instance */ #define seqcount_latch_init(s) seqcount_init(&(s)->seqcount) /** * raw_read_seqcount_latch() - pick even/odd latch data copy * @s: Pointer to seqcount_latch_t * * See raw_write_seqcount_latch() for details and a full reader/writer * usage example. * * Return: sequence counter raw value. Use the lowest bit as an index for * picking which data copy to read. The full counter must then be checked * with read_seqcount_latch_retry(). */ static inline unsigned raw_read_seqcount_latch(const seqcount_latch_t *s) { /* * Pairs with the first smp_wmb() in raw_write_seqcount_latch(). * Due to the dependent load, a full smp_rmb() is not needed. */ return READ_ONCE(s->seqcount.sequence); } /** * read_seqcount_latch_retry() - end a seqcount_latch_t read section * @s: Pointer to seqcount_latch_t * @start: count, from raw_read_seqcount_latch() * * Return: true if a read section retry is required, else false */ static inline int read_seqcount_latch_retry(const seqcount_latch_t *s, unsigned start) { return read_seqcount_retry(&s->seqcount, start); } /** * raw_write_seqcount_latch() - redirect latch readers to even/odd copy * @s: Pointer to seqcount_latch_t * * The latch technique is a multiversion concurrency control method that allows * queries during non-atomic modifications. If you can guarantee queries never * interrupt the modification -- e.g. the concurrency is strictly between CPUs * -- you most likely do not need this. * * Where the traditional RCU/lockless data structures rely on atomic * modifications to ensure queries observe either the old or the new state the * latch allows the same for non-atomic updates. The trade-off is doubling the * cost of storage; we have to maintain two copies of the entire data * structure. * * Very simply put: we first modify one copy and then the other. This ensures * there is always one copy in a stable state, ready to give us an answer. * * The basic form is a data structure like:: * * struct latch_struct { * seqcount_latch_t seq; * struct data_struct data[2]; * }; * * Where a modification, which is assumed to be externally serialized, does the * following:: * * void latch_modify(struct latch_struct *latch, ...) * { * smp_wmb(); // Ensure that the last data[1] update is visible * latch->seq.sequence++; * smp_wmb(); // Ensure that the seqcount update is visible * * modify(latch->data[0], ...); * * smp_wmb(); // Ensure that the data[0] update is visible * latch->seq.sequence++; * smp_wmb(); // Ensure that the seqcount update is visible * * modify(latch->data[1], ...); * } * * The query will have a form like:: * * struct entry *latch_query(struct latch_struct *latch, ...) * { * struct entry *entry; * unsigned seq, idx; * * do { * seq = raw_read_seqcount_latch(&latch->seq); * * idx = seq & 0x01; * entry = data_query(latch->data[idx], ...); * * // This includes needed smp_rmb() * } while (read_seqcount_latch_retry(&latch->seq, seq)); * * return entry; * } * * So during the modification, queries are first redirected to data[1]. Then we * modify data[0]. When that is complete, we redirect queries back to data[0] * and we can modify data[1]. * * NOTE: * * The non-requirement for atomic modifications does _NOT_ include * the publishing of new entries in the case where data is a dynamic * data structure. * * An iteration might start in data[0] and get suspended long enough * to miss an entire modification sequence, once it resumes it might * observe the new entry. * * NOTE2: * * When data is a dynamic data structure; one should use regular RCU * patterns to manage the lifetimes of the objects within. */ static inline void raw_write_seqcount_latch(seqcount_latch_t *s) { smp_wmb(); /* prior stores before incrementing "sequence" */ s->seqcount.sequence++; smp_wmb(); /* increment "sequence" before following stores */ } /* * Sequential locks (seqlock_t) * * Sequence counters with an embedded spinlock for writer serialization * and non-preemptibility. * * For more info, see: * - Comments on top of seqcount_t * - Documentation/locking/seqlock.rst */ typedef struct { /* * Make sure that readers don't starve writers on PREEMPT_RT: use * seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK(). */ seqcount_spinlock_t seqcount; spinlock_t lock; } seqlock_t; #define __SEQLOCK_UNLOCKED(lockname) \ { \ .seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \ .lock = __SPIN_LOCK_UNLOCKED(lockname) \ } /** * seqlock_init() - dynamic initializer for seqlock_t * @sl: Pointer to the seqlock_t instance */ #define seqlock_init(sl) \ do { \ spin_lock_init(&(sl)->lock); \ seqcount_spinlock_init(&(sl)->seqcount, &(sl)->lock); \ } while (0) /** * DEFINE_SEQLOCK(sl) - Define a statically allocated seqlock_t * @sl: Name of the seqlock_t instance */ #define DEFINE_SEQLOCK(sl) \ seqlock_t sl = __SEQLOCK_UNLOCKED(sl) /** * read_seqbegin() - start a seqlock_t read side critical section * @sl: Pointer to seqlock_t * * Return: count, to be passed to read_seqretry() */ static inline unsigned read_seqbegin(const seqlock_t *sl) { return read_seqcount_begin(&sl->seqcount); } /** * read_seqretry() - end a seqlock_t read side section * @sl: Pointer to seqlock_t * @start: count, from read_seqbegin() * * read_seqretry closes the read side critical section of given seqlock_t. * If the critical section was invalid, it must be ignored (and typically * retried). * * Return: true if a read section retry is required, else false */ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) { return read_seqcount_retry(&sl->seqcount, start); } /* * For all seqlock_t write side functions, use the the internal * do_write_seqcount_begin() instead of generic write_seqcount_begin(). * This way, no redundant lockdep_assert_held() checks are added. */ /** * write_seqlock() - start a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_seqlock opens a write side critical section for the given * seqlock_t. It also implicitly acquires the spinlock_t embedded inside * that sequential lock. All seqlock_t write side sections are thus * automatically serialized and non-preemptible. * * Context: if the seqlock_t read section, or other write side critical * sections, can be invoked from hardirq or softirq contexts, use the * _irqsave or _bh variants of this function instead. */ static inline void write_seqlock(seqlock_t *sl) { spin_lock(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock() - end a seqlock_t write side critical section * @sl: Pointer to seqlock_t * * write_sequnlock closes the (serialized and non-preemptible) write side * critical section of given seqlock_t. */ static inline void write_sequnlock(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock(&sl->lock); } /** * write_seqlock_bh() - start a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * _bh variant of write_seqlock(). Use only if the read side section, or * other write side sections, can be invoked from softirq contexts. */ static inline void write_seqlock_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_bh() - end a softirqs-disabled seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_bh closes the serialized, non-preemptible, and * softirqs-disabled, seqlock_t write side critical section opened with * write_seqlock_bh(). */ static inline void write_sequnlock_bh(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_bh(&sl->lock); } /** * write_seqlock_irq() - start a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * _irq variant of write_seqlock(). Use only if the read side section, or * other write sections, can be invoked from hardirq contexts. */ static inline void write_seqlock_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); do_write_seqcount_begin(&sl->seqcount.seqcount); } /** * write_sequnlock_irq() - end a non-interruptible seqlock_t write section * @sl: Pointer to seqlock_t * * write_sequnlock_irq closes the serialized and non-interruptible * seqlock_t write side section opened with write_seqlock_irq(). */ static inline void write_sequnlock_irq(seqlock_t *sl) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_irq(&sl->lock); } static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl) { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); do_write_seqcount_begin(&sl->seqcount.seqcount); return flags; } /** * write_seqlock_irqsave() - start a non-interruptible seqlock_t write * section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to write_sequnlock_irqrestore(). * * _irqsave variant of write_seqlock(). Use it only if the read side * section, or other write sections, can be invoked from hardirq context. */ #define write_seqlock_irqsave(lock, flags) \ do { flags = __write_seqlock_irqsave(lock); } while (0) /** * write_sequnlock_irqrestore() - end non-interruptible seqlock_t write * section * @sl: Pointer to seqlock_t * @flags: Caller's saved interrupt state, from write_seqlock_irqsave() * * write_sequnlock_irqrestore closes the serialized and non-interruptible * seqlock_t write section previously opened with write_seqlock_irqsave(). */ static inline void write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) { do_write_seqcount_end(&sl->seqcount.seqcount); spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqlock_excl() - begin a seqlock_t locking reader section * @sl: Pointer to seqlock_t * * read_seqlock_excl opens a seqlock_t locking reader critical section. A * locking reader exclusively locks out *both* other writers *and* other * locking readers, but it does not update the embedded sequence number. * * Locking readers act like a normal spin_lock()/spin_unlock(). * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * The opened read section must be closed with read_sequnlock_excl(). */ static inline void read_seqlock_excl(seqlock_t *sl) { spin_lock(&sl->lock); } /** * read_sequnlock_excl() - end a seqlock_t locking reader critical section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl(seqlock_t *sl) { spin_unlock(&sl->lock); } /** * read_seqlock_excl_bh() - start a seqlock_t locking reader section with * softirqs disabled * @sl: Pointer to seqlock_t * * _bh variant of read_seqlock_excl(). Use this variant only if the * seqlock_t write side section, *or other read sections*, can be invoked * from softirq contexts. */ static inline void read_seqlock_excl_bh(seqlock_t *sl) { spin_lock_bh(&sl->lock); } /** * read_sequnlock_excl_bh() - stop a seqlock_t softirq-disabled locking * reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_bh(seqlock_t *sl) { spin_unlock_bh(&sl->lock); } /** * read_seqlock_excl_irq() - start a non-interruptible seqlock_t locking * reader section * @sl: Pointer to seqlock_t * * _irq variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ static inline void read_seqlock_excl_irq(seqlock_t *sl) { spin_lock_irq(&sl->lock); } /** * read_sequnlock_excl_irq() - end an interrupts-disabled seqlock_t * locking reader section * @sl: Pointer to seqlock_t */ static inline void read_sequnlock_excl_irq(seqlock_t *sl) { spin_unlock_irq(&sl->lock); } static inline unsigned long __read_seqlock_excl_irqsave(seqlock_t *sl) { unsigned long flags; spin_lock_irqsave(&sl->lock, flags); return flags; } /** * read_seqlock_excl_irqsave() - start a non-interruptible seqlock_t * locking reader section * @lock: Pointer to seqlock_t * @flags: Stack-allocated storage for saving caller's local interrupt * state, to be passed to read_sequnlock_excl_irqrestore(). * * _irqsave variant of read_seqlock_excl(). Use this only if the seqlock_t * write side section, *or other read sections*, can be invoked from a * hardirq context. */ #define read_seqlock_excl_irqsave(lock, flags) \ do { flags = __read_seqlock_excl_irqsave(lock); } while (0) /** * read_sequnlock_excl_irqrestore() - end non-interruptible seqlock_t * locking reader section * @sl: Pointer to seqlock_t * @flags: Caller saved interrupt state, from read_seqlock_excl_irqsave() */ static inline void read_sequnlock_excl_irqrestore(seqlock_t *sl, unsigned long flags) { spin_unlock_irqrestore(&sl->lock, flags); } /** * read_seqbegin_or_lock() - begin a seqlock_t lockless or locking reader * @lock: Pointer to seqlock_t * @seq : Marker and return parameter. If the passed value is even, the * reader will become a *lockless* seqlock_t reader as in read_seqbegin(). * If the passed value is odd, the reader will become a *locking* reader * as in read_seqlock_excl(). In the first call to this function, the * caller *must* initialize and pass an even value to @seq; this way, a * lockless read can be optimistically tried first. * * read_seqbegin_or_lock is an API designed to optimistically try a normal * lockless seqlock_t read section first. If an odd counter is found, the * lockless read trial has failed, and the next read iteration transforms * itself into a full seqlock_t locking reader. * * This is typically used to avoid seqlock_t lockless readers starvation * (too much retry loops) in the case of a sharp spike in write side * activity. * * Context: if the seqlock_t write section, *or other read sections*, can * be invoked from hardirq or softirq contexts, use the _irqsave or _bh * variant of this function instead. * * Check Documentation/locking/seqlock.rst for template example code. * * Return: the encountered sequence counter value, through the @seq * parameter, which is overloaded as a return parameter. This returned * value must be checked with need_seqretry(). If the read section need to * be retried, this returned value must also be passed as the @seq * parameter of the next read_seqbegin_or_lock() iteration. */ static inline void read_seqbegin_or_lock(seqlock_t *lock, int *seq) { if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl(lock); } /** * need_seqretry() - validate seqlock_t "locking or lockless" read section * @lock: Pointer to seqlock_t * @seq: sequence count, from read_seqbegin_or_lock() * * Return: true if a read section retry is required, false otherwise */ static inline int need_seqretry(seqlock_t *lock, int seq) { return !(seq & 1) && read_seqretry(lock, seq); } /** * done_seqretry() - end seqlock_t "locking or lockless" reader section * @lock: Pointer to seqlock_t * @seq: count, from read_seqbegin_or_lock() * * done_seqretry finishes the seqlock_t read side critical section started * with read_seqbegin_or_lock() and validated by need_seqretry(). */ static inline void done_seqretry(seqlock_t *lock, int seq) { if (seq & 1) read_sequnlock_excl(lock); } /** * read_seqbegin_or_lock_irqsave() - begin a seqlock_t lockless reader, or * a non-interruptible locking reader * @lock: Pointer to seqlock_t * @seq: Marker and return parameter. Check read_seqbegin_or_lock(). * * This is the _irqsave variant of read_seqbegin_or_lock(). Use it only if * the seqlock_t write section, *or other read sections*, can be invoked * from hardirq context. * * Note: Interrupts will be disabled only for "locking reader" mode. * * Return: * * 1. The saved local interrupts state in case of a locking reader, to * be passed to done_seqretry_irqrestore(). * * 2. The encountered sequence counter value, returned through @seq * overloaded as a return parameter. Check read_seqbegin_or_lock(). */ static inline unsigned long read_seqbegin_or_lock_irqsave(seqlock_t *lock, int *seq) { unsigned long flags = 0; if (!(*seq & 1)) /* Even */ *seq = read_seqbegin(lock); else /* Odd */ read_seqlock_excl_irqsave(lock, flags); return flags; } /** * done_seqretry_irqrestore() - end a seqlock_t lockless reader, or a * non-interruptible locking reader section * @lock: Pointer to seqlock_t * @seq: Count, from read_seqbegin_or_lock_irqsave() * @flags: Caller's saved local interrupt state in case of a locking * reader, also from read_seqbegin_or_lock_irqsave() * * This is the _irqrestore variant of done_seqretry(). The read section * must've been opened with read_seqbegin_or_lock_irqsave(), and validated * by need_seqretry(). */ static inline void done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags) { if (seq & 1) read_sequnlock_excl_irqrestore(lock, flags); } #endif /* __LINUX_SEQLOCK_H */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* memcontrol.h - Memory Controller * * Copyright IBM Corporation, 2007 * Author Balbir Singh <balbir@linux.vnet.ibm.com> * * Copyright 2007 OpenVZ SWsoft Inc * Author: Pavel Emelianov <xemul@openvz.org> */ #ifndef _LINUX_MEMCONTROL_H #define _LINUX_MEMCONTROL_H #include <linux/cgroup.h> #include <linux/vm_event_item.h> #include <linux/hardirq.h> #include <linux/jump_label.h> #include <linux/page_counter.h> #include <linux/vmpressure.h> #include <linux/eventfd.h> #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/writeback.h> #include <linux/page-flags.h> struct mem_cgroup; struct obj_cgroup; struct page; struct mm_struct; struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, MEMCG_PERCPU_B, MEMCG_NR_STAT, }; enum memcg_memory_event { MEMCG_LOW, MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, }; struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; unsigned int generation; }; #ifdef CONFIG_MEMCG #define MEM_CGROUP_ID_SHIFT 16 #define MEM_CGROUP_ID_MAX USHRT_MAX struct mem_cgroup_id { int id; refcount_t ref; }; /* * Per memcg event counter is incremented at every pagein/pageout. With THP, * it will be incremented by the number of pages. This counter is used * to trigger some periodic events. This is straightforward and better * than using jiffies etc. to handle periodic memcg event. */ enum mem_cgroup_events_target { MEM_CGROUP_TARGET_THRESH, MEM_CGROUP_TARGET_SOFTLIMIT, MEM_CGROUP_NTARGETS, }; struct memcg_vmstats_percpu { long stat[MEMCG_NR_STAT]; unsigned long events[NR_VM_EVENT_ITEMS]; unsigned long nr_page_events; unsigned long targets[MEM_CGROUP_NTARGETS]; }; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; /* scan generation, increased every round-trip */ unsigned int generation; }; struct lruvec_stat { long count[NR_VM_NODE_STAT_ITEMS]; }; /* * Bitmap of shrinker::id corresponding to memcg-aware shrinkers, * which have elements charged to this memcg. */ struct memcg_shrinker_map { struct rcu_head rcu; unsigned long map[]; }; /* * per-node information in memory controller. */ struct mem_cgroup_per_node { struct lruvec lruvec; /* Legacy local VM stats */ struct lruvec_stat __percpu *lruvec_stat_local; /* Subtree VM stats (batched updates) */ struct lruvec_stat __percpu *lruvec_stat_cpu; atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS]; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter; struct memcg_shrinker_map __rcu *shrinker_map; struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; unsigned long threshold; }; /* For threshold */ struct mem_cgroup_threshold_ary { /* An array index points to threshold just below or equal to usage. */ int current_threshold; /* Size of entries[] */ unsigned int size; /* Array of thresholds */ struct mem_cgroup_threshold entries[]; }; struct mem_cgroup_thresholds { /* Primary thresholds array */ struct mem_cgroup_threshold_ary *primary; /* * Spare threshold array. * This is needed to make mem_cgroup_unregister_event() "never fail". * It must be able to store at least primary->size - 1 entries. */ struct mem_cgroup_threshold_ary *spare; }; enum memcg_kmem_state { KMEM_NONE, KMEM_ALLOCATED, KMEM_ONLINE, }; #if defined(CONFIG_SMP) struct memcg_padding { char x[0]; } ____cacheline_internodealigned_in_smp; #define MEMCG_PADDING(name) struct memcg_padding name; #else #define MEMCG_PADDING(name) #endif /* * Remember four most recent foreign writebacks with dirty pages in this * cgroup. Inode sharing is expected to be uncommon and, even if we miss * one in a given round, we're likely to catch it later if it keeps * foreign-dirtying, so a fairly low count should be enough. * * See mem_cgroup_track_foreign_dirty_slowpath() for details. */ #define MEMCG_CGWB_FRN_CNT 4 struct memcg_cgwb_frn { u64 bdi_id; /* bdi->id of the foreign inode */ int memcg_id; /* memcg->css.id of foreign inode */ u64 at; /* jiffies_64 at the time of dirtying */ struct wb_completion done; /* tracks in-flight foreign writebacks */ }; /* * Bucket for arbitrarily byte-sized objects charged to a memory * cgroup. The bucket can be reparented in one piece when the cgroup * is destroyed, without having to round up the individual references * of all live memory objects in the wild. */ struct obj_cgroup { struct percpu_ref refcnt; struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; }; /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide * statistics based on the statistics developed by Rik Van Riel for clock-pro, * to help the administrator determine what knobs to tune. */ struct mem_cgroup { struct cgroup_subsys_state css; /* Private memcg ID. Used to ID objects that outlive the cgroup */ struct mem_cgroup_id id; /* Accounted resources */ struct page_counter memory; /* Both v1 & v2 */ union { struct page_counter swap; /* v2 only */ struct page_counter memsw; /* v1 only */ }; /* Legacy consumer-oriented counters */ struct page_counter kmem; /* v1 only */ struct page_counter tcpmem; /* v1 only */ /* Range enforcement for interrupt charges */ struct work_struct high_work; unsigned long soft_limit; /* vmpressure notifications */ struct vmpressure vmpressure; /* * Should the accounting and control be hierarchical, per subtree? */ bool use_hierarchy; /* * Should the OOM killer kill all belonging tasks, had it kill one? */ bool oom_group; /* protected by memcg_oom_lock */ bool oom_lock; int under_oom; int swappiness; /* OOM-Killer disable */ int oom_kill_disable; /* memory.events and memory.events.local */ struct cgroup_file events_file; struct cgroup_file events_local_file; /* handle for "memory.swap.events" */ struct cgroup_file swap_events_file; /* protect arrays of thresholds */ struct mutex thresholds_lock; /* thresholds for memory usage. RCU-protected */ struct mem_cgroup_thresholds thresholds; /* thresholds for mem+swap usage. RCU-protected */ struct mem_cgroup_thresholds memsw_thresholds; /* For oom notifier event fd */ struct list_head oom_notify; /* * Should we move charges of a task when a task is moved into this * mem_cgroup ? And what type of charges should we move ? */ unsigned long move_charge_at_immigrate; /* taken only while moving_account > 0 */ spinlock_t move_lock; unsigned long move_lock_flags; MEMCG_PADDING(_pad1_); atomic_long_t vmstats[MEMCG_NR_STAT]; atomic_long_t vmevents[NR_VM_EVENT_ITEMS]; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; unsigned long socket_pressure; /* Legacy tcp memory accounting */ bool tcpmem_active; int tcpmem_pressure; #ifdef CONFIG_MEMCG_KMEM /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; enum memcg_kmem_state kmem_state; struct obj_cgroup __rcu *objcg; /* list of inherited objcgs, protected by objcg_lock */ struct list_head objcg_list; #endif MEMCG_PADDING(_pad2_); /* * set > 0 if pages under this cgroup are moving to other cgroup. */ atomic_t moving_account; struct task_struct *move_lock_task; /* Legacy local VM stats and events */ struct memcg_vmstats_percpu __percpu *vmstats_local; /* Subtree VM stats and events (batched updates) */ struct memcg_vmstats_percpu __percpu *vmstats_percpu; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif struct mem_cgroup_per_node *nodeinfo[0]; /* WARNING: nodeinfo must be the last member here */ }; /* * size of first charge trial. "32" comes from vmscan.c's magic value. * TODO: maybe necessary to use big numbers in big irons. */ #define MEMCG_CHARGE_BATCH 32U extern struct mem_cgroup *root_mem_cgroup; static __always_inline bool memcg_stat_item_in_bytes(int idx) { if (idx == MEMCG_PERCPU_B) return true; return vmstat_item_in_bytes(idx); } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); } static inline bool mem_cgroup_disabled(void) { return !cgroup_subsys_enabled(memory_cgrp_subsys); } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low) { *min = *low = 0; if (mem_cgroup_disabled()) return; /* * There is no reclaim protection applied to a targeted reclaim. * We are special casing this specific case here because * mem_cgroup_protected calculation is not robust enough to keep * the protection invariant for calculated effective values for * parallel reclaimers with different reclaim target. This is * especially a problem for tail memcgs (as they have pages on LRU) * which would want to have effective values 0 for targeted reclaim * but a different value for external reclaim. * * Example * Let's have global and A's reclaim in parallel: * | * A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G) * |\ * | C (low = 1G, usage = 2.5G) * B (low = 1G, usage = 0.5G) * * For the global reclaim * A.elow = A.low * B.elow = min(B.usage, B.low) because children_low_usage <= A.elow * C.elow = min(C.usage, C.low) * * With the effective values resetting we have A reclaim * A.elow = 0 * B.elow = B.low * C.elow = C.low * * If the global reclaim races with A's reclaim then * B.elow = C.elow = 0 because children_low_usage > A.elow) * is possible and reclaiming B would be violating the protection. * */ if (root == memcg) return; *min = READ_ONCE(memcg->memory.emin); *low = READ_ONCE(memcg->memory.elow); } void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg); static inline bool mem_cgroup_supports_protection(struct mem_cgroup *memcg) { /* * The root memcg doesn't account charges, and doesn't support * protection. */ return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg); } static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg) { if (!mem_cgroup_supports_protection(memcg)) return false; return READ_ONCE(memcg->memory.elow) >= page_counter_read(&memcg->memory); } static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) { if (!mem_cgroup_supports_protection(memcg)) return false; return READ_ONCE(memcg->memory.emin) >= page_counter_read(&memcg->memory); } int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); static struct mem_cgroup_per_node * mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) { return memcg->nodeinfo[nid]; } /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node * @memcg: memcg of the wanted lruvec * * Returns the lru list vector holding pages for a given @memcg & * @node combination. This can be the node lruvec, if the memory * controller is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { struct mem_cgroup_per_node *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { lruvec = &pgdat->__lruvec; goto out; } if (!memcg) memcg = root_mem_cgroup; mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); lruvec = &mz->lruvec; out: /* * Since a node can be onlined after the mem_cgroup was created, * we have to be prepared to initialize lruvec->pgdat here; * and if offlined then reonlined, we need to reinitialize it. */ if (unlikely(lruvec->pgdat != pgdat)) lruvec->pgdat = pgdat; return lruvec; } struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *); struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); struct mem_cgroup *get_mem_cgroup_from_page(struct page *page); static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg) { return percpu_ref_tryget(&objcg->refcnt); } static inline void obj_cgroup_get(struct obj_cgroup *objcg) { percpu_ref_get(&objcg->refcnt); } static inline void obj_cgroup_put(struct obj_cgroup *objcg) { percpu_ref_put(&objcg->refcnt); } /* * After the initialization objcg->memcg is always pointing at * a valid memcg, but can be atomically swapped to the parent memcg. * * The caller must ensure that the returned memcg won't be released: * e.g. acquire the rcu_read_lock or css_set_lock. */ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) { return READ_ONCE(objcg->memcg); } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { if (memcg) css_put(&memcg->css); } #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); int mem_cgroup_scan_tasks(struct mem_cgroup *, int (*)(struct task_struct *, void *), void *); static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return 0; return memcg->id.id; } struct mem_cgroup *mem_cgroup_from_id(unsigned short id); static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return mem_cgroup_from_css(seq_css(m)); } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { struct mem_cgroup_per_node *mz; if (mem_cgroup_disabled()) return NULL; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return mz->memcg; } /** * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find * * Returns the parent memcg, or NULL if this is the root or the memory * controller is in legacy no-hierarchy mode. */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { if (!memcg->memory.parent) return NULL; return mem_cgroup_from_counter(memcg->memory.parent, memory); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root) { if (root == memcg) return true; if (!root->use_hierarchy) return false; return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { struct mem_cgroup *task_memcg; bool match = false; rcu_read_lock(); task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (task_memcg) match = mem_cgroup_is_descendant(task_memcg, memcg); rcu_read_unlock(); return match; } struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); ino_t page_cgroup_ino(struct page *page); static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return true; return !!(memcg->css.flags & CSS_ONLINE); } /* * For memory reclaim. */ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, int nr_pages); static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { struct mem_cgroup_per_node *mz; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } void mem_cgroup_handle_over_high(void); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); unsigned long mem_cgroup_size(struct mem_cgroup *memcg); void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p); void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg); static inline void mem_cgroup_enter_user_fault(void) { WARN_ON(current->in_user_fault); current->in_user_fault = 1; } static inline void mem_cgroup_exit_user_fault(void) { WARN_ON(!current->in_user_fault); current->in_user_fault = 0; } static inline bool task_in_memcg_oom(struct task_struct *p) { return p->memcg_in_oom; } bool mem_cgroup_oom_synchronize(bool wait); struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); #ifdef CONFIG_MEMCG_SWAP extern bool cgroup_memory_noswap; #endif struct mem_cgroup *lock_page_memcg(struct page *page); void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); /* * idx can be of type enum memcg_stat_item or node_stat_item. * Keep in sync with memcg_exact_page_state(). */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { long x = atomic_long_read(&memcg->vmstats[idx]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * idx can be of type enum memcg_stat_item or node_stat_item. * Keep in sync with memcg_exact_page_state(). */ static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) { long x = 0; int cpu; for_each_possible_cpu(cpu) x += per_cpu(memcg->vmstats_local->stat[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) { unsigned long flags; local_irq_save(flags); __mod_memcg_state(memcg, idx, val); local_irq_restore(flags); } /** * mod_memcg_page_state - update page state statistics * @page: the page * @idx: page state item to account * @val: number of pages (positive or negative) * * The @page must be locked or the caller must use lock_page_memcg() * to prevent double accounting when the page is concurrently being * moved to another memcg: * * lock_page(page) or lock_page_memcg(page) * if (TestClearPageState(page)) * mod_memcg_page_state(page, state, -1); * unlock_page(page) or unlock_page_memcg(page) * * Kernel pages are an exception to this, since they'll never move. */ static inline void __mod_memcg_page_state(struct page *page, int idx, int val) { if (page->mem_cgroup) __mod_memcg_state(page->mem_cgroup, idx, val); } static inline void mod_memcg_page_state(struct page *page, int idx, int val) { if (page->mem_cgroup) mod_memcg_state(page->mem_cgroup, idx, val); } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; long x; if (mem_cgroup_disabled()) return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); x = atomic_long_read(&pn->lruvec_stat[idx]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; long x = 0; int cpu; if (mem_cgroup_disabled()) return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); for_each_possible_cpu(cpu) x += per_cpu(pn->lruvec_stat_local->count[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val); void mod_memcg_obj_state(void *p, int idx, int val); static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_slab_state(p, idx, val); local_irq_restore(flags); } static inline void mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_memcg_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { struct page *head = compound_head(page); /* rmap on tail pages */ pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; /* Untracked pages have no memcg, no lruvec. Update only the node */ if (!head->mem_cgroup) { __mod_node_page_state(pgdat, idx, val); return; } lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat); __mod_lruvec_state(lruvec, idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_page_state(page, idx, val); local_irq_restore(flags); } unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { unsigned long flags; local_irq_save(flags); __count_memcg_events(memcg, idx, count); local_irq_restore(flags); } static inline void count_memcg_page_event(struct page *page, enum vm_event_item idx) { if (page->mem_cgroup) count_memcg_events(page->mem_cgroup, idx, 1); } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) count_memcg_events(memcg, idx, 1); rcu_read_unlock(); } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX || event == MEMCG_SWAP_FAIL; atomic_long_inc(&memcg->memory_events_local[event]); if (!swap_event) cgroup_file_notify(&memcg->events_local_file); do { atomic_long_inc(&memcg->memory_events[event]); if (swap_event) cgroup_file_notify(&memcg->swap_events_file); else cgroup_file_notify(&memcg->events_file); if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) break; if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) break; } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) memcg_memory_event(memcg, event); rcu_read_unlock(); } void split_page_memcg(struct page *head, unsigned int nr); #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 #define MEM_CGROUP_ID_MAX 0 struct mem_cgroup; static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_disabled(void) { return true; } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low) { *min = *low = 0; } static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg) { } static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg) { return false; } static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) { return false; } static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { return 0; } static inline void mem_cgroup_uncharge(struct page *page) { } static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } static inline void mem_cgroup_migrate(struct page *old, struct page *new) { } static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { return &pgdat->__lruvec; } static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat) { return &pgdat->__lruvec; } static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return NULL; } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { return true; } static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) { return NULL; } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim) { return NULL; } static inline void mem_cgroup_iter_break(struct mem_cgroup *root, struct mem_cgroup *prev) { } static inline int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*fn)(struct task_struct *, void *), void *arg) { return 0; } static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { return 0; } static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { WARN_ON_ONCE(id); /* XXX: This should always return root_mem_cgroup */ return NULL; } static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return NULL; } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { return NULL; } static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { return true; } static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { return 0; } static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) { return 0; } static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg) { return 0; } static inline void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) { } static inline void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } static inline struct mem_cgroup *lock_page_memcg(struct page *page) { return NULL; } static inline void __unlock_page_memcg(struct mem_cgroup *memcg) { } static inline void unlock_page_memcg(struct page *page) { } static inline void mem_cgroup_handle_over_high(void) { } static inline void mem_cgroup_enter_user_fault(void) { } static inline void mem_cgroup_exit_user_fault(void) { } static inline bool task_in_memcg_oom(struct task_struct *p) { return false; } static inline bool mem_cgroup_oom_synchronize(bool wait) { return false; } static inline struct mem_cgroup *mem_cgroup_get_oom_group( struct task_struct *victim, struct mem_cgroup *oom_domain) { return NULL; } static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) { } static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return 0; } static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) { return 0; } static inline void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int nr) { } static inline void mod_memcg_state(struct mem_cgroup *memcg, int idx, int nr) { } static inline void __mod_memcg_page_state(struct page *page, int idx, int nr) { } static inline void mod_memcg_page_state(struct page *page, int idx, int nr) { } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { } static inline void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { __mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { mod_node_page_state(page_pgdat(page), idx, val); } static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); __mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_memcg_obj_state(void *p, int idx, int val) { } static inline unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned) { return 0; } static inline void split_page_memcg(struct page *head, unsigned int nr) { } static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void count_memcg_page_event(struct page *page, int idx) { } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } #endif /* CONFIG_MEMCG */ /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __inc_memcg_state(struct mem_cgroup *memcg, int idx) { __mod_memcg_state(memcg, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __dec_memcg_state(struct mem_cgroup *memcg, int idx) { __mod_memcg_state(memcg, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __inc_memcg_page_state(struct page *page, int idx) { __mod_memcg_page_state(page, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __dec_memcg_page_state(struct page *page, int idx) { __mod_memcg_page_state(page, idx, -1); } static inline void __inc_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { __mod_lruvec_state(lruvec, idx, 1); } static inline void __dec_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { __mod_lruvec_state(lruvec, idx, -1); } static inline void __inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { __mod_lruvec_page_state(page, idx, 1); } static inline void __dec_lruvec_page_state(struct page *page, enum node_stat_item idx) { __mod_lruvec_page_state(page, idx, -1); } static inline void __inc_lruvec_slab_state(void *p, enum node_stat_item idx) { __mod_lruvec_slab_state(p, idx, 1); } static inline void __dec_lruvec_slab_state(void *p, enum node_stat_item idx) { __mod_lruvec_slab_state(p, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_state(struct mem_cgroup *memcg, int idx) { mod_memcg_state(memcg, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void dec_memcg_state(struct mem_cgroup *memcg, int idx) { mod_memcg_state(memcg, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_page_state(struct page *page, int idx) { mod_memcg_page_state(page, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void dec_memcg_page_state(struct page *page, int idx) { mod_memcg_page_state(page, idx, -1); } static inline void inc_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { mod_lruvec_state(lruvec, idx, 1); } static inline void dec_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { mod_lruvec_state(lruvec, idx, -1); } static inline void inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { mod_lruvec_page_state(page, idx, 1); } static inline void dec_lruvec_page_state(struct page *page, enum node_stat_item idx) { mod_lruvec_page_state(page, idx, -1); } static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) { struct mem_cgroup *memcg; memcg = lruvec_memcg(lruvec); if (!memcg) return NULL; memcg = parent_mem_cgroup(memcg); if (!memcg) return NULL; return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); } #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, struct bdi_writeback *wb); static inline void mem_cgroup_track_foreign_dirty(struct page *page, struct bdi_writeback *wb) { if (mem_cgroup_disabled()) return; if (unlikely(&page->mem_cgroup->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(page, wb); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); #else /* CONFIG_CGROUP_WRITEBACK */ static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) { return NULL; } static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback) { } static inline void mem_cgroup_track_foreign_dirty(struct page *page, struct bdi_writeback *wb) { } static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) { } #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) return true; do { if (time_before(jiffies, memcg->socket_pressure)) return true; } while ((memcg = parent_mem_cgroup(memcg))); return false; } extern int memcg_expand_shrinker_maps(int new_id); extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; static inline void mem_cgroup_sk_free(struct sock *sk) { }; static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { return false; } static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { } #endif #ifdef CONFIG_MEMCG_KMEM int __memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, unsigned int nr_pages); void __memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); struct obj_cgroup *get_obj_cgroup_from_current(void); int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); extern struct static_key_false memcg_kmem_enabled_key; extern int memcg_nr_cache_ids; void memcg_get_cache_ids(void); void memcg_put_cache_ids(void); /* * Helper macro to loop through all memcg-specific caches. Callers must still * check if the cache is valid (it is either valid or NULL). * the slab_mutex must be held when looping through those caches */ #define for_each_memcg_cache_index(_idx) \ for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++) static inline bool memcg_kmem_enabled(void) { return static_branch_likely(&memcg_kmem_enabled_key); } static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { if (memcg_kmem_enabled()) return __memcg_kmem_charge_page(page, gfp, order); return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { if (memcg_kmem_enabled()) __memcg_kmem_uncharge_page(page, order); } static inline int memcg_kmem_charge(struct mem_cgroup *memcg, gfp_t gfp, unsigned int nr_pages) { if (memcg_kmem_enabled()) return __memcg_kmem_charge(memcg, gfp, nr_pages); return 0; } static inline void memcg_kmem_uncharge(struct mem_cgroup *memcg, unsigned int nr_pages) { if (memcg_kmem_enabled()) __memcg_kmem_uncharge(memcg, nr_pages); } /* * helper for accessing a memcg's index. It will be used as an index in the * child cache array in kmem_cache, and also to derive its name. This function * will return -1 when this is not a kmem-limited memcg. */ static inline int memcg_cache_id(struct mem_cgroup *memcg) { return memcg ? memcg->kmemcg_id : -1; } struct mem_cgroup *mem_cgroup_from_obj(void *p); #else static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { } static inline int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) static inline bool memcg_kmem_enabled(void) { return false; } static inline int memcg_cache_id(struct mem_cgroup *memcg) { return -1; } static inline void memcg_get_cache_ids(void) { } static inline void memcg_put_cache_ids(void) { } static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) { return NULL; } #endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/buffer.c * * Copyright (C) 1991, 1992, 2002 Linus Torvalds */ /* * Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95 * * Removed a lot of unnecessary code and simplified things now that * the buffer cache isn't our primary cache - Andrew Tridgell 12/96 * * Speed up hash, lru, and free list operations. Use gfp() for allocating * hash table, use SLAB cache for buffer heads. SMP threading. -DaveM * * Added 32k buffer block sizes - these are required older ARM systems. - RMK * * async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de> */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/iomap.h> #include <linux/mm.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/capability.h> #include <linux/blkdev.h> #include <linux/file.h> #include <linux/quotaops.h> #include <linux/highmem.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #include <linux/hash.h> #include <linux/suspend.h> #include <linux/buffer_head.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/mpage.h> #include <linux/bit_spinlock.h> #include <linux/pagevec.h> #include <linux/sched/mm.h> #include <trace/events/block.h> #include <linux/fscrypt.h> #include "internal.h" static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, enum rw_hint hint, struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) inline void touch_buffer(struct buffer_head *bh) { trace_block_touch_buffer(bh); mark_page_accessed(bh->b_page); } EXPORT_SYMBOL(touch_buffer); void __lock_buffer(struct buffer_head *bh) { wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); void unlock_buffer(struct buffer_head *bh) { clear_bit_unlock(BH_Lock, &bh->b_state); smp_mb__after_atomic(); wake_up_bit(&bh->b_state, BH_Lock); } EXPORT_SYMBOL(unlock_buffer); /* * Returns if the page has dirty or writeback buffers. If all the buffers * are unlocked and clean then the PageDirty information is stale. If * any of the pages are locked, it is assumed they are locked for IO. */ void buffer_check_dirty_writeback(struct page *page, bool *dirty, bool *writeback) { struct buffer_head *head, *bh; *dirty = false; *writeback = false; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) return; if (PageWriteback(page)) *writeback = true; head = page_buffers(page); bh = head; do { if (buffer_locked(bh)) *writeback = true; if (buffer_dirty(bh)) *dirty = true; bh = bh->b_this_page; } while (bh != head); } EXPORT_SYMBOL(buffer_check_dirty_writeback); /* * Block until a buffer comes unlocked. This doesn't stop it * from becoming locked again - you have to lock it yourself * if you want to preserve its state. */ void __wait_on_buffer(struct buffer_head * bh) { wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__wait_on_buffer); static void buffer_io_error(struct buffer_head *bh, char *msg) { if (!test_bit(BH_Quiet, &bh->b_state)) printk_ratelimited(KERN_ERR "Buffer I/O error on dev %pg, logical block %llu%s\n", bh->b_bdev, (unsigned long long)bh->b_blocknr, msg); } /* * End-of-IO handler helper function which does not touch the bh after * unlocking it. * Note: unlock_buffer() sort-of does touch the bh after unlocking it, but * a race there is benign: unlock_buffer() only use the bh's address for * hashing after unlocking the buffer, so it doesn't actually touch the bh * itself. */ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { /* This happens, due to failed read-ahead attempts. */ clear_buffer_uptodate(bh); } unlock_buffer(bh); } /* * Default synchronous end-of-IO handler.. Just mark it up-to-date and * unlock the buffer. This is what ll_rw_block uses too. */ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) { put_bh(bh); __end_buffer_read_notouch(bh, uptodate); } EXPORT_SYMBOL(end_buffer_read_sync); void end_buffer_write_sync(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost sync page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } unlock_buffer(bh); put_bh(bh); } EXPORT_SYMBOL(end_buffer_write_sync); /* * Various filesystems appear to want __find_get_block to be non-blocking. * But it's the page lock which protects the buffers. To get around this, * we get exclusion from try_to_free_buffers with the blockdev mapping's * private_lock. * * Hack idea: for the blockdev mapping, private_lock contention * may be quite high. This code could TryLock the page, and if that * succeeds, there is no need to take private_lock. */ static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block) { struct inode *bd_inode = bdev->bd_inode; struct address_space *bd_mapping = bd_inode->i_mapping; struct buffer_head *ret = NULL; pgoff_t index; struct buffer_head *bh; struct buffer_head *head; struct page *page; int all_mapped = 1; static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); if (!page) goto out; spin_lock(&bd_mapping->private_lock); if (!page_has_buffers(page)) goto out_unlock; head = page_buffers(page); bh = head; do { if (!buffer_mapped(bh)) all_mapped = 0; else if (bh->b_blocknr == block) { ret = bh; get_bh(bh); goto out_unlock; } bh = bh->b_this_page; } while (bh != head); /* we might be here because some of the buffers on this page are * not mapped. This is due to various races between * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); if (all_mapped && __ratelimit(&last_warned)) { printk("__find_get_block_slow() failed. block=%llu, " "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " "device %pg blocksize: %d\n", (unsigned long long)block, (unsigned long long)bh->b_blocknr, bh->b_state, bh->b_size, bdev, 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); put_page(page); out: return ret; } static void end_buffer_async_read(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct page *page; int page_uptodate = 1; BUG_ON(!buffer_async_read(bh)); page = bh->b_page; if (uptodate) { set_buffer_uptodate(bh); } else { clear_buffer_uptodate(bh); buffer_io_error(bh, ", async page read"); SetPageError(page); } /* * Be _very_ careful from here on. Bad things can happen if * two buffer heads end IO at almost the same time and both * decide that the page is now completely done. */ first = page_buffers(page); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; do { if (!buffer_uptodate(tmp)) page_uptodate = 0; if (buffer_async_read(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } while (tmp != bh); spin_unlock_irqrestore(&first->b_uptodate_lock, flags); /* * If none of the buffers had errors and they are all * uptodate then we can set the page uptodate. */ if (page_uptodate && !PageError(page)) SetPageUptodate(page); unlock_page(page); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); return; } struct decrypt_bh_ctx { struct work_struct work; struct buffer_head *bh; }; static void decrypt_bh(struct work_struct *work) { struct decrypt_bh_ctx *ctx = container_of(work, struct decrypt_bh_ctx, work); struct buffer_head *bh = ctx->bh; int err; err = fscrypt_decrypt_pagecache_blocks(bh->b_page, bh->b_size, bh_offset(bh)); end_buffer_async_read(bh, err == 0); kfree(ctx); } /* * I/O completion handler for block_read_full_page() - pages * which come unlocked at the end of I/O. */ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { /* Decrypt if needed */ if (uptodate && fscrypt_inode_uses_fs_layer_crypto(bh->b_page->mapping->host)) { struct decrypt_bh_ctx *ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC); if (ctx) { INIT_WORK(&ctx->work, decrypt_bh); ctx->bh = bh; fscrypt_enqueue_decrypt_work(&ctx->work); return; } uptodate = 0; } end_buffer_async_read(bh, uptodate); } /* * Completion handler for block_write_full_page() - pages which are unlocked * during I/O, and which have PageWriteback cleared upon I/O completion. */ void end_buffer_async_write(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct page *page; BUG_ON(!buffer_async_write(bh)); page = bh->b_page; if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); SetPageError(page); } first = page_buffers(page); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_write(bh); unlock_buffer(bh); tmp = bh->b_this_page; while (tmp != bh) { if (buffer_async_write(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } spin_unlock_irqrestore(&first->b_uptodate_lock, flags); end_page_writeback(page); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); return; } EXPORT_SYMBOL(end_buffer_async_write); /* * If a page's buffers are under async readin (end_buffer_async_read * completion) then there is a possibility that another thread of * control could lock one of the buffers after it has completed * but while some of the other buffers have not completed. This * locked buffer would confuse end_buffer_async_read() into not unlocking * the page. So the absence of BH_Async_Read tells end_buffer_async_read() * that this buffer is not under async I/O. * * The page comes unlocked when it has no locked buffer_async buffers * left. * * PageLocked prevents anyone starting new async I/O reads any of * the buffers. * * PageWriteback is used to prevent simultaneous writeout of the same * page. * * PageLocked prevents anyone from starting writeback of a page which is * under read I/O (PageWriteback is only ever set against a locked page). */ static void mark_buffer_async_read(struct buffer_head *bh) { bh->b_end_io = end_buffer_async_read_io; set_buffer_async_read(bh); } static void mark_buffer_async_write_endio(struct buffer_head *bh, bh_end_io_t *handler) { bh->b_end_io = handler; set_buffer_async_write(bh); } void mark_buffer_async_write(struct buffer_head *bh) { mark_buffer_async_write_endio(bh, end_buffer_async_write); } EXPORT_SYMBOL(mark_buffer_async_write); /* * fs/buffer.c contains helper functions for buffer-backed address space's * fsync functions. A common requirement for buffer-based filesystems is * that certain data from the backing blockdev needs to be written out for * a successful fsync(). For example, ext2 indirect blocks need to be * written back and waited upon before fsync() returns. * * The functions mark_buffer_inode_dirty(), fsync_inode_buffers(), * inode_has_buffers() and invalidate_inode_buffers() are provided for the * management of a list of dependent buffers at ->i_mapping->private_list. * * Locking is a little subtle: try_to_free_buffers() will remove buffers * from their controlling inode's queue when they are being freed. But * try_to_free_buffers() will be operating against the *blockdev* mapping * at the time, not against the S_ISREG file which depends on those buffers. * So the locking for private_list is via the private_lock in the address_space * which backs the buffers. Which is different from the address_space * against which the buffers are listed. So for a particular address_space, * mapping->private_lock does *not* protect mapping->private_list! In fact, * mapping->private_list will always be protected by the backing blockdev's * ->private_lock. * * Which introduces a requirement: all buffers on an address_space's * ->private_list must be from the same address_space: the blockdev's. * * address_spaces which do not place buffers at ->private_list via these * utility functions are free to use private_lock and private_list for * whatever they want. The only requirement is that list_empty(private_list) * be true at clear_inode() time. * * FIXME: clear_inode should not call invalidate_inode_buffers(). The * filesystems should do that. invalidate_inode_buffers() should just go * BUG_ON(!list_empty). * * FIXME: mark_buffer_dirty_inode() is a data-plane operation. It should * take an address_space, not an inode. And it should be called * mark_buffer_dirty_fsync() to clearly define why those buffers are being * queued up. * * FIXME: mark_buffer_dirty_inode() doesn't need to add the buffer to the * list if it is already on a list. Because if the buffer is on a list, * it *must* already be on the right one. If not, the filesystem is being * silly. This will save a ton of locking. But first we have to ensure * that buffers are taken *off* the old inode's list when they are freed * (presumably in truncate). That requires careful auditing of all * filesystems (do it inside bforget()). It could also be done by bringing * b_inode back. */ /* * The buffer's backing address_space's private_lock must be held */ static void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_assoc_map); bh->b_assoc_map = NULL; } int inode_has_buffers(struct inode *inode) { return !list_empty(&inode->i_data.private_list); } /* * osync is designed to support O_SYNC io. It waits synchronously for * all already-submitted IO to complete, but does not queue any new * writes to the disk. * * To do O_SYNC writes, just queue the buffer writes with ll_rw_block as * you dirty the buffers, and then use osync_inode_buffers to wait for * completion. Any other dirty buffers which are not yet queued for * write will not be flushed to disk by the osync. */ static int osync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head *p; int err = 0; spin_lock(lock); repeat: list_for_each_prev(p, list) { bh = BH_ENTRY(p); if (buffer_locked(bh)) { get_bh(bh); spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); goto repeat; } } spin_unlock(lock); return err; } void emergency_thaw_bdev(struct super_block *sb) { while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb)) printk(KERN_WARNING "Emergency Thaw on %pg\n", sb->s_bdev); } /** * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers * @mapping: the mapping which wants those buffers written * * Starts I/O against the buffers at mapping->private_list, and waits upon * that I/O. * * Basically, this is a convenience function for fsync(). * @mapping is a file or directory which needs those buffers to be written for * a successful fsync(). */ int sync_mapping_buffers(struct address_space *mapping) { struct address_space *buffer_mapping = mapping->private_data; if (buffer_mapping == NULL || list_empty(&mapping->private_list)) return 0; return fsync_buffers_list(&buffer_mapping->private_lock, &mapping->private_list); } EXPORT_SYMBOL(sync_mapping_buffers); /* * Called when we've recently written block `bblock', and it is known that * `bblock' was for a buffer_boundary() buffer. This means that the block at * `bblock + 1' is probably a dirty indirect block. Hunt it down and, if it's * dirty, schedule it for IO. So that indirects merge nicely with their data. */ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize) { struct buffer_head *bh = __find_get_block(bdev, bblock + 1, blocksize); if (bh) { if (buffer_dirty(bh)) ll_rw_block(REQ_OP_WRITE, 0, 1, &bh); put_bh(bh); } } void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) { struct address_space *mapping = inode->i_mapping; struct address_space *buffer_mapping = bh->b_page->mapping; mark_buffer_dirty(bh); if (!mapping->private_data) { mapping->private_data = buffer_mapping; } else { BUG_ON(mapping->private_data != buffer_mapping); } if (!bh->b_assoc_map) { spin_lock(&buffer_mapping->private_lock); list_move_tail(&bh->b_assoc_buffers, &mapping->private_list); bh->b_assoc_map = mapping; spin_unlock(&buffer_mapping->private_lock); } } EXPORT_SYMBOL(mark_buffer_dirty_inode); /* * Mark the page dirty, and set it dirty in the page cache, and mark the inode * dirty. * * If warn is true, then emit a warning if the page is not uptodate and has * not been truncated. * * The caller must hold lock_page_memcg(). */ void __set_page_dirty(struct page *page, struct address_space *mapping, int warn) { unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); if (page->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !PageUptodate(page)); account_page_dirtied(page, mapping); __xa_set_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); } xa_unlock_irqrestore(&mapping->i_pages, flags); } EXPORT_SYMBOL_GPL(__set_page_dirty); /* * Add a page to the dirty page list. * * It is a sad fact of life that this function is called from several places * deeply under spinlocking. It may not sleep. * * If the page has buffers, the uptodate buffers are set dirty, to preserve * dirty-state coherency between the page and the buffers. It the page does * not have buffers then when they are later attached they will all be set * dirty. * * The buffers are dirtied before the page is dirtied. There's a small race * window in which a writepage caller may see the page cleanness but not the * buffer dirtiness. That's fine. If this code were to set the page dirty * before the buffers, a concurrent writepage caller could clear the page dirty * bit, see a bunch of clean buffers and we'd end up with dirty buffers/clean * page on the dirty page list. * * We use private_lock to lock against try_to_free_buffers while using the * page's buffer list. Also use this to protect against clean buffers being * added to the page after it was set dirty. * * FIXME: may need to call ->reservepage here as well. That's rather up to the * address_space though. */ int __set_page_dirty_buffers(struct page *page) { int newly_dirty; struct address_space *mapping = page_mapping(page); if (unlikely(!mapping)) return !TestSetPageDirty(page); spin_lock(&mapping->private_lock); if (page_has_buffers(page)) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; do { set_buffer_dirty(bh); bh = bh->b_this_page; } while (bh != head); } /* * Lock out page->mem_cgroup migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ lock_page_memcg(page); newly_dirty = !TestSetPageDirty(page); spin_unlock(&mapping->private_lock); if (newly_dirty) __set_page_dirty(page, mapping, 1); unlock_page_memcg(page); if (newly_dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); return newly_dirty; } EXPORT_SYMBOL(__set_page_dirty_buffers); /* * Write out and wait upon a list of buffers. * * We have conflicting pressures: we want to make sure that all * initially dirty buffers get waited on, but that any subsequently * dirtied buffers don't. After all, we don't want fsync to last * forever if somebody is actively writing to the file. * * Do this in two main stages: first we copy dirty buffers to a * temporary inode list, queueing the writes as we go. Then we clean * up, waiting for those writes to complete. * * During this second stage, any subsequent updates to the file may end * up refiling the buffer on the original inode's dirty list again, so * there is a chance we will end up with a buffer queued for write but * not yet completed on that list. So, as a final cleanup we go through * the osync code to catch these locked, dirty buffers without requeuing * any newly dirty buffers for write. */ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) { struct buffer_head *bh; struct list_head tmp; struct address_space *mapping; int err = 0, err2; struct blk_plug plug; INIT_LIST_HEAD(&tmp); blk_start_plug(&plug); spin_lock(lock); while (!list_empty(list)) { bh = BH_ENTRY(list->next); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh) || buffer_locked(bh)) { list_add(&bh->b_assoc_buffers, &tmp); bh->b_assoc_map = mapping; if (buffer_dirty(bh)) { get_bh(bh); spin_unlock(lock); /* * Ensure any pending I/O completes so that * write_dirty_buffer() actually writes the * current contents - it is a noop if I/O is * still in flight on potentially older * contents. */ write_dirty_buffer(bh, REQ_SYNC); /* * Kick off IO for the previous mapping. Note * that we will not run the very last mapping, * wait_on_buffer() will do that for us * through sync_buffer(). */ brelse(bh); spin_lock(lock); } } } spin_unlock(lock); blk_finish_plug(&plug); spin_lock(lock); while (!list_empty(&tmp)) { bh = BH_ENTRY(tmp.prev); get_bh(bh); mapping = bh->b_assoc_map; __remove_assoc_queue(bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh)) { list_add(&bh->b_assoc_buffers, &mapping->private_list); bh->b_assoc_map = mapping; } spin_unlock(lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(lock); } spin_unlock(lock); err2 = osync_buffers_list(lock, list); if (err) return err; else return err2; } /* * Invalidate any and all dirty buffers on a given inode. We are * probably unmounting the fs, but that doesn't mean we have already * done a sync(). Just drop the buffers from the inode list. * * NOTE: we take the inode's blockdev's mapping's private_lock. Which * assumes that all the buffers are against the blockdev. Not true * for reiserfs. */ void invalidate_inode_buffers(struct inode *inode) { if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->private_list; struct address_space *buffer_mapping = mapping->private_data; spin_lock(&buffer_mapping->private_lock); while (!list_empty(list)) __remove_assoc_queue(BH_ENTRY(list->next)); spin_unlock(&buffer_mapping->private_lock); } } EXPORT_SYMBOL(invalidate_inode_buffers); /* * Remove any clean buffers from the inode's buffer list. This is called * when we're trying to free the inode itself. Those buffers can pin it. * * Returns true if all buffers were removed. */ int remove_inode_buffers(struct inode *inode) { int ret = 1; if (inode_has_buffers(inode)) { struct address_space *mapping = &inode->i_data; struct list_head *list = &mapping->private_list; struct address_space *buffer_mapping = mapping->private_data; spin_lock(&buffer_mapping->private_lock); while (!list_empty(list)) { struct buffer_head *bh = BH_ENTRY(list->next); if (buffer_dirty(bh)) { ret = 0; break; } __remove_assoc_queue(bh); } spin_unlock(&buffer_mapping->private_lock); } return ret; } /* * Create the appropriate buffers when given a page for data area and * the size of each buffer.. Use the bh->b_this_page linked list to * follow the buffers created. Return NULL if unable to create more * buffers. * * The retry flag is used to differentiate async IO (paging, swapping) * which may not fail from ordinary buffer allocations. */ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry) { struct buffer_head *bh, *head; gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; long offset; struct mem_cgroup *memcg, *old_memcg; if (retry) gfp |= __GFP_NOFAIL; memcg = get_mem_cgroup_from_page(page); old_memcg = set_active_memcg(memcg); head = NULL; offset = PAGE_SIZE; while ((offset -= size) >= 0) { bh = alloc_buffer_head(gfp); if (!bh) goto no_grow; bh->b_this_page = head; bh->b_blocknr = -1; head = bh; bh->b_size = size; /* Link the buffer to its page */ set_bh_page(bh, page, offset); } out: set_active_memcg(old_memcg); mem_cgroup_put(memcg); return head; /* * In case anything failed, we just free everything we got. */ no_grow: if (head) { do { bh = head; head = head->b_this_page; free_buffer_head(bh); } while (head); } goto out; } EXPORT_SYMBOL_GPL(alloc_page_buffers); static inline void link_dev_buffers(struct page *page, struct buffer_head *head) { struct buffer_head *bh, *tail; bh = head; do { tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; attach_page_private(page, head); } static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) { sector_t retval = ~((sector_t)0); loff_t sz = i_size_read(bdev->bd_inode); if (sz) { unsigned int sizebits = blksize_bits(size); retval = (sz >> sizebits); } return retval; } /* * Initialise the state of a blockdev page's buffers. */ static sector_t init_page_buffers(struct page *page, struct block_device *bdev, sector_t block, int size) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; int uptodate = PageUptodate(page); sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode), size); do { if (!buffer_mapped(bh)) { bh->b_end_io = NULL; bh->b_private = NULL; bh->b_bdev = bdev; bh->b_blocknr = block; if (uptodate) set_buffer_uptodate(bh); if (block < end_block) set_buffer_mapped(bh); } block++; bh = bh->b_this_page; } while (bh != head); /* * Caller needs to validate requested block against end of device. */ return end_block; } /* * Create the page-cache page that contains the requested block. * * This is used purely for blockdev mappings. */ static int grow_dev_page(struct block_device *bdev, sector_t block, pgoff_t index, int size, int sizebits, gfp_t gfp) { struct inode *inode = bdev->bd_inode; struct page *page; struct buffer_head *bh; sector_t end_block; int ret = 0; gfp_t gfp_mask; gfp_mask = mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS) | gfp; /* * XXX: __getblk_slow() can not really deal with failure and * will endlessly loop on improvised global reclaim. Prefer * looping in the allocator rather than here, at least that * code knows what it's doing. */ gfp_mask |= __GFP_NOFAIL; page = find_or_create_page(inode->i_mapping, index, gfp_mask); BUG_ON(!PageLocked(page)); if (page_has_buffers(page)) { bh = page_buffers(page); if (bh->b_size == size) { end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, size); goto done; } if (!try_to_free_buffers(page)) goto failed; } /* * Allocate some buffers for this page */ bh = alloc_page_buffers(page, size, true); /* * Link the page to the buffers and initialise them. Take the * lock to be atomic wrt __find_get_block(), which does not * run under the page lock. */ spin_lock(&inode->i_mapping->private_lock); link_dev_buffers(page, bh); end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, size); spin_unlock(&inode->i_mapping->private_lock); done: ret = (block < end_block) ? 1 : -ENXIO; failed: unlock_page(page); put_page(page); return ret; } /* * Create buffers for the specified block device block's page. If * that page was dirty, the buffers are set dirty also. */ static int grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp) { pgoff_t index; int sizebits; sizebits = -1; do { sizebits++; } while ((size << sizebits) < PAGE_SIZE); index = block >> sizebits; /* * Check for a block which wants to lie outside our maximum possible * pagecache index. (this comparison is done using sector_t types). */ if (unlikely(index != block >> sizebits)) { printk(KERN_ERR "%s: requested out-of-range block %llu for " "device %pg\n", __func__, (unsigned long long)block, bdev); return -EIO; } /* Create a page with the proper size buffers.. */ return grow_dev_page(bdev, block, index, size, sizebits, gfp); } static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { printk(KERN_ERR "getblk(): invalid block size %d requested\n", size); printk(KERN_ERR "logical block size: %d\n", bdev_logical_block_size(bdev)); dump_stack(); return NULL; } for (;;) { struct buffer_head *bh; int ret; bh = __find_get_block(bdev, block, size); if (bh) return bh; ret = grow_buffers(bdev, block, size, gfp); if (ret < 0) return NULL; } } /* * The relationship between dirty buffers and dirty pages: * * Whenever a page has any dirty buffers, the page's dirty bit is set, and * the page is tagged dirty in the page cache. * * At all times, the dirtiness of the buffers represents the dirtiness of * subsections of the page. If the page has buffers, the page dirty bit is * merely a hint about the true dirty state. * * When a page is set dirty in its entirety, all its buffers are marked dirty * (if the page has buffers). * * When a buffer is marked dirty, its page is dirtied, but the page's other * buffers are not. * * Also. When blockdev buffers are explicitly read with bread(), they * individually become uptodate. But their backing page remains not * uptodate - even if all of its buffers are uptodate. A subsequent * block_read_full_page() against that page will discover all the uptodate * buffers, will set the page uptodate and will perform no I/O. */ /** * mark_buffer_dirty - mark a buffer_head as needing writeout * @bh: the buffer_head to mark dirty * * mark_buffer_dirty() will set the dirty bit against the buffer, then set * its backing page dirty, then tag the page as dirty in the page cache * and then attach the address_space's inode to its superblock's dirty * inode list. * * mark_buffer_dirty() is atomic. It takes bh->b_page->mapping->private_lock, * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { WARN_ON_ONCE(!buffer_uptodate(bh)); trace_block_dirty_buffer(bh); /* * Very *carefully* optimize the it-is-already-dirty case. * * Don't let the final "is it dirty" escape to before we * perhaps modified the buffer. */ if (buffer_dirty(bh)) { smp_mb(); if (buffer_dirty(bh)) return; } if (!test_set_buffer_dirty(bh)) { struct page *page = bh->b_page; struct address_space *mapping = NULL; lock_page_memcg(page); if (!TestSetPageDirty(page)) { mapping = page_mapping(page); if (mapping) __set_page_dirty(page, mapping, 0); } unlock_page_memcg(page); if (mapping) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } } EXPORT_SYMBOL(mark_buffer_dirty); void mark_buffer_write_io_error(struct buffer_head *bh) { struct super_block *sb; set_buffer_write_io_error(bh); /* FIXME: do we need to set this in both places? */ if (bh->b_page && bh->b_page->mapping) mapping_set_error(bh->b_page->mapping, -EIO); if (bh->b_assoc_map) mapping_set_error(bh->b_assoc_map, -EIO); rcu_read_lock(); sb = READ_ONCE(bh->b_bdev->bd_super); if (sb) errseq_set(&sb->s_wb_err, -EIO); rcu_read_unlock(); } EXPORT_SYMBOL(mark_buffer_write_io_error); /* * Decrement a buffer_head's reference count. If all buffers against a page * have zero reference count, are clean and unlocked, and if the page is clean * and unlocked then try_to_free_buffers() may strip the buffers from the page * in preparation for freeing it (sometimes, rarely, buffers are removed from * a page but it ends up not being freed, and buffers may later be reattached). */ void __brelse(struct buffer_head * buf) { if (atomic_read(&buf->b_count)) { put_bh(buf); return; } WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n"); } EXPORT_SYMBOL(__brelse); /* * bforget() is like brelse(), except it discards any * potentially dirty data. */ void __bforget(struct buffer_head *bh) { clear_buffer_dirty(bh); if (bh->b_assoc_map) { struct address_space *buffer_mapping = bh->b_page->mapping; spin_lock(&buffer_mapping->private_lock); list_del_init(&bh->b_assoc_buffers); bh->b_assoc_map = NULL; spin_unlock(&buffer_mapping->private_lock); } __brelse(bh); } EXPORT_SYMBOL(__bforget); static struct buffer_head *__bread_slow(struct buffer_head *bh) { lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); return bh; } else { get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, 0, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; } brelse(bh); return NULL; } /* * Per-cpu buffer LRU implementation. To reduce the cost of __find_get_block(). * The bhs[] array is sorted - newest buffer is at bhs[0]. Buffers have their * refcount elevated by one when they're in an LRU. A buffer can only appear * once in a particular CPU's LRU. A single buffer can be present in multiple * CPU's LRUs at the same time. * * This is a transparent caching front-end to sb_bread(), sb_getblk() and * sb_find_get_block(). * * The LRUs themselves only need locking against invalidate_bh_lrus. We use * a local interrupt disable for that. */ #define BH_LRU_SIZE 16 struct bh_lru { struct buffer_head *bhs[BH_LRU_SIZE]; }; static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }}; #ifdef CONFIG_SMP #define bh_lru_lock() local_irq_disable() #define bh_lru_unlock() local_irq_enable() #else #define bh_lru_lock() preempt_disable() #define bh_lru_unlock() preempt_enable() #endif static inline void check_irqs_on(void) { #ifdef irqs_disabled BUG_ON(irqs_disabled()); #endif } /* * Install a buffer_head into this cpu's LRU. If not already in the LRU, it is * inserted at the front, and the buffer_head at the back if any is evicted. * Or, if already in the LRU it is moved to the front. */ static void bh_lru_install(struct buffer_head *bh) { struct buffer_head *evictee = bh; struct bh_lru *b; int i; check_irqs_on(); bh_lru_lock(); b = this_cpu_ptr(&bh_lrus); for (i = 0; i < BH_LRU_SIZE; i++) { swap(evictee, b->bhs[i]); if (evictee == bh) { bh_lru_unlock(); return; } } get_bh(bh); bh_lru_unlock(); brelse(evictee); } /* * Look up the bh in this cpu's LRU. If it's there, move it to the head. */ static struct buffer_head * lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *ret = NULL; unsigned int i; check_irqs_on(); bh_lru_lock(); for (i = 0; i < BH_LRU_SIZE; i++) { struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]); if (bh && bh->b_blocknr == block && bh->b_bdev == bdev && bh->b_size == size) { if (i) { while (i) { __this_cpu_write(bh_lrus.bhs[i], __this_cpu_read(bh_lrus.bhs[i - 1])); i--; } __this_cpu_write(bh_lrus.bhs[0], bh); } get_bh(bh); ret = bh; break; } } bh_lru_unlock(); return ret; } /* * Perform a pagecache lookup for the matching buffer. If it's there, refresh * it in the LRU and mark it as accessed. If it is not present then return * NULL */ struct buffer_head * __find_get_block(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); } else touch_buffer(bh); return bh; } EXPORT_SYMBOL(__find_get_block); /* * __getblk_gfp() will locate (and, if necessary, create) the buffer_head * which corresponds to the passed block_device, block and size. The * returned buffer has its reference count incremented. * * __getblk_gfp() will lock up the machine if grow_dev_page's * try_to_free_buffers() attempt is failing. FIXME, perhaps? */ struct buffer_head * __getblk_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __find_get_block(bdev, block, size); might_sleep(); if (bh == NULL) bh = __getblk_slow(bdev, block, size, gfp); return bh; } EXPORT_SYMBOL(__getblk_gfp); /* * Do async read-ahead on a buffer.. */ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = __getblk(bdev, block, size); if (likely(bh)) { ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh); brelse(bh); } } EXPORT_SYMBOL(__breadahead); void __breadahead_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp); if (likely(bh)) { ll_rw_block(REQ_OP_READ, REQ_RAHEAD, 1, &bh); brelse(bh); } } EXPORT_SYMBOL(__breadahead_gfp); /** * __bread_gfp() - reads a specified block and returns the bh * @bdev: the block_device to read from * @block: number of block * @size: size (in bytes) to read * @gfp: page allocation flag * * Reads a specified block, and returns buffer head that contains it. * The page cache can be allocated from non-movable area * not to prevent page migration if you set gfp to zero. * It returns NULL if the block was unreadable. */ struct buffer_head * __bread_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp); if (likely(bh) && !buffer_uptodate(bh)) bh = __bread_slow(bh); return bh; } EXPORT_SYMBOL(__bread_gfp); /* * invalidate_bh_lrus() is called rarely - but not only at unmount. * This doesn't race because it runs in each cpu either in irq * or with preempt disabled. */ static void invalidate_bh_lru(void *arg) { struct bh_lru *b = &get_cpu_var(bh_lrus); int i; for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } put_cpu_var(bh_lrus); } static bool has_bh_in_lru(int cpu, void *dummy) { struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu); int i; for (i = 0; i < BH_LRU_SIZE; i++) { if (b->bhs[i]) return true; } return false; } void invalidate_bh_lrus(void) { on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1); } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset) { bh->b_page = page; BUG_ON(offset >= PAGE_SIZE); if (PageHighMem(page)) /* * This catches illegal uses and preserves the offset: */ bh->b_data = (char *)(0 + offset); else bh->b_data = page_address(page) + offset; } EXPORT_SYMBOL(set_bh_page); /* * Called when truncating a buffer on a page completely. */ /* Bits that are cleared during an invalidate */ #define BUFFER_FLAGS_DISCARD \ (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ 1 << BH_Delay | 1 << BH_Unwritten) static void discard_buffer(struct buffer_head * bh) { unsigned long b_state, b_state_old; lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; b_state = bh->b_state; for (;;) { b_state_old = cmpxchg(&bh->b_state, b_state, (b_state & ~BUFFER_FLAGS_DISCARD)); if (b_state_old == b_state) break; b_state = b_state_old; } unlock_buffer(bh); } /** * block_invalidatepage - invalidate part or all of a buffer-backed page * * @page: the page which is affected * @offset: start of the range to invalidate * @length: length of the range to invalidate * * block_invalidatepage() is called when all or part of the page has become * invalidated by a truncate operation. * * block_invalidatepage() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void block_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { struct buffer_head *head, *bh, *next; unsigned int curr_off = 0; unsigned int stop = length + offset; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) goto out; /* * Check for overflow */ BUG_ON(stop > PAGE_SIZE || stop < length); head = page_buffers(page); bh = head; do { unsigned int next_off = curr_off + bh->b_size; next = bh->b_this_page; /* * Are we still fully in range ? */ if (next_off > stop) goto out; /* * is this block fully invalidated? */ if (offset <= curr_off) discard_buffer(bh); curr_off = next_off; bh = next; } while (bh != head); /* * We release buffers only if the entire page is being invalidated. * The get_block cached value has been unconditionally invalidated, * so real IO is not possible anymore. */ if (length == PAGE_SIZE) try_to_release_page(page, 0); out: return; } EXPORT_SYMBOL(block_invalidatepage); /* * We attach and possibly dirty the buffers atomically wrt * __set_page_dirty_buffers() via private_lock. try_to_free_buffers * is already excluded via the page lock. */ void create_empty_buffers(struct page *page, unsigned long blocksize, unsigned long b_state) { struct buffer_head *bh, *head, *tail; head = alloc_page_buffers(page, blocksize, true); bh = head; do { bh->b_state |= b_state; tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; spin_lock(&page->mapping->private_lock); if (PageUptodate(page) || PageDirty(page)) { bh = head; do { if (PageDirty(page)) set_buffer_dirty(bh); if (PageUptodate(page)) set_buffer_uptodate(bh); bh = bh->b_this_page; } while (bh != head); } attach_page_private(page, head); spin_unlock(&page->mapping->private_lock); } EXPORT_SYMBOL(create_empty_buffers); /** * clean_bdev_aliases: clean a range of buffers in block device * @bdev: Block device to clean buffers in * @block: Start of a range of blocks to clean * @len: Number of blocks to clean * * We are taking a range of blocks for data and we don't want writeback of any * buffer-cache aliases starting from return from this function and until the * moment when something will explicitly mark the buffer dirty (hopefully that * will not happen until we will free that block ;-) We don't even need to mark * it not-uptodate - nobody can expect anything from a newly allocated buffer * anyway. We used to use unmap_buffer() for such invalidation, but that was * wrong. We definitely don't want to mark the alias unmapped, for example - it * would confuse anyone who might pick it with bread() afterwards... * * Also.. Note that bforget() doesn't lock the buffer. So there can be * writeout I/O going on against recently-freed buffers. We don't wait on that * I/O in bforget() - it's more efficient to wait on the I/O only if we really * need to. That happens here. */ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) { struct inode *bd_inode = bdev->bd_inode; struct address_space *bd_mapping = bd_inode->i_mapping; struct pagevec pvec; pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); pgoff_t end; int i, count; struct buffer_head *bh; struct buffer_head *head; end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits); pagevec_init(&pvec); while (pagevec_lookup_range(&pvec, bd_mapping, &index, end)) { count = pagevec_count(&pvec); for (i = 0; i < count; i++) { struct page *page = pvec.pages[i]; if (!page_has_buffers(page)) continue; /* * We use page lock instead of bd_mapping->private_lock * to pin buffers here since we can afford to sleep and * it scales better than a global spinlock lock. */ lock_page(page); /* Recheck when the page is locked which pins bhs */ if (!page_has_buffers(page)) goto unlock_page; head = page_buffers(page); bh = head; do { if (!buffer_mapped(bh) || (bh->b_blocknr < block)) goto next; if (bh->b_blocknr >= block + len) break; clear_buffer_dirty(bh); wait_on_buffer(bh); clear_buffer_req(bh); next: bh = bh->b_this_page; } while (bh != head); unlock_page: unlock_page(page); } pagevec_release(&pvec); cond_resched(); /* End of range already reached? */ if (index > end || !index) break; } } EXPORT_SYMBOL(clean_bdev_aliases); /* * Size is a power-of-two in the range 512..PAGE_SIZE, * and the case we care about most is PAGE_SIZE. * * So this *could* possibly be written with those * constraints in mind (relevant mostly if some * architecture has a slow bit-scan instruction) */ static inline int block_size_bits(unsigned int blocksize) { return ilog2(blocksize); } static struct buffer_head *create_page_buffers(struct page *page, struct inode *inode, unsigned int b_state) { BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) create_empty_buffers(page, 1 << READ_ONCE(inode->i_blkbits), b_state); return page_buffers(page); } /* * NOTE! All mapped/uptodate combinations are valid: * * Mapped Uptodate Meaning * * No No "unknown" - must do get_block() * No Yes "hole" - zero-filled * Yes No "allocated" - allocated on disk, not read in * Yes Yes "valid" - allocated and up-to-date in memory. * * "Dirty" is valid only with the last case (mapped+uptodate). */ /* * While block_write_full_page is writing back the dirty buffers under * the page lock, whoever dirtied the buffers may decide to clean them * again at any time. We handle that by only looking at the buffer * state inside lock_buffer(). * * If block_write_full_page() is called for regular writeback * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a * locked buffer. This only can happen if someone has written the buffer * directly, with submit_bh(). At the address_space level PageWriteback * prevents this contention from occurring. * * If block_write_full_page() is called with wbc->sync_mode == * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this * causes the writes to be flagged as synchronous writes. */ int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, bh_end_io_t *handler) { int err; sector_t block; sector_t last_block; struct buffer_head *bh, *head; unsigned int blocksize, bbits; int nr_underway = 0; int write_flags = wbc_to_write_flags(wbc); head = create_page_buffers(page, inode, (1 << BH_Dirty)|(1 << BH_Uptodate)); /* * Be very careful. We have no exclusion from __set_page_dirty_buffers * here, and the (potentially unmapped) buffers may become dirty at * any time. If a buffer becomes dirty here after we've inspected it * then we just miss that fact, and the page stays dirty. * * Buffers outside i_size may be dirtied by __set_page_dirty_buffers; * handle that here by just cleaning them. */ bh = head; blocksize = bh->b_size; bbits = block_size_bits(blocksize); block = (sector_t)page->index << (PAGE_SHIFT - bbits); last_block = (i_size_read(inode) - 1) >> bbits; /* * Get all the dirty buffers mapped to disk addresses and * handle any aliases from the underlying blockdev's mapping. */ do { if (block > last_block) { /* * mapped buffers outside i_size will occur, because * this page can be outside i_size when there is a * truncate in progress. */ /* * The buffer was zeroed by block_write_full_page() */ clear_buffer_dirty(bh); set_buffer_uptodate(bh); } else if ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, block, bh, 1); if (err) goto recover; clear_buffer_delay(bh); if (buffer_new(bh)) { /* blockdev mappings never come here */ clear_buffer_new(bh); clean_bdev_bh_alias(bh); } } bh = bh->b_this_page; block++; } while (bh != head); do { if (!buffer_mapped(bh)) continue; /* * If it's a fully non-blocking write attempt and we cannot * lock the buffer then redirty the page. Note that this can * potentially cause a busy-wait loop from writeback threads * and kswapd activity, but those code paths have their own * higher-level throttling. */ if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { redirty_page_for_writepage(wbc, page); continue; } if (test_clear_buffer_dirty(bh)) { mark_buffer_async_write_endio(bh, handler); } else { unlock_buffer(bh); } } while ((bh = bh->b_this_page) != head); /* * The page and its buffers are protected by PageWriteback(), so we can * drop the bh refcounts early. */ BUG_ON(PageWriteback(page)); set_page_writeback(page); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); unlock_page(page); err = 0; done: if (nr_underway == 0) { /* * The page was marked dirty, but the buffers were * clean. Someone wrote them back by hand with * ll_rw_block/submit_bh. A rare case. */ end_page_writeback(page); /* * The page and buffer_heads can be released at any time from * here on. */ } return err; recover: /* * ENOSPC, or some other error. We may already have added some * blocks to the file, so we need to write these out to avoid * exposing stale data. * The page is currently locked and not marked for writeback */ bh = head; /* Recovery: lock and submit the mapped buffers */ do { if (buffer_mapped(bh) && buffer_dirty(bh) && !buffer_delay(bh)) { lock_buffer(bh); mark_buffer_async_write_endio(bh, handler); } else { /* * The buffer may have been set dirty during * attachment to a dirty page. */ clear_buffer_dirty(bh); } } while ((bh = bh->b_this_page) != head); SetPageError(page); BUG_ON(PageWriteback(page)); mapping_set_error(page->mapping, err); set_page_writeback(page); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); unlock_page(page); goto done; } EXPORT_SYMBOL(__block_write_full_page); /* * If a page has any new buffers, zero them out here, and mark them uptodate * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ void page_zero_new_buffers(struct page *page, unsigned from, unsigned to) { unsigned int block_start, block_end; struct buffer_head *head, *bh; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) return; bh = head = page_buffers(page); block_start = 0; do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { if (!PageUptodate(page)) { unsigned start, size; start = max(from, block_start); size = min(to, block_end) - start; zero_user(page, start, size); set_buffer_uptodate(bh); } clear_buffer_new(bh); mark_buffer_dirty(bh); } } block_start = block_end; bh = bh->b_this_page; } while (bh != head); } EXPORT_SYMBOL(page_zero_new_buffers); static void iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, struct iomap *iomap) { loff_t offset = block << inode->i_blkbits; bh->b_bdev = iomap->bdev; /* * Block points to offset in file we need to map, iomap contains * the offset at which the map starts. If the map ends before the * current block, then do not map the buffer and let the caller * handle it. */ BUG_ON(offset >= iomap->offset + iomap->length); switch (iomap->type) { case IOMAP_HOLE: /* * If the buffer is not up to date or beyond the current EOF, * we need to mark it as new to ensure sub-block zeroing is * executed if necessary. */ if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); break; case IOMAP_DELALLOC: if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); set_buffer_uptodate(bh); set_buffer_mapped(bh); set_buffer_delay(bh); break; case IOMAP_UNWRITTEN: /* * For unwritten regions, we always need to ensure that regions * in the block we are not writing to are zeroed. Mark the * buffer as new to ensure this. */ set_buffer_new(bh); set_buffer_unwritten(bh); fallthrough; case IOMAP_MAPPED: if ((iomap->flags & IOMAP_F_NEW) || offset >= i_size_read(inode)) set_buffer_new(bh); bh->b_blocknr = (iomap->addr + offset - iomap->offset) >> inode->i_blkbits; set_buffer_mapped(bh); break; } } int __block_write_begin_int(struct page *page, loff_t pos, unsigned len, get_block_t *get_block, struct iomap *iomap) { unsigned from = pos & (PAGE_SIZE - 1); unsigned to = from + len; struct inode *inode = page->mapping->host; unsigned block_start, block_end; sector_t block; int err = 0; unsigned blocksize, bbits; struct buffer_head *bh, *head, *wait[2], **wait_bh=wait; BUG_ON(!PageLocked(page)); BUG_ON(from > PAGE_SIZE); BUG_ON(to > PAGE_SIZE); BUG_ON(from > to); head = create_page_buffers(page, inode, 0); blocksize = head->b_size; bbits = block_size_bits(blocksize); block = (sector_t)page->index << (PAGE_SHIFT - bbits); for(bh = head, block_start = 0; bh != head || !block_start; block++, block_start=block_end, bh = bh->b_this_page) { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (PageUptodate(page)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } continue; } if (buffer_new(bh)) clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); if (get_block) { err = get_block(inode, block, bh, 1); if (err) break; } else { iomap_to_bh(inode, block, bh, iomap); } if (buffer_new(bh)) { clean_bdev_bh_alias(bh); if (PageUptodate(page)) { clear_buffer_new(bh); set_buffer_uptodate(bh); mark_buffer_dirty(bh); continue; } if (block_end > to || block_start < from) zero_user_segments(page, to, block_end, block_start, from); continue; } } if (PageUptodate(page)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); continue; } if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh) && (block_start < from || block_end > to)) { ll_rw_block(REQ_OP_READ, 0, 1, &bh); *wait_bh++=bh; } } /* * If we issued read requests - let them complete. */ while(wait_bh > wait) { wait_on_buffer(*--wait_bh); if (!buffer_uptodate(*wait_bh)) err = -EIO; } if (unlikely(err)) page_zero_new_buffers(page, from, to); return err; } int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) { return __block_write_begin_int(page, pos, len, get_block, NULL); } EXPORT_SYMBOL(__block_write_begin); static int __block_commit_write(struct inode *inode, struct page *page, unsigned from, unsigned to) { unsigned block_start, block_end; int partial = 0; unsigned blocksize; struct buffer_head *bh, *head; bh = head = page_buffers(page); blocksize = bh->b_size; block_start = 0; do { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) partial = 1; } else { set_buffer_uptodate(bh); mark_buffer_dirty(bh); } clear_buffer_new(bh); block_start = block_end; bh = bh->b_this_page; } while (bh != head); /* * If this is a partial write which happened to make all buffers * uptodate then we can optimize away a bogus readpage() for * the next read(). Here we 'discover' whether the page went * uptodate as a result of this (potentially partial) write. */ if (!partial) SetPageUptodate(page); return 0; } /* * block_write_begin takes care of the basic task of block allocation and * bringing partial write blocks uptodate first. * * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, get_block_t *get_block) { pgoff_t index = pos >> PAGE_SHIFT; struct page *page; int status; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; status = __block_write_begin(page, pos, len, get_block); if (unlikely(status)) { unlock_page(page); put_page(page); page = NULL; } *pagep = page; return status; } EXPORT_SYMBOL(block_write_begin); int block_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; unsigned start; start = pos & (PAGE_SIZE - 1); if (unlikely(copied < len)) { /* * The buffers that were written will now be uptodate, so we * don't have to worry about a readpage reading them and * overwriting a partial write. However if we have encountered * a short write and only partially written into a buffer, it * will not be marked uptodate, so a readpage might come in and * destroy our partial write. * * Do the simplest thing, and just treat any short write to a * non uptodate page as a zero-length write, and force the * caller to redo the whole thing. */ if (!PageUptodate(page)) copied = 0; page_zero_new_buffers(page, start+copied, start+len); } flush_dcache_page(page); /* This could be a short (even 0-length) commit */ __block_commit_write(inode, page, start, start+copied); return copied; } EXPORT_SYMBOL(block_write_end); int generic_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; loff_t old_size = inode->i_size; bool i_size_changed = false; copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); /* * No need to use i_size_read() here, the i_size cannot change under us * because we hold i_rwsem. * * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ if (pos + copied > inode->i_size) { i_size_write(inode, pos + copied); i_size_changed = true; } unlock_page(page); put_page(page); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock * ordering of page lock and transaction start for journaling * filesystems. */ if (i_size_changed) mark_inode_dirty(inode); return copied; } EXPORT_SYMBOL(generic_write_end); /* * block_is_partially_uptodate checks whether buffers within a page are * uptodate or not. * * Returns true if all buffers which correspond to a file portion * we want to read are uptodate. */ int block_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count) { unsigned block_start, block_end, blocksize; unsigned to; struct buffer_head *bh, *head; int ret = 1; if (!page_has_buffers(page)) return 0; head = page_buffers(page); blocksize = head->b_size; to = min_t(unsigned, PAGE_SIZE - from, count); to = from + to; if (from < blocksize && to > PAGE_SIZE - blocksize) return 0; bh = head; block_start = 0; do { block_end = block_start + blocksize; if (block_end > from && block_start < to) { if (!buffer_uptodate(bh)) { ret = 0; break; } if (block_end >= to) break; } block_start = block_end; bh = bh->b_this_page; } while (bh != head); return ret; } EXPORT_SYMBOL(block_is_partially_uptodate); /* * Generic "read page" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. * Reads the page asynchronously --- the unlock_buffer() and * set/clear_buffer_uptodate() functions propagate buffer state into the * page struct once IO has completed. */ int block_read_full_page(struct page *page, get_block_t *get_block) { struct inode *inode = page->mapping->host; sector_t iblock, lblock; struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE]; unsigned int blocksize, bbits; int nr, i; int fully_mapped = 1; head = create_page_buffers(page, inode, 0); blocksize = head->b_size; bbits = block_size_bits(blocksize); iblock = (sector_t)page->index << (PAGE_SHIFT - bbits); lblock = (i_size_read(inode)+blocksize-1) >> bbits; bh = head; nr = 0; i = 0; do { if (buffer_uptodate(bh)) continue; if (!buffer_mapped(bh)) { int err = 0; fully_mapped = 0; if (iblock < lblock) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) SetPageError(page); } if (!buffer_mapped(bh)) { zero_user(page, i * blocksize, blocksize); if (!err) set_buffer_uptodate(bh); continue; } /* * get_block() might have updated the buffer * synchronously */ if (buffer_uptodate(bh)) continue; } arr[nr++] = bh; } while (i++, iblock++, (bh = bh->b_this_page) != head); if (fully_mapped) SetPageMappedToDisk(page); if (!nr) { /* * All buffers are uptodate - we can set the page uptodate * as well. But not if get_block() returned an error. */ if (!PageError(page)) SetPageUptodate(page); unlock_page(page); return 0; } /* Stage two: lock the buffers */ for (i = 0; i < nr; i++) { bh = arr[i]; lock_buffer(bh); mark_buffer_async_read(bh); } /* * Stage 3: start the IO. Check for uptodateness * inside the buffer lock in case another process reading * the underlying blockdev brought it uptodate (the sct fix). */ for (i = 0; i < nr; i++) { bh = arr[i]; if (buffer_uptodate(bh)) end_buffer_async_read(bh, 1); else submit_bh(REQ_OP_READ, 0, bh); } return 0; } EXPORT_SYMBOL(block_read_full_page); /* utility function for filesystems that need to do work on expanding * truncates. Uses filesystem pagecache writes to allow the filesystem to * deal with the hole. */ int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; struct page *page; void *fsdata = NULL; int err; err = inode_newsize_ok(inode, size); if (err) goto out; err = pagecache_write_begin(NULL, mapping, size, 0, AOP_FLAG_CONT_EXPAND, &page, &fsdata); if (err) goto out; err = pagecache_write_end(NULL, mapping, size, 0, 0, page, fsdata); BUG_ON(err > 0); out: return err; } EXPORT_SYMBOL(generic_cont_expand_simple); static int cont_expand_zero(struct file *file, struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); struct page *page; void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; unsigned zerofrom, offset, len; int err = 0; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) { zerofrom = curpos & ~PAGE_MASK; if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = PAGE_SIZE - zerofrom; err = pagecache_write_begin(file, mapping, curpos, len, 0, &page, &fsdata); if (err) goto out; zero_user(page, zerofrom, len); err = pagecache_write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; balance_dirty_pages_ratelimited(mapping); if (fatal_signal_pending(current)) { err = -EINTR; goto out; } } /* page covers the boundary, find the boundary offset */ if (index == curidx) { zerofrom = curpos & ~PAGE_MASK; /* if we will expand the thing last block will be filled */ if (offset <= zerofrom) { goto out; } if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = offset - zerofrom; err = pagecache_write_begin(file, mapping, curpos, len, 0, &page, &fsdata); if (err) goto out; zero_user(page, zerofrom, len); err = pagecache_write_end(file, mapping, curpos, len, len, page, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; } out: return err; } /* * For moronic filesystems that do not allow holes in file. * We may have to extend the file. */ int cont_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); unsigned int zerofrom; int err; err = cont_expand_zero(file, mapping, pos, bytes); if (err) return err; zerofrom = *bytes & ~PAGE_MASK; if (pos+len > *bytes && zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } return block_write_begin(mapping, pos, len, flags, pagep, get_block); } EXPORT_SYMBOL(cont_write_begin); int block_commit_write(struct page *page, unsigned from, unsigned to) { struct inode *inode = page->mapping->host; __block_commit_write(inode,page,from,to); return 0; } EXPORT_SYMBOL(block_commit_write); /* * block_page_mkwrite() is not allowed to change the file size as it gets * called from a page fault handler when a page is first dirtied. Hence we must * be careful to check for EOF conditions here. We set the page up correctly * for a written page which means we get ENOSPC checking when writing into * holes and correct delalloc and unwritten extent mapping on filesystems that * support these features. * * We are not allowed to take the i_mutex here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because * truncate writes the inode size before removing pages, once we have the * page lock we can determine safely if the page is beyond EOF. If it is not * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. * * Direct callers of this function should protect against filesystem freezing * using sb_start_pagefault() - sb_end_pagefault() functions. */ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) { struct page *page = vmf->page; struct inode *inode = file_inode(vma->vm_file); unsigned long end; loff_t size; int ret; lock_page(page); size = i_size_read(inode); if ((page->mapping != inode->i_mapping) || (page_offset(page) > size)) { /* We overload EFAULT to mean page got truncated */ ret = -EFAULT; goto out_unlock; } /* page is wholly or partially inside EOF */ if (((page->index + 1) << PAGE_SHIFT) > size) end = size & ~PAGE_MASK; else end = PAGE_SIZE; ret = __block_write_begin(page, 0, end, get_block); if (!ret) ret = block_commit_write(page, 0, end); if (unlikely(ret < 0)) goto out_unlock; set_page_dirty(page); wait_for_stable_page(page); return 0; out_unlock: unlock_page(page); return ret; } EXPORT_SYMBOL(block_page_mkwrite); /* * nobh_write_begin()'s prereads are special: the buffer_heads are freed * immediately, while under the page lock. So it needs a special end_io * handler which does not touch the bh after unlocking it. */ static void end_buffer_read_nobh(struct buffer_head *bh, int uptodate) { __end_buffer_read_notouch(bh, uptodate); } /* * Attach the singly-linked list of buffers created by nobh_write_begin, to * the page (converting it to circular linked list and taking care of page * dirty races). */ static void attach_nobh_buffers(struct page *page, struct buffer_head *head) { struct buffer_head *bh; BUG_ON(!PageLocked(page)); spin_lock(&page->mapping->private_lock); bh = head; do { if (PageDirty(page)) set_buffer_dirty(bh); if (!bh->b_this_page) bh->b_this_page = head; bh = bh->b_this_page; } while (bh != head); attach_page_private(page, head); spin_unlock(&page->mapping->private_lock); } /* * On entry, the page is fully not uptodate. * On exit the page is fully uptodate in the areas outside (from,to) * The filesystem needs to handle block truncation upon failure. */ int nobh_write_begin(struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, get_block_t *get_block) { struct inode *inode = mapping->host; const unsigned blkbits = inode->i_blkbits; const unsigned blocksize = 1 << blkbits; struct buffer_head *head, *bh; struct page *page; pgoff_t index; unsigned from, to; unsigned block_in_page; unsigned block_start, block_end; sector_t block_in_file; int nr_reads = 0; int ret = 0; int is_mapped_to_disk = 1; index = pos >> PAGE_SHIFT; from = pos & (PAGE_SIZE - 1); to = from + len; page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; *pagep = page; *fsdata = NULL; if (page_has_buffers(page)) { ret = __block_write_begin(page, pos, len, get_block); if (unlikely(ret)) goto out_release; return ret; } if (PageMappedToDisk(page)) return 0; /* * Allocate buffers so that we can keep track of state, and potentially * attach them to the page if an error occurs. In the common case of * no error, they will just be freed again without ever being attached * to the page (which is all OK, because we're under the page lock). * * Be careful: the buffer linked list is a NULL terminated one, rather * than the circular one we're used to. */ head = alloc_page_buffers(page, blocksize, false); if (!head) { ret = -ENOMEM; goto out_release; } block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits); /* * We loop across all blocks in the page, whether or not they are * part of the affected region. This is so we can discover if the * page is fully mapped-to-disk. */ for (block_start = 0, block_in_page = 0, bh = head; block_start < PAGE_SIZE; block_in_page++, block_start += blocksize, bh = bh->b_this_page) { int create; block_end = block_start + blocksize; bh->b_state = 0; create = 1; if (block_start >= to) create = 0; ret = get_block(inode, block_in_file + block_in_page, bh, create); if (ret) goto failed; if (!buffer_mapped(bh)) is_mapped_to_disk = 0; if (buffer_new(bh)) clean_bdev_bh_alias(bh); if (PageUptodate(page)) { set_buffer_uptodate(bh); continue; } if (buffer_new(bh) || !buffer_mapped(bh)) { zero_user_segments(page, block_start, from, to, block_end); continue; } if (buffer_uptodate(bh)) continue; /* reiserfs does this */ if (block_start < from || block_end > to) { lock_buffer(bh); bh->b_end_io = end_buffer_read_nobh; submit_bh(REQ_OP_READ, 0, bh); nr_reads++; } } if (nr_reads) { /* * The page is locked, so these buffers are protected from * any VM or truncate activity. Hence we don't need to care * for the buffer_head refcounts. */ for (bh = head; bh; bh = bh->b_this_page) { wait_on_buffer(bh); if (!buffer_uptodate(bh)) ret = -EIO; } if (ret) goto failed; } if (is_mapped_to_disk) SetPageMappedToDisk(page); *fsdata = head; /* to be released by nobh_write_end */ return 0; failed: BUG_ON(!ret); /* * Error recovery is a bit difficult. We need to zero out blocks that * were newly allocated, and dirty them to ensure they get written out. * Buffers need to be attached to the page at this point, otherwise * the handling of potential IO errors during writeout would be hard * (could try doing synchronous writeout, but what if that fails too?) */ attach_nobh_buffers(page, head); page_zero_new_buffers(page, from, to); out_release: unlock_page(page); put_page(page); *pagep = NULL; return ret; } EXPORT_SYMBOL(nobh_write_begin); int nobh_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = page->mapping->host; struct buffer_head *head = fsdata; struct buffer_head *bh; BUG_ON(fsdata != NULL && page_has_buffers(page)); if (unlikely(copied < len) && head) attach_nobh_buffers(page, head); if (page_has_buffers(page)) return generic_write_end(file, mapping, pos, len, copied, page, fsdata); SetPageUptodate(page); set_page_dirty(page); if (pos+copied > inode->i_size) { i_size_write(inode, pos+copied); mark_inode_dirty(inode); } unlock_page(page); put_page(page); while (head) { bh = head; head = head->b_this_page; free_buffer_head(bh); } return copied; } EXPORT_SYMBOL(nobh_write_end); /* * nobh_writepage() - based on block_full_write_page() except * that it tries to operate without attaching bufferheads to * the page. */ int nobh_writepage(struct page *page, get_block_t *get_block, struct writeback_control *wbc) { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); const pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned offset; int ret; /* Is the page fully inside i_size? */ if (page->index < end_index) goto out; /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { unlock_page(page); return 0; /* don't care */ } /* * The page straddles i_size. It must be zeroed out on each and every * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ zero_user_segment(page, offset, PAGE_SIZE); out: ret = mpage_writepage(page, get_block, wbc); if (ret == -EAGAIN) ret = __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); return ret; } EXPORT_SYMBOL(nobh_writepage); int nobh_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize; sector_t iblock; unsigned length, pos; struct inode *inode = mapping->host; struct page *page; struct buffer_head map_bh; int err; blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits); page = grab_cache_page(mapping, index); err = -ENOMEM; if (!page) goto out; if (page_has_buffers(page)) { has_buffers: unlock_page(page); put_page(page); return block_truncate_page(mapping, from, get_block); } /* Find the buffer that contains "offset" */ pos = blocksize; while (offset >= pos) { iblock++; pos += blocksize; } map_bh.b_size = blocksize; map_bh.b_state = 0; err = get_block(inode, iblock, &map_bh, 0); if (err) goto unlock; /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(&map_bh)) goto unlock; /* Ok, it's mapped. Make sure it's up-to-date */ if (!PageUptodate(page)) { err = mapping->a_ops->readpage(NULL, page); if (err) { put_page(page); goto out; } lock_page(page); if (!PageUptodate(page)) { err = -EIO; goto unlock; } if (page_has_buffers(page)) goto has_buffers; } zero_user(page, offset, length); set_page_dirty(page); err = 0; unlock: unlock_page(page); put_page(page); out: return err; } EXPORT_SYMBOL(nobh_truncate_page); int block_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize; sector_t iblock; unsigned length, pos; struct inode *inode = mapping->host; struct page *page; struct buffer_head *bh; int err; blocksize = i_blocksize(inode); length = offset & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits); page = grab_cache_page(mapping, index); err = -ENOMEM; if (!page) goto out; if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); /* Find the buffer that contains "offset" */ bh = page_buffers(page); pos = blocksize; while (offset >= pos) { bh = bh->b_this_page; iblock++; pos += blocksize; } err = 0; if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) goto unlock; /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(bh)) goto unlock; } /* Ok, it's mapped. Make sure it's up-to-date */ if (PageUptodate(page)) set_buffer_uptodate(bh); if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) { err = -EIO; ll_rw_block(REQ_OP_READ, 0, 1, &bh); wait_on_buffer(bh); /* Uhhuh. Read error. Complain and punt. */ if (!buffer_uptodate(bh)) goto unlock; } zero_user(page, offset, length); mark_buffer_dirty(bh); err = 0; unlock: unlock_page(page); put_page(page); out: return err; } EXPORT_SYMBOL(block_truncate_page); /* * The generic ->writepage function for buffer-backed address_spaces */ int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc) { struct inode * const inode = page->mapping->host; loff_t i_size = i_size_read(inode); const pgoff_t end_index = i_size >> PAGE_SHIFT; unsigned offset; /* Is the page fully inside i_size? */ if (page->index < end_index) return __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); /* Is the page fully outside i_size? (truncate in progress) */ offset = i_size & (PAGE_SIZE-1); if (page->index >= end_index+1 || !offset) { unlock_page(page); return 0; /* don't care */ } /* * The page straddles i_size. It must be zeroed out on each and every * writepage invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ zero_user_segment(page, offset, PAGE_SIZE); return __block_write_full_page(inode, page, get_block, wbc, end_buffer_async_write); } EXPORT_SYMBOL(block_write_full_page); sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) { struct inode *inode = mapping->host; struct buffer_head tmp = { .b_size = i_blocksize(inode), }; get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } EXPORT_SYMBOL(generic_block_bmap); static void end_bio_bh_io_sync(struct bio *bio) { struct buffer_head *bh = bio->bi_private; if (unlikely(bio_flagged(bio, BIO_QUIET))) set_bit(BH_Quiet, &bh->b_state); bh->b_end_io(bh, !bio->bi_status); bio_put(bio); } static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, enum rw_hint write_hint, struct writeback_control *wbc) { struct bio *bio; BUG_ON(!buffer_locked(bh)); BUG_ON(!buffer_mapped(bh)); BUG_ON(!bh->b_end_io); BUG_ON(buffer_delay(bh)); BUG_ON(buffer_unwritten(bh)); /* * Only clear out a write error when rewriting */ if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE)) clear_buffer_write_io_error(bh); bio = bio_alloc(GFP_NOIO, 1); fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_write_hint = write_hint; bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); BUG_ON(bio->bi_iter.bi_size != bh->b_size); bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; if (buffer_meta(bh)) op_flags |= REQ_META; if (buffer_prio(bh)) op_flags |= REQ_PRIO; bio_set_op_attrs(bio, op, op_flags); /* Take care of bh's that straddle the end of the device */ guard_bio_eod(bio); if (wbc) { wbc_init_bio(wbc, bio); wbc_account_cgroup_owner(wbc, bh->b_page, bh->b_size); } submit_bio(bio); return 0; } int submit_bh(int op, int op_flags, struct buffer_head *bh) { return submit_bh_wbc(op, op_flags, bh, 0, NULL); } EXPORT_SYMBOL(submit_bh); /** * ll_rw_block: low-level access to block devices (DEPRECATED) * @op: whether to %READ or %WRITE * @op_flags: req_flag_bits * @nr: number of &struct buffer_heads in the array * @bhs: array of pointers to &struct buffer_head * * ll_rw_block() takes an array of pointers to &struct buffer_heads, and * requests an I/O operation on them, either a %REQ_OP_READ or a %REQ_OP_WRITE. * @op_flags contains flags modifying the detailed I/O behavior, most notably * %REQ_RAHEAD. * * This function drops any buffer that it cannot get a lock on (with the * BH_Lock state bit), any buffer that appears to be clean when doing a write * request, and any buffer that appears to be up-to-date when doing read * request. Further it marks as clean buffers that are processed for * writing (the buffer cache won't assume that they are actually clean * until the buffer gets unlocked). * * ll_rw_block sets b_end_io to simple completion handler that marks * the buffer up-to-date (if appropriate), unlocks the buffer and wakes * any waiters. * * All of the buffers must be for the same device, and must also be a * multiple of the current approved size for the device. */ void ll_rw_block(int op, int op_flags, int nr, struct buffer_head *bhs[]) { int i; for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; if (!trylock_buffer(bh)) continue; if (op == WRITE) { if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(op, op_flags, bh); continue; } } else { if (!buffer_uptodate(bh)) { bh->b_end_io = end_buffer_read_sync; get_bh(bh); submit_bh(op, op_flags, bh); continue; } } unlock_buffer(bh); } } EXPORT_SYMBOL(ll_rw_block); void write_dirty_buffer(struct buffer_head *bh, int op_flags) { lock_buffer(bh); if (!test_clear_buffer_dirty(bh)) { unlock_buffer(bh); return; } bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(REQ_OP_WRITE, op_flags, bh); } EXPORT_SYMBOL(write_dirty_buffer); /* * For a data-integrity writeout, we need to wait upon any in-progress I/O * and then start new I/O and then wait upon it. The caller must have a ref on * the buffer_head. */ int __sync_dirty_buffer(struct buffer_head *bh, int op_flags) { int ret = 0; WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { /* * The bh should be mapped, but it might not be if the * device was hot-removed. Not much we can do but fail the I/O. */ if (!buffer_mapped(bh)) { unlock_buffer(bh); return -EIO; } get_bh(bh); bh->b_end_io = end_buffer_write_sync; ret = submit_bh(REQ_OP_WRITE, op_flags, bh); wait_on_buffer(bh); if (!ret && !buffer_uptodate(bh)) ret = -EIO; } else { unlock_buffer(bh); } return ret; } EXPORT_SYMBOL(__sync_dirty_buffer); int sync_dirty_buffer(struct buffer_head *bh) { return __sync_dirty_buffer(bh, REQ_SYNC); } EXPORT_SYMBOL(sync_dirty_buffer); /* * try_to_free_buffers() checks if all the buffers on this particular page * are unused, and releases them if so. * * Exclusion against try_to_free_buffers may be obtained by either * locking the page or by holding its mapping's private_lock. * * If the page is dirty but all the buffers are clean then we need to * be sure to mark the page clean as well. This is because the page * may be against a block device, and a later reattachment of buffers * to a dirty page will set *all* buffers dirty. Which would corrupt * filesystem data on the same device. * * The same applies to regular filesystem pages: if all the buffers are * clean then we set the page clean and proceed. To do that, we require * total exclusion from __set_page_dirty_buffers(). That is obtained with * private_lock. * * try_to_free_buffers() is non-blocking. */ static inline int buffer_busy(struct buffer_head *bh) { return atomic_read(&bh->b_count) | (bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock))); } static int drop_buffers(struct page *page, struct buffer_head **buffers_to_free) { struct buffer_head *head = page_buffers(page); struct buffer_head *bh; bh = head; do { if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; } while (bh != head); do { struct buffer_head *next = bh->b_this_page; if (bh->b_assoc_map) __remove_assoc_queue(bh); bh = next; } while (bh != head); *buffers_to_free = head; detach_page_private(page); return 1; failed: return 0; } int try_to_free_buffers(struct page *page) { struct address_space * const mapping = page->mapping; struct buffer_head *buffers_to_free = NULL; int ret = 0; BUG_ON(!PageLocked(page)); if (PageWriteback(page)) return 0; if (mapping == NULL) { /* can this still happen? */ ret = drop_buffers(page, &buffers_to_free); goto out; } spin_lock(&mapping->private_lock); ret = drop_buffers(page, &buffers_to_free); /* * If the filesystem writes its buffers by hand (eg ext3) * then we can have clean buffers against a dirty page. We * clean the page here; otherwise the VM will never notice * that the filesystem did any IO at all. * * Also, during truncate, discard_buffer will have marked all * the page's buffers clean. We discover that here and clean * the page also. * * private_lock must be held over this entire operation in order * to synchronise against __set_page_dirty_buffers and prevent the * dirty bit from being lost. */ if (ret) cancel_dirty_page(page); spin_unlock(&mapping->private_lock); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; do { struct buffer_head *next = bh->b_this_page; free_buffer_head(bh); bh = next; } while (bh != buffers_to_free); } return ret; } EXPORT_SYMBOL(try_to_free_buffers); /* * There are no bdflush tunables left. But distributions are * still running obsolete flush daemons, so we terminate them here. * * Use of bdflush() is deprecated and will be removed in a future kernel. * The `flush-X' kernel threads fully replace bdflush daemons and this call. */ SYSCALL_DEFINE2(bdflush, int, func, long, data) { static int msg_count; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (msg_count < 5) { msg_count++; printk(KERN_INFO "warning: process `%s' used the obsolete bdflush" " system call\n", current->comm); printk(KERN_INFO "Fix your initscripts?\n"); } if (func == 1) do_exit(0); return 0; } /* * Buffer-head allocation */ static struct kmem_cache *bh_cachep __read_mostly; /* * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ static unsigned long max_buffer_heads; int buffer_heads_over_limit; struct bh_accounting { int nr; /* Number of live bh's */ int ratelimit; /* Limit cacheline bouncing */ }; static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0}; static void recalc_bh_state(void) { int i; int tot = 0; if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096) return; __this_cpu_write(bh_accounting.ratelimit, 0); for_each_online_cpu(i) tot += per_cpu(bh_accounting, i).nr; buffer_heads_over_limit = (tot > max_buffer_heads); } struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); spin_lock_init(&ret->b_uptodate_lock); preempt_disable(); __this_cpu_inc(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } return ret; } EXPORT_SYMBOL(alloc_buffer_head); void free_buffer_head(struct buffer_head *bh) { BUG_ON(!list_empty(&bh->b_assoc_buffers)); kmem_cache_free(bh_cachep, bh); preempt_disable(); __this_cpu_dec(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } EXPORT_SYMBOL(free_buffer_head); static int buffer_exit_cpu_dead(unsigned int cpu) { int i; struct bh_lru *b = &per_cpu(bh_lrus, cpu); for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr); per_cpu(bh_accounting, cpu).nr = 0; return 0; } /** * bh_uptodate_or_lock - Test whether the buffer is uptodate * @bh: struct buffer_head * * Return true if the buffer is up-to-date and false, * with the buffer locked, if not. */ int bh_uptodate_or_lock(struct buffer_head *bh) { if (!buffer_uptodate(bh)) { lock_buffer(bh); if (!buffer_uptodate(bh)) return 0; unlock_buffer(bh); } return 1; } EXPORT_SYMBOL(bh_uptodate_or_lock); /** * bh_submit_read - Submit a locked buffer for reading * @bh: struct buffer_head * * Returns zero on success and -EIO on error. */ int bh_submit_read(struct buffer_head *bh) { BUG_ON(!buffer_locked(bh)); if (buffer_uptodate(bh)) { unlock_buffer(bh); return 0; } get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, 0, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return 0; return -EIO; } EXPORT_SYMBOL(bh_submit_read); void __init buffer_init(void) { unsigned long nrpages; int ret; bh_cachep = kmem_cache_create("buffer_head", sizeof(struct buffer_head), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_MEM_SPREAD), NULL); /* * Limit the bh occupancy to 10% of ZONE_NORMAL */ nrpages = (nr_free_buffer_pages() * 10) / 100; max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head)); ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead", NULL, buffer_exit_cpu_dead); WARN_ON(ret < 0); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/fault-inject.h> #include <linux/fault-inject-usercopy.h> static struct { struct fault_attr attr; } fail_usercopy = { .attr = FAULT_ATTR_INITIALIZER, }; static int __init setup_fail_usercopy(char *str) { return setup_fault_attr(&fail_usercopy.attr, str); } __setup("fail_usercopy=", setup_fail_usercopy); #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS static int __init fail_usercopy_debugfs(void) { struct dentry *dir; dir = fault_create_debugfs_attr("fail_usercopy", NULL, &fail_usercopy.attr); if (IS_ERR(dir)) return PTR_ERR(dir); return 0; } late_initcall(fail_usercopy_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ bool should_fail_usercopy(void) { return should_fail(&fail_usercopy.attr, 1); } EXPORT_SYMBOL_GPL(should_fail_usercopy); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | /* SPDX-License-Identifier: GPL-2.0 */ /* * bvec iterator * * Copyright (C) 2001 Ming Lei <ming.lei@canonical.com> */ #ifndef __LINUX_BVEC_ITER_H #define __LINUX_BVEC_ITER_H #include <linux/bug.h> #include <linux/errno.h> #include <linux/limits.h> #include <linux/minmax.h> #include <linux/mm.h> #include <linux/types.h> struct page; /** * struct bio_vec - a contiguous range of physical memory addresses * @bv_page: First page associated with the address range. * @bv_len: Number of bytes in the address range. * @bv_offset: Start of the address range relative to the start of @bv_page. * * The following holds for a bvec if n * PAGE_SIZE < bv_offset + bv_len: * * nth_page(@bv_page, n) == @bv_page + n * * This holds because page_is_mergeable() checks the above property. */ struct bio_vec { struct page *bv_page; unsigned int bv_len; unsigned int bv_offset; }; struct bvec_iter { sector_t bi_sector; /* device address in 512 byte sectors */ unsigned int bi_size; /* residual I/O count */ unsigned int bi_idx; /* current index into bvl_vec */ unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ }; struct bvec_iter_all { struct bio_vec bv; int idx; unsigned done; }; /* * various member access, note that bio_data should of course not be used * on highmem page vectors */ #define __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx]) /* multi-page (mp_bvec) helpers */ #define mp_bvec_iter_page(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_page) #define mp_bvec_iter_len(bvec, iter) \ min((iter).bi_size, \ __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done) #define mp_bvec_iter_offset(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done) #define mp_bvec_iter_page_idx(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) / PAGE_SIZE) #define mp_bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = mp_bvec_iter_page((bvec), (iter)), \ .bv_len = mp_bvec_iter_len((bvec), (iter)), \ .bv_offset = mp_bvec_iter_offset((bvec), (iter)), \ }) /* For building single-page bvec in flight */ #define bvec_iter_offset(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) % PAGE_SIZE) #define bvec_iter_len(bvec, iter) \ min_t(unsigned, mp_bvec_iter_len((bvec), (iter)), \ PAGE_SIZE - bvec_iter_offset((bvec), (iter))) #define bvec_iter_page(bvec, iter) \ (mp_bvec_iter_page((bvec), (iter)) + \ mp_bvec_iter_page_idx((bvec), (iter))) #define bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = bvec_iter_page((bvec), (iter)), \ .bv_len = bvec_iter_len((bvec), (iter)), \ .bv_offset = bvec_iter_offset((bvec), (iter)), \ }) static inline bool bvec_iter_advance(const struct bio_vec *bv, struct bvec_iter *iter, unsigned bytes) { unsigned int idx = iter->bi_idx; if (WARN_ONCE(bytes > iter->bi_size, "Attempted to advance past end of bvec iter\n")) { iter->bi_size = 0; return false; } iter->bi_size -= bytes; bytes += iter->bi_bvec_done; while (bytes && bytes >= bv[idx].bv_len) { bytes -= bv[idx].bv_len; idx++; } iter->bi_idx = idx; iter->bi_bvec_done = bytes; return true; } static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter) { iter->bi_bvec_done = 0; iter->bi_idx++; } #define for_each_bvec(bvl, bio_vec, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter), \ (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter))) /* for iterating one bio from start to end */ #define BVEC_ITER_ALL_INIT (struct bvec_iter) \ { \ .bi_sector = 0, \ .bi_size = UINT_MAX, \ .bi_idx = 0, \ .bi_bvec_done = 0, \ } static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all) { iter_all->done = 0; iter_all->idx = 0; return &iter_all->bv; } static inline void bvec_advance(const struct bio_vec *bvec, struct bvec_iter_all *iter_all) { struct bio_vec *bv = &iter_all->bv; if (iter_all->done) { bv->bv_page++; bv->bv_offset = 0; } else { bv->bv_page = bvec->bv_page + (bvec->bv_offset >> PAGE_SHIFT); bv->bv_offset = bvec->bv_offset & ~PAGE_MASK; } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); iter_all->done += bv->bv_len; if (iter_all->done == bvec->bv_len) { iter_all->idx++; iter_all->done = 0; } } #endif /* __LINUX_BVEC_ITER_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_COUNTER_H #define _LINUX_PERCPU_COUNTER_H /* * A simple "approximate counter" for use in ext2 and ext3 superblocks. * * WARNING: these things are HUGE. 4 kbytes per counter on 32-way P4. */ #include <linux/spinlock.h> #include <linux/smp.h> #include <linux/list.h> #include <linux/threads.h> #include <linux/percpu.h> #include <linux/types.h> #include <linux/gfp.h> #ifdef CONFIG_SMP struct percpu_counter { raw_spinlock_t lock; s64 count; #ifdef CONFIG_HOTPLUG_CPU struct list_head list; /* All percpu_counters are on a list */ #endif s32 __percpu *counters; }; extern int percpu_counter_batch; int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, struct lock_class_key *key); #define percpu_counter_init(fbc, value, gfp) \ ({ \ static struct lock_class_key __key; \ \ __percpu_counter_init(fbc, value, gfp, &__key); \ }) void percpu_counter_destroy(struct percpu_counter *fbc); void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); void percpu_counter_sync(struct percpu_counter *fbc); static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { return __percpu_counter_compare(fbc, rhs, percpu_counter_batch); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { percpu_counter_add_batch(fbc, amount, percpu_counter_batch); } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { s64 ret = __percpu_counter_sum(fbc); return ret < 0 ? 0 : ret; } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return __percpu_counter_sum(fbc); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * It is possible for the percpu_counter_read() to return a small negative * number for some counter which should never be negative. * */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { /* Prevent reloads of fbc->count */ s64 ret = READ_ONCE(fbc->count); if (ret >= 0) return ret; return 0; } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return (fbc->counters != NULL); } #else /* !CONFIG_SMP */ struct percpu_counter { s64 count; }; static inline int percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp) { fbc->count = amount; return 0; } static inline void percpu_counter_destroy(struct percpu_counter *fbc) { } static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { fbc->count = amount; } static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs) { if (fbc->count > rhs) return 1; else if (fbc->count < rhs) return -1; else return 0; } static inline int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { return percpu_counter_compare(fbc, rhs); } static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount) { preempt_disable(); fbc->count += amount; preempt_enable(); } static inline void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { percpu_counter_add(fbc, amount); } static inline s64 percpu_counter_read(struct percpu_counter *fbc) { return fbc->count; } /* * percpu_counter is intended to track positive numbers. In the UP case the * number should never be negative. */ static inline s64 percpu_counter_read_positive(struct percpu_counter *fbc) { return fbc->count; } static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc) { return percpu_counter_read_positive(fbc); } static inline s64 percpu_counter_sum(struct percpu_counter *fbc) { return percpu_counter_read(fbc); } static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return true; } static inline void percpu_counter_sync(struct percpu_counter *fbc) { } #endif /* CONFIG_SMP */ static inline void percpu_counter_inc(struct percpu_counter *fbc) { percpu_counter_add(fbc, 1); } static inline void percpu_counter_dec(struct percpu_counter *fbc) { percpu_counter_add(fbc, -1); } static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount) { percpu_counter_add(fbc, -amount); } #endif /* _LINUX_PERCPU_COUNTER_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 | /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/xattr.h Extended attributes handling. Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org> Copyright (c) 2001-2002 Silicon Graphics, Inc. All Rights Reserved. Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #ifndef _LINUX_XATTR_H #define _LINUX_XATTR_H #include <linux/slab.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <uapi/linux/xattr.h> struct inode; struct dentry; /* * struct xattr_handler: When @name is set, match attributes with exactly that * name. When @prefix is set instead, match attributes with that prefix and * with a non-empty suffix. */ struct xattr_handler { const char *name; const char *prefix; int flags; /* fs private flags */ bool (*list)(struct dentry *dentry); int (*get)(const struct xattr_handler *, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); }; const char *xattr_full_name(const struct xattr_handler *, const char *); struct xattr { const char *name; void *value; size_t value_len; }; ssize_t __vfs_getxattr(struct dentry *, struct inode *, const char *, void *, size_t); ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); int __vfs_setxattr(struct dentry *, struct inode *, const char *, const void *, size_t, int); int __vfs_setxattr_noperm(struct dentry *, const char *, const void *, size_t, int); int __vfs_setxattr_locked(struct dentry *, const char *, const void *, size_t, int, struct inode **); int vfs_setxattr(struct dentry *, const char *, const void *, size_t, int); int __vfs_removexattr(struct dentry *, const char *); int __vfs_removexattr_locked(struct dentry *, const char *, struct inode **); int vfs_removexattr(struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); int xattr_supported_namespace(struct inode *inode, const char *prefix); static inline const char *xattr_prefix(const struct xattr_handler *handler) { return handler->prefix ?: handler->name; } struct simple_xattrs { struct list_head head; spinlock_t lock; }; struct simple_xattr { struct list_head list; char *name; size_t size; char value[]; }; /* * initialize the simple_xattrs structure */ static inline void simple_xattrs_init(struct simple_xattrs *xattrs) { INIT_LIST_HEAD(&xattrs->head); spin_lock_init(&xattrs->lock); } /* * free all the xattrs */ static inline void simple_xattrs_free(struct simple_xattrs *xattrs) { struct simple_xattr *xattr, *node; list_for_each_entry_safe(xattr, node, &xattrs->head, list) { kfree(xattr->name); kvfree(xattr); } } struct simple_xattr *simple_xattr_alloc(const void *value, size_t size); int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size); int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags, ssize_t *removed_size); ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size); void simple_xattr_list_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr); #endif /* _LINUX_XATTR_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 | // SPDX-License-Identifier: GPL-2.0-only /* * Implementation of the security services. * * Authors : Stephen Smalley, <sds@tycho.nsa.gov> * James Morris <jmorris@redhat.com> * * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * * Support for enhanced MLS infrastructure. * Support for context based audit filters. * * Updated: Frank Mayer <mayerf@tresys.com> and Karl MacMillan <kmacmillan@tresys.com> * * Added conditional policy language extensions * * Updated: Hewlett-Packard <paul@paul-moore.com> * * Added support for NetLabel * Added support for the policy capability bitmap * * Updated: Chad Sellers <csellers@tresys.com> * * Added validation of kernel classes and permissions * * Updated: KaiGai Kohei <kaigai@ak.jp.nec.com> * * Added support for bounds domain and audit messaged on masked permissions * * Updated: Guido Trentalancia <guido@trentalancia.com> * * Added support for runtime switching of the policy type * * Copyright (C) 2008, 2009 NEC Corporation * Copyright (C) 2006, 2007 Hewlett-Packard Development Company, L.P. * Copyright (C) 2004-2006 Trusted Computer Solutions, Inc. * Copyright (C) 2003 - 2004, 2006 Tresys Technology, LLC * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/sched.h> #include <linux/audit.h> #include <linux/vmalloc.h> #include <net/netlabel.h> #include "flask.h" #include "avc.h" #include "avc_ss.h" #include "security.h" #include "context.h" #include "policydb.h" #include "sidtab.h" #include "services.h" #include "conditional.h" #include "mls.h" #include "objsec.h" #include "netlabel.h" #include "xfrm.h" #include "ebitmap.h" #include "audit.h" #include "policycap_names.h" struct convert_context_args { struct selinux_state *state; struct policydb *oldp; struct policydb *newp; }; struct selinux_policy_convert_data { struct convert_context_args args; struct sidtab_convert_params sidtab_params; }; /* Forward declaration. */ static int context_struct_to_string(struct policydb *policydb, struct context *context, char **scontext, u32 *scontext_len); static int sidtab_entry_to_string(struct policydb *policydb, struct sidtab *sidtab, struct sidtab_entry *entry, char **scontext, u32 *scontext_len); static void context_struct_compute_av(struct policydb *policydb, struct context *scontext, struct context *tcontext, u16 tclass, struct av_decision *avd, struct extended_perms *xperms); static int selinux_set_mapping(struct policydb *pol, struct security_class_mapping *map, struct selinux_map *out_map) { u16 i, j; unsigned k; bool print_unknown_handle = false; /* Find number of classes in the input mapping */ if (!map) return -EINVAL; i = 0; while (map[i].name) i++; /* Allocate space for the class records, plus one for class zero */ out_map->mapping = kcalloc(++i, sizeof(*out_map->mapping), GFP_ATOMIC); if (!out_map->mapping) return -ENOMEM; /* Store the raw class and permission values */ j = 0; while (map[j].name) { struct security_class_mapping *p_in = map + (j++); struct selinux_mapping *p_out = out_map->mapping + j; /* An empty class string skips ahead */ if (!strcmp(p_in->name, "")) { p_out->num_perms = 0; continue; } p_out->value = string_to_security_class(pol, p_in->name); if (!p_out->value) { pr_info("SELinux: Class %s not defined in policy.\n", p_in->name); if (pol->reject_unknown) goto err; p_out->num_perms = 0; print_unknown_handle = true; continue; } k = 0; while (p_in->perms[k]) { /* An empty permission string skips ahead */ if (!*p_in->perms[k]) { k++; continue; } p_out->perms[k] = string_to_av_perm(pol, p_out->value, p_in->perms[k]); if (!p_out->perms[k]) { pr_info("SELinux: Permission %s in class %s not defined in policy.\n", p_in->perms[k], p_in->name); if (pol->reject_unknown) goto err; print_unknown_handle = true; } k++; } p_out->num_perms = k; } if (print_unknown_handle) pr_info("SELinux: the above unknown classes and permissions will be %s\n", pol->allow_unknown ? "allowed" : "denied"); out_map->size = i; return 0; err: kfree(out_map->mapping); out_map->mapping = NULL; return -EINVAL; } /* * Get real, policy values from mapped values */ static u16 unmap_class(struct selinux_map *map, u16 tclass) { if (tclass < map->size) return map->mapping[tclass].value; return tclass; } /* * Get kernel value for class from its policy value */ static u16 map_class(struct selinux_map *map, u16 pol_value) { u16 i; for (i = 1; i < map->size; i++) { if (map->mapping[i].value == pol_value) return i; } return SECCLASS_NULL; } static void map_decision(struct selinux_map *map, u16 tclass, struct av_decision *avd, int allow_unknown) { if (tclass < map->size) { struct selinux_mapping *mapping = &map->mapping[tclass]; unsigned int i, n = mapping->num_perms; u32 result; for (i = 0, result = 0; i < n; i++) { if (avd->allowed & mapping->perms[i]) result |= 1<<i; if (allow_unknown && !mapping->perms[i]) result |= 1<<i; } avd->allowed = result; for (i = 0, result = 0; i < n; i++) if (avd->auditallow & mapping->perms[i]) result |= 1<<i; avd->auditallow = result; for (i = 0, result = 0; i < n; i++) { if (avd->auditdeny & mapping->perms[i]) result |= 1<<i; if (!allow_unknown && !mapping->perms[i]) result |= 1<<i; } /* * In case the kernel has a bug and requests a permission * between num_perms and the maximum permission number, we * should audit that denial */ for (; i < (sizeof(u32)*8); i++) result |= 1<<i; avd->auditdeny = result; } } int security_mls_enabled(struct selinux_state *state) { int mls_enabled; struct selinux_policy *policy; if (!selinux_initialized(state)) return 0; rcu_read_lock(); policy = rcu_dereference(state->policy); mls_enabled = policy->policydb.mls_enabled; rcu_read_unlock(); return mls_enabled; } /* * Return the boolean value of a constraint expression * when it is applied to the specified source and target * security contexts. * * xcontext is a special beast... It is used by the validatetrans rules * only. For these rules, scontext is the context before the transition, * tcontext is the context after the transition, and xcontext is the context * of the process performing the transition. All other callers of * constraint_expr_eval should pass in NULL for xcontext. */ static int constraint_expr_eval(struct policydb *policydb, struct context *scontext, struct context *tcontext, struct context *xcontext, struct constraint_expr *cexpr) { u32 val1, val2; struct context *c; struct role_datum *r1, *r2; struct mls_level *l1, *l2; struct constraint_expr *e; int s[CEXPR_MAXDEPTH]; int sp = -1; for (e = cexpr; e; e = e->next) { switch (e->expr_type) { case CEXPR_NOT: BUG_ON(sp < 0); s[sp] = !s[sp]; break; case CEXPR_AND: BUG_ON(sp < 1); sp--; s[sp] &= s[sp + 1]; break; case CEXPR_OR: BUG_ON(sp < 1); sp--; s[sp] |= s[sp + 1]; break; case CEXPR_ATTR: if (sp == (CEXPR_MAXDEPTH - 1)) return 0; switch (e->attr) { case CEXPR_USER: val1 = scontext->user; val2 = tcontext->user; break; case CEXPR_TYPE: val1 = scontext->type; val2 = tcontext->type; break; case CEXPR_ROLE: val1 = scontext->role; val2 = tcontext->role; r1 = policydb->role_val_to_struct[val1 - 1]; r2 = policydb->role_val_to_struct[val2 - 1]; switch (e->op) { case CEXPR_DOM: s[++sp] = ebitmap_get_bit(&r1->dominates, val2 - 1); continue; case CEXPR_DOMBY: s[++sp] = ebitmap_get_bit(&r2->dominates, val1 - 1); continue; case CEXPR_INCOMP: s[++sp] = (!ebitmap_get_bit(&r1->dominates, val2 - 1) && !ebitmap_get_bit(&r2->dominates, val1 - 1)); continue; default: break; } break; case CEXPR_L1L2: l1 = &(scontext->range.level[0]); l2 = &(tcontext->range.level[0]); goto mls_ops; case CEXPR_L1H2: l1 = &(scontext->range.level[0]); l2 = &(tcontext->range.level[1]); goto mls_ops; case CEXPR_H1L2: l1 = &(scontext->range.level[1]); l2 = &(tcontext->range.level[0]); goto mls_ops; case CEXPR_H1H2: l1 = &(scontext->range.level[1]); l2 = &(tcontext->range.level[1]); goto mls_ops; case CEXPR_L1H1: l1 = &(scontext->range.level[0]); l2 = &(scontext->range.level[1]); goto mls_ops; case CEXPR_L2H2: l1 = &(tcontext->range.level[0]); l2 = &(tcontext->range.level[1]); goto mls_ops; mls_ops: switch (e->op) { case CEXPR_EQ: s[++sp] = mls_level_eq(l1, l2); continue; case CEXPR_NEQ: s[++sp] = !mls_level_eq(l1, l2); continue; case CEXPR_DOM: s[++sp] = mls_level_dom(l1, l2); continue; case CEXPR_DOMBY: s[++sp] = mls_level_dom(l2, l1); continue; case CEXPR_INCOMP: s[++sp] = mls_level_incomp(l2, l1); continue; default: BUG(); return 0; } break; default: BUG(); return 0; } switch (e->op) { case CEXPR_EQ: s[++sp] = (val1 == val2); break; case CEXPR_NEQ: s[++sp] = (val1 != val2); break; default: BUG(); return 0; } break; case CEXPR_NAMES: if (sp == (CEXPR_MAXDEPTH-1)) return 0; c = scontext; if (e->attr & CEXPR_TARGET) c = tcontext; else if (e->attr & CEXPR_XTARGET) { c = xcontext; if (!c) { BUG(); return 0; } } if (e->attr & CEXPR_USER) val1 = c->user; else if (e->attr & CEXPR_ROLE) val1 = c->role; else if (e->attr & CEXPR_TYPE) val1 = c->type; else { BUG(); return 0; } switch (e->op) { case CEXPR_EQ: s[++sp] = ebitmap_get_bit(&e->names, val1 - 1); break; case CEXPR_NEQ: s[++sp] = !ebitmap_get_bit(&e->names, val1 - 1); break; default: BUG(); return 0; } break; default: BUG(); return 0; } } BUG_ON(sp != 0); return s[0]; } /* * security_dump_masked_av - dumps masked permissions during * security_compute_av due to RBAC, MLS/Constraint and Type bounds. */ static int dump_masked_av_helper(void *k, void *d, void *args) { struct perm_datum *pdatum = d; char **permission_names = args; BUG_ON(pdatum->value < 1 || pdatum->value > 32); permission_names[pdatum->value - 1] = (char *)k; return 0; } static void security_dump_masked_av(struct policydb *policydb, struct context *scontext, struct context *tcontext, u16 tclass, u32 permissions, const char *reason) { struct common_datum *common_dat; struct class_datum *tclass_dat; struct audit_buffer *ab; char *tclass_name; char *scontext_name = NULL; char *tcontext_name = NULL; char *permission_names[32]; int index; u32 length; bool need_comma = false; if (!permissions) return; tclass_name = sym_name(policydb, SYM_CLASSES, tclass - 1); tclass_dat = policydb->class_val_to_struct[tclass - 1]; common_dat = tclass_dat->comdatum; /* init permission_names */ if (common_dat && hashtab_map(&common_dat->permissions.table, dump_masked_av_helper, permission_names) < 0) goto out; if (hashtab_map(&tclass_dat->permissions.table, dump_masked_av_helper, permission_names) < 0) goto out; /* get scontext/tcontext in text form */ if (context_struct_to_string(policydb, scontext, &scontext_name, &length) < 0) goto out; if (context_struct_to_string(policydb, tcontext, &tcontext_name, &length) < 0) goto out; /* audit a message */ ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) goto out; audit_log_format(ab, "op=security_compute_av reason=%s " "scontext=%s tcontext=%s tclass=%s perms=", reason, scontext_name, tcontext_name, tclass_name); for (index = 0; index < 32; index++) { u32 mask = (1 << index); if ((mask & permissions) == 0) continue; audit_log_format(ab, "%s%s", need_comma ? "," : "", permission_names[index] ? permission_names[index] : "????"); need_comma = true; } audit_log_end(ab); out: /* release scontext/tcontext */ kfree(tcontext_name); kfree(scontext_name); return; } /* * security_boundary_permission - drops violated permissions * on boundary constraint. */ static void type_attribute_bounds_av(struct policydb *policydb, struct context *scontext, struct context *tcontext, u16 tclass, struct av_decision *avd) { struct context lo_scontext; struct context lo_tcontext, *tcontextp = tcontext; struct av_decision lo_avd; struct type_datum *source; struct type_datum *target; u32 masked = 0; source = policydb->type_val_to_struct[scontext->type - 1]; BUG_ON(!source); if (!source->bounds) return; target = policydb->type_val_to_struct[tcontext->type - 1]; BUG_ON(!target); memset(&lo_avd, 0, sizeof(lo_avd)); memcpy(&lo_scontext, scontext, sizeof(lo_scontext)); lo_scontext.type = source->bounds; if (target->bounds) { memcpy(&lo_tcontext, tcontext, sizeof(lo_tcontext)); lo_tcontext.type = target->bounds; tcontextp = &lo_tcontext; } context_struct_compute_av(policydb, &lo_scontext, tcontextp, tclass, &lo_avd, NULL); masked = ~lo_avd.allowed & avd->allowed; if (likely(!masked)) return; /* no masked permission */ /* mask violated permissions */ avd->allowed &= ~masked; /* audit masked permissions */ security_dump_masked_av(policydb, scontext, tcontext, tclass, masked, "bounds"); } /* * flag which drivers have permissions * only looking for ioctl based extended permssions */ void services_compute_xperms_drivers( struct extended_perms *xperms, struct avtab_node *node) { unsigned int i; if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLDRIVER) { /* if one or more driver has all permissions allowed */ for (i = 0; i < ARRAY_SIZE(xperms->drivers.p); i++) xperms->drivers.p[i] |= node->datum.u.xperms->perms.p[i]; } else if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLFUNCTION) { /* if allowing permissions within a driver */ security_xperm_set(xperms->drivers.p, node->datum.u.xperms->driver); } /* If no ioctl commands are allowed, ignore auditallow and auditdeny */ if (node->key.specified & AVTAB_XPERMS_ALLOWED) xperms->len = 1; } /* * Compute access vectors and extended permissions based on a context * structure pair for the permissions in a particular class. */ static void context_struct_compute_av(struct policydb *policydb, struct context *scontext, struct context *tcontext, u16 tclass, struct av_decision *avd, struct extended_perms *xperms) { struct constraint_node *constraint; struct role_allow *ra; struct avtab_key avkey; struct avtab_node *node; struct class_datum *tclass_datum; struct ebitmap *sattr, *tattr; struct ebitmap_node *snode, *tnode; unsigned int i, j; avd->allowed = 0; avd->auditallow = 0; avd->auditdeny = 0xffffffff; if (xperms) { memset(&xperms->drivers, 0, sizeof(xperms->drivers)); xperms->len = 0; } if (unlikely(!tclass || tclass > policydb->p_classes.nprim)) { if (printk_ratelimit()) pr_warn("SELinux: Invalid class %hu\n", tclass); return; } tclass_datum = policydb->class_val_to_struct[tclass - 1]; /* * If a specific type enforcement rule was defined for * this permission check, then use it. */ avkey.target_class = tclass; avkey.specified = AVTAB_AV | AVTAB_XPERMS; sattr = &policydb->type_attr_map_array[scontext->type - 1]; tattr = &policydb->type_attr_map_array[tcontext->type - 1]; ebitmap_for_each_positive_bit(sattr, snode, i) { ebitmap_for_each_positive_bit(tattr, tnode, j) { avkey.source_type = i + 1; avkey.target_type = j + 1; for (node = avtab_search_node(&policydb->te_avtab, &avkey); node; node = avtab_search_node_next(node, avkey.specified)) { if (node->key.specified == AVTAB_ALLOWED) avd->allowed |= node->datum.u.data; else if (node->key.specified == AVTAB_AUDITALLOW) avd->auditallow |= node->datum.u.data; else if (node->key.specified == AVTAB_AUDITDENY) avd->auditdeny &= node->datum.u.data; else if (xperms && (node->key.specified & AVTAB_XPERMS)) services_compute_xperms_drivers(xperms, node); } /* Check conditional av table for additional permissions */ cond_compute_av(&policydb->te_cond_avtab, &avkey, avd, xperms); } } /* * Remove any permissions prohibited by a constraint (this includes * the MLS policy). */ constraint = tclass_datum->constraints; while (constraint) { if ((constraint->permissions & (avd->allowed)) && !constraint_expr_eval(policydb, scontext, tcontext, NULL, constraint->expr)) { avd->allowed &= ~(constraint->permissions); } constraint = constraint->next; } /* * If checking process transition permission and the * role is changing, then check the (current_role, new_role) * pair. */ if (tclass == policydb->process_class && (avd->allowed & policydb->process_trans_perms) && scontext->role != tcontext->role) { for (ra = policydb->role_allow; ra; ra = ra->next) { if (scontext->role == ra->role && tcontext->role == ra->new_role) break; } if (!ra) avd->allowed &= ~policydb->process_trans_perms; } /* * If the given source and target types have boundary * constraint, lazy checks have to mask any violated * permission and notice it to userspace via audit. */ type_attribute_bounds_av(policydb, scontext, tcontext, tclass, avd); } static int security_validtrans_handle_fail(struct selinux_state *state, struct selinux_policy *policy, struct sidtab_entry *oentry, struct sidtab_entry *nentry, struct sidtab_entry *tentry, u16 tclass) { struct policydb *p = &policy->policydb; struct sidtab *sidtab = policy->sidtab; char *o = NULL, *n = NULL, *t = NULL; u32 olen, nlen, tlen; if (sidtab_entry_to_string(p, sidtab, oentry, &o, &olen)) goto out; if (sidtab_entry_to_string(p, sidtab, nentry, &n, &nlen)) goto out; if (sidtab_entry_to_string(p, sidtab, tentry, &t, &tlen)) goto out; audit_log(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR, "op=security_validate_transition seresult=denied" " oldcontext=%s newcontext=%s taskcontext=%s tclass=%s", o, n, t, sym_name(p, SYM_CLASSES, tclass-1)); out: kfree(o); kfree(n); kfree(t); if (!enforcing_enabled(state)) return 0; return -EPERM; } static int security_compute_validatetrans(struct selinux_state *state, u32 oldsid, u32 newsid, u32 tasksid, u16 orig_tclass, bool user) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct sidtab_entry *oentry; struct sidtab_entry *nentry; struct sidtab_entry *tentry; struct class_datum *tclass_datum; struct constraint_node *constraint; u16 tclass; int rc = 0; if (!selinux_initialized(state)) return 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; if (!user) tclass = unmap_class(&policy->map, orig_tclass); else tclass = orig_tclass; if (!tclass || tclass > policydb->p_classes.nprim) { rc = -EINVAL; goto out; } tclass_datum = policydb->class_val_to_struct[tclass - 1]; oentry = sidtab_search_entry(sidtab, oldsid); if (!oentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, oldsid); rc = -EINVAL; goto out; } nentry = sidtab_search_entry(sidtab, newsid); if (!nentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, newsid); rc = -EINVAL; goto out; } tentry = sidtab_search_entry(sidtab, tasksid); if (!tentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tasksid); rc = -EINVAL; goto out; } constraint = tclass_datum->validatetrans; while (constraint) { if (!constraint_expr_eval(policydb, &oentry->context, &nentry->context, &tentry->context, constraint->expr)) { if (user) rc = -EPERM; else rc = security_validtrans_handle_fail(state, policy, oentry, nentry, tentry, tclass); goto out; } constraint = constraint->next; } out: rcu_read_unlock(); return rc; } int security_validate_transition_user(struct selinux_state *state, u32 oldsid, u32 newsid, u32 tasksid, u16 tclass) { return security_compute_validatetrans(state, oldsid, newsid, tasksid, tclass, true); } int security_validate_transition(struct selinux_state *state, u32 oldsid, u32 newsid, u32 tasksid, u16 orig_tclass) { return security_compute_validatetrans(state, oldsid, newsid, tasksid, orig_tclass, false); } /* * security_bounded_transition - check whether the given * transition is directed to bounded, or not. * It returns 0, if @newsid is bounded by @oldsid. * Otherwise, it returns error code. * * @oldsid : current security identifier * @newsid : destinated security identifier */ int security_bounded_transition(struct selinux_state *state, u32 old_sid, u32 new_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct sidtab_entry *old_entry, *new_entry; struct type_datum *type; int index; int rc; if (!selinux_initialized(state)) return 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; rc = -EINVAL; old_entry = sidtab_search_entry(sidtab, old_sid); if (!old_entry) { pr_err("SELinux: %s: unrecognized SID %u\n", __func__, old_sid); goto out; } rc = -EINVAL; new_entry = sidtab_search_entry(sidtab, new_sid); if (!new_entry) { pr_err("SELinux: %s: unrecognized SID %u\n", __func__, new_sid); goto out; } rc = 0; /* type/domain unchanged */ if (old_entry->context.type == new_entry->context.type) goto out; index = new_entry->context.type; while (true) { type = policydb->type_val_to_struct[index - 1]; BUG_ON(!type); /* not bounded anymore */ rc = -EPERM; if (!type->bounds) break; /* @newsid is bounded by @oldsid */ rc = 0; if (type->bounds == old_entry->context.type) break; index = type->bounds; } if (rc) { char *old_name = NULL; char *new_name = NULL; u32 length; if (!sidtab_entry_to_string(policydb, sidtab, old_entry, &old_name, &length) && !sidtab_entry_to_string(policydb, sidtab, new_entry, &new_name, &length)) { audit_log(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR, "op=security_bounded_transition " "seresult=denied " "oldcontext=%s newcontext=%s", old_name, new_name); } kfree(new_name); kfree(old_name); } out: rcu_read_unlock(); return rc; } static void avd_init(struct selinux_policy *policy, struct av_decision *avd) { avd->allowed = 0; avd->auditallow = 0; avd->auditdeny = 0xffffffff; if (policy) avd->seqno = policy->latest_granting; else avd->seqno = 0; avd->flags = 0; } void services_compute_xperms_decision(struct extended_perms_decision *xpermd, struct avtab_node *node) { unsigned int i; if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLFUNCTION) { if (xpermd->driver != node->datum.u.xperms->driver) return; } else if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLDRIVER) { if (!security_xperm_test(node->datum.u.xperms->perms.p, xpermd->driver)) return; } else { pr_warn_once( "SELinux: unknown extended permission (%u) will be ignored\n", node->datum.u.xperms->specified); return; } if (node->key.specified == AVTAB_XPERMS_ALLOWED) { xpermd->used |= XPERMS_ALLOWED; if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLDRIVER) { memset(xpermd->allowed->p, 0xff, sizeof(xpermd->allowed->p)); } if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLFUNCTION) { for (i = 0; i < ARRAY_SIZE(xpermd->allowed->p); i++) xpermd->allowed->p[i] |= node->datum.u.xperms->perms.p[i]; } } else if (node->key.specified == AVTAB_XPERMS_AUDITALLOW) { xpermd->used |= XPERMS_AUDITALLOW; if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLDRIVER) { memset(xpermd->auditallow->p, 0xff, sizeof(xpermd->auditallow->p)); } if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLFUNCTION) { for (i = 0; i < ARRAY_SIZE(xpermd->auditallow->p); i++) xpermd->auditallow->p[i] |= node->datum.u.xperms->perms.p[i]; } } else if (node->key.specified == AVTAB_XPERMS_DONTAUDIT) { xpermd->used |= XPERMS_DONTAUDIT; if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLDRIVER) { memset(xpermd->dontaudit->p, 0xff, sizeof(xpermd->dontaudit->p)); } if (node->datum.u.xperms->specified == AVTAB_XPERMS_IOCTLFUNCTION) { for (i = 0; i < ARRAY_SIZE(xpermd->dontaudit->p); i++) xpermd->dontaudit->p[i] |= node->datum.u.xperms->perms.p[i]; } } else { pr_warn_once("SELinux: unknown specified key (%u)\n", node->key.specified); } } void security_compute_xperms_decision(struct selinux_state *state, u32 ssid, u32 tsid, u16 orig_tclass, u8 driver, struct extended_perms_decision *xpermd) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; u16 tclass; struct context *scontext, *tcontext; struct avtab_key avkey; struct avtab_node *node; struct ebitmap *sattr, *tattr; struct ebitmap_node *snode, *tnode; unsigned int i, j; xpermd->driver = driver; xpermd->used = 0; memset(xpermd->allowed->p, 0, sizeof(xpermd->allowed->p)); memset(xpermd->auditallow->p, 0, sizeof(xpermd->auditallow->p)); memset(xpermd->dontaudit->p, 0, sizeof(xpermd->dontaudit->p)); rcu_read_lock(); if (!selinux_initialized(state)) goto allow; policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; scontext = sidtab_search(sidtab, ssid); if (!scontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, ssid); goto out; } tcontext = sidtab_search(sidtab, tsid); if (!tcontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tsid); goto out; } tclass = unmap_class(&policy->map, orig_tclass); if (unlikely(orig_tclass && !tclass)) { if (policydb->allow_unknown) goto allow; goto out; } if (unlikely(!tclass || tclass > policydb->p_classes.nprim)) { pr_warn_ratelimited("SELinux: Invalid class %hu\n", tclass); goto out; } avkey.target_class = tclass; avkey.specified = AVTAB_XPERMS; sattr = &policydb->type_attr_map_array[scontext->type - 1]; tattr = &policydb->type_attr_map_array[tcontext->type - 1]; ebitmap_for_each_positive_bit(sattr, snode, i) { ebitmap_for_each_positive_bit(tattr, tnode, j) { avkey.source_type = i + 1; avkey.target_type = j + 1; for (node = avtab_search_node(&policydb->te_avtab, &avkey); node; node = avtab_search_node_next(node, avkey.specified)) services_compute_xperms_decision(xpermd, node); cond_compute_xperms(&policydb->te_cond_avtab, &avkey, xpermd); } } out: rcu_read_unlock(); return; allow: memset(xpermd->allowed->p, 0xff, sizeof(xpermd->allowed->p)); goto out; } /** * security_compute_av - Compute access vector decisions. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @avd: access vector decisions * @xperms: extended permissions * * Compute a set of access vector decisions based on the * SID pair (@ssid, @tsid) for the permissions in @tclass. */ void security_compute_av(struct selinux_state *state, u32 ssid, u32 tsid, u16 orig_tclass, struct av_decision *avd, struct extended_perms *xperms) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; u16 tclass; struct context *scontext = NULL, *tcontext = NULL; rcu_read_lock(); policy = rcu_dereference(state->policy); avd_init(policy, avd); xperms->len = 0; if (!selinux_initialized(state)) goto allow; policydb = &policy->policydb; sidtab = policy->sidtab; scontext = sidtab_search(sidtab, ssid); if (!scontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, ssid); goto out; } /* permissive domain? */ if (ebitmap_get_bit(&policydb->permissive_map, scontext->type)) avd->flags |= AVD_FLAGS_PERMISSIVE; tcontext = sidtab_search(sidtab, tsid); if (!tcontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tsid); goto out; } tclass = unmap_class(&policy->map, orig_tclass); if (unlikely(orig_tclass && !tclass)) { if (policydb->allow_unknown) goto allow; goto out; } context_struct_compute_av(policydb, scontext, tcontext, tclass, avd, xperms); map_decision(&policy->map, orig_tclass, avd, policydb->allow_unknown); out: rcu_read_unlock(); return; allow: avd->allowed = 0xffffffff; goto out; } void security_compute_av_user(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct context *scontext = NULL, *tcontext = NULL; rcu_read_lock(); policy = rcu_dereference(state->policy); avd_init(policy, avd); if (!selinux_initialized(state)) goto allow; policydb = &policy->policydb; sidtab = policy->sidtab; scontext = sidtab_search(sidtab, ssid); if (!scontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, ssid); goto out; } /* permissive domain? */ if (ebitmap_get_bit(&policydb->permissive_map, scontext->type)) avd->flags |= AVD_FLAGS_PERMISSIVE; tcontext = sidtab_search(sidtab, tsid); if (!tcontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tsid); goto out; } if (unlikely(!tclass)) { if (policydb->allow_unknown) goto allow; goto out; } context_struct_compute_av(policydb, scontext, tcontext, tclass, avd, NULL); out: rcu_read_unlock(); return; allow: avd->allowed = 0xffffffff; goto out; } /* * Write the security context string representation of * the context structure `context' into a dynamically * allocated string of the correct size. Set `*scontext' * to point to this string and set `*scontext_len' to * the length of the string. */ static int context_struct_to_string(struct policydb *p, struct context *context, char **scontext, u32 *scontext_len) { char *scontextp; if (scontext) *scontext = NULL; *scontext_len = 0; if (context->len) { *scontext_len = context->len; if (scontext) { *scontext = kstrdup(context->str, GFP_ATOMIC); if (!(*scontext)) return -ENOMEM; } return 0; } /* Compute the size of the context. */ *scontext_len += strlen(sym_name(p, SYM_USERS, context->user - 1)) + 1; *scontext_len += strlen(sym_name(p, SYM_ROLES, context->role - 1)) + 1; *scontext_len += strlen(sym_name(p, SYM_TYPES, context->type - 1)) + 1; *scontext_len += mls_compute_context_len(p, context); if (!scontext) return 0; /* Allocate space for the context; caller must free this space. */ scontextp = kmalloc(*scontext_len, GFP_ATOMIC); if (!scontextp) return -ENOMEM; *scontext = scontextp; /* * Copy the user name, role name and type name into the context. */ scontextp += sprintf(scontextp, "%s:%s:%s", sym_name(p, SYM_USERS, context->user - 1), sym_name(p, SYM_ROLES, context->role - 1), sym_name(p, SYM_TYPES, context->type - 1)); mls_sid_to_context(p, context, &scontextp); *scontextp = 0; return 0; } static int sidtab_entry_to_string(struct policydb *p, struct sidtab *sidtab, struct sidtab_entry *entry, char **scontext, u32 *scontext_len) { int rc = sidtab_sid2str_get(sidtab, entry, scontext, scontext_len); if (rc != -ENOENT) return rc; rc = context_struct_to_string(p, &entry->context, scontext, scontext_len); if (!rc && scontext) sidtab_sid2str_put(sidtab, entry, *scontext, *scontext_len); return rc; } #include "initial_sid_to_string.h" int security_sidtab_hash_stats(struct selinux_state *state, char *page) { struct selinux_policy *policy; int rc; if (!selinux_initialized(state)) { pr_err("SELinux: %s: called before initial load_policy\n", __func__); return -EINVAL; } rcu_read_lock(); policy = rcu_dereference(state->policy); rc = sidtab_hash_stats(policy->sidtab, page); rcu_read_unlock(); return rc; } const char *security_get_initial_sid_context(u32 sid) { if (unlikely(sid > SECINITSID_NUM)) return NULL; return initial_sid_to_string[sid]; } static int security_sid_to_context_core(struct selinux_state *state, u32 sid, char **scontext, u32 *scontext_len, int force, int only_invalid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct sidtab_entry *entry; int rc = 0; if (scontext) *scontext = NULL; *scontext_len = 0; if (!selinux_initialized(state)) { if (sid <= SECINITSID_NUM) { char *scontextp; const char *s = initial_sid_to_string[sid]; if (!s) return -EINVAL; *scontext_len = strlen(s) + 1; if (!scontext) return 0; scontextp = kmemdup(s, *scontext_len, GFP_ATOMIC); if (!scontextp) return -ENOMEM; *scontext = scontextp; return 0; } pr_err("SELinux: %s: called before initial " "load_policy on unknown SID %d\n", __func__, sid); return -EINVAL; } rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; if (force) entry = sidtab_search_entry_force(sidtab, sid); else entry = sidtab_search_entry(sidtab, sid); if (!entry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, sid); rc = -EINVAL; goto out_unlock; } if (only_invalid && !entry->context.len) goto out_unlock; rc = sidtab_entry_to_string(policydb, sidtab, entry, scontext, scontext_len); out_unlock: rcu_read_unlock(); return rc; } /** * security_sid_to_context - Obtain a context for a given SID. * @sid: security identifier, SID * @scontext: security context * @scontext_len: length in bytes * * Write the string representation of the context associated with @sid * into a dynamically allocated string of the correct size. Set @scontext * to point to this string and set @scontext_len to the length of the string. */ int security_sid_to_context(struct selinux_state *state, u32 sid, char **scontext, u32 *scontext_len) { return security_sid_to_context_core(state, sid, scontext, scontext_len, 0, 0); } int security_sid_to_context_force(struct selinux_state *state, u32 sid, char **scontext, u32 *scontext_len) { return security_sid_to_context_core(state, sid, scontext, scontext_len, 1, 0); } /** * security_sid_to_context_inval - Obtain a context for a given SID if it * is invalid. * @sid: security identifier, SID * @scontext: security context * @scontext_len: length in bytes * * Write the string representation of the context associated with @sid * into a dynamically allocated string of the correct size, but only if the * context is invalid in the current policy. Set @scontext to point to * this string (or NULL if the context is valid) and set @scontext_len to * the length of the string (or 0 if the context is valid). */ int security_sid_to_context_inval(struct selinux_state *state, u32 sid, char **scontext, u32 *scontext_len) { return security_sid_to_context_core(state, sid, scontext, scontext_len, 1, 1); } /* * Caveat: Mutates scontext. */ static int string_to_context_struct(struct policydb *pol, struct sidtab *sidtabp, char *scontext, struct context *ctx, u32 def_sid) { struct role_datum *role; struct type_datum *typdatum; struct user_datum *usrdatum; char *scontextp, *p, oldc; int rc = 0; context_init(ctx); /* Parse the security context. */ rc = -EINVAL; scontextp = (char *) scontext; /* Extract the user. */ p = scontextp; while (*p && *p != ':') p++; if (*p == 0) goto out; *p++ = 0; usrdatum = symtab_search(&pol->p_users, scontextp); if (!usrdatum) goto out; ctx->user = usrdatum->value; /* Extract role. */ scontextp = p; while (*p && *p != ':') p++; if (*p == 0) goto out; *p++ = 0; role = symtab_search(&pol->p_roles, scontextp); if (!role) goto out; ctx->role = role->value; /* Extract type. */ scontextp = p; while (*p && *p != ':') p++; oldc = *p; *p++ = 0; typdatum = symtab_search(&pol->p_types, scontextp); if (!typdatum || typdatum->attribute) goto out; ctx->type = typdatum->value; rc = mls_context_to_sid(pol, oldc, p, ctx, sidtabp, def_sid); if (rc) goto out; /* Check the validity of the new context. */ rc = -EINVAL; if (!policydb_context_isvalid(pol, ctx)) goto out; rc = 0; out: if (rc) context_destroy(ctx); return rc; } static int security_context_to_sid_core(struct selinux_state *state, const char *scontext, u32 scontext_len, u32 *sid, u32 def_sid, gfp_t gfp_flags, int force) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; char *scontext2, *str = NULL; struct context context; int rc = 0; /* An empty security context is never valid. */ if (!scontext_len) return -EINVAL; /* Copy the string to allow changes and ensure a NUL terminator */ scontext2 = kmemdup_nul(scontext, scontext_len, gfp_flags); if (!scontext2) return -ENOMEM; if (!selinux_initialized(state)) { int i; for (i = 1; i < SECINITSID_NUM; i++) { const char *s = initial_sid_to_string[i]; if (s && !strcmp(s, scontext2)) { *sid = i; goto out; } } *sid = SECINITSID_KERNEL; goto out; } *sid = SECSID_NULL; if (force) { /* Save another copy for storing in uninterpreted form */ rc = -ENOMEM; str = kstrdup(scontext2, gfp_flags); if (!str) goto out; } retry: rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; rc = string_to_context_struct(policydb, sidtab, scontext2, &context, def_sid); if (rc == -EINVAL && force) { context.str = str; context.len = strlen(str) + 1; str = NULL; } else if (rc) goto out_unlock; rc = sidtab_context_to_sid(sidtab, &context, sid); if (rc == -ESTALE) { rcu_read_unlock(); if (context.str) { str = context.str; context.str = NULL; } context_destroy(&context); goto retry; } context_destroy(&context); out_unlock: rcu_read_unlock(); out: kfree(scontext2); kfree(str); return rc; } /** * security_context_to_sid - Obtain a SID for a given security context. * @scontext: security context * @scontext_len: length in bytes * @sid: security identifier, SID * @gfp: context for the allocation * * Obtains a SID associated with the security context that * has the string representation specified by @scontext. * Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient * memory is available, or 0 on success. */ int security_context_to_sid(struct selinux_state *state, const char *scontext, u32 scontext_len, u32 *sid, gfp_t gfp) { return security_context_to_sid_core(state, scontext, scontext_len, sid, SECSID_NULL, gfp, 0); } int security_context_str_to_sid(struct selinux_state *state, const char *scontext, u32 *sid, gfp_t gfp) { return security_context_to_sid(state, scontext, strlen(scontext), sid, gfp); } /** * security_context_to_sid_default - Obtain a SID for a given security context, * falling back to specified default if needed. * * @scontext: security context * @scontext_len: length in bytes * @sid: security identifier, SID * @def_sid: default SID to assign on error * * Obtains a SID associated with the security context that * has the string representation specified by @scontext. * The default SID is passed to the MLS layer to be used to allow * kernel labeling of the MLS field if the MLS field is not present * (for upgrading to MLS without full relabel). * Implicitly forces adding of the context even if it cannot be mapped yet. * Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient * memory is available, or 0 on success. */ int security_context_to_sid_default(struct selinux_state *state, const char *scontext, u32 scontext_len, u32 *sid, u32 def_sid, gfp_t gfp_flags) { return security_context_to_sid_core(state, scontext, scontext_len, sid, def_sid, gfp_flags, 1); } int security_context_to_sid_force(struct selinux_state *state, const char *scontext, u32 scontext_len, u32 *sid) { return security_context_to_sid_core(state, scontext, scontext_len, sid, SECSID_NULL, GFP_KERNEL, 1); } static int compute_sid_handle_invalid_context( struct selinux_state *state, struct selinux_policy *policy, struct sidtab_entry *sentry, struct sidtab_entry *tentry, u16 tclass, struct context *newcontext) { struct policydb *policydb = &policy->policydb; struct sidtab *sidtab = policy->sidtab; char *s = NULL, *t = NULL, *n = NULL; u32 slen, tlen, nlen; struct audit_buffer *ab; if (sidtab_entry_to_string(policydb, sidtab, sentry, &s, &slen)) goto out; if (sidtab_entry_to_string(policydb, sidtab, tentry, &t, &tlen)) goto out; if (context_struct_to_string(policydb, newcontext, &n, &nlen)) goto out; ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); audit_log_format(ab, "op=security_compute_sid invalid_context="); /* no need to record the NUL with untrusted strings */ audit_log_n_untrustedstring(ab, n, nlen - 1); audit_log_format(ab, " scontext=%s tcontext=%s tclass=%s", s, t, sym_name(policydb, SYM_CLASSES, tclass-1)); audit_log_end(ab); out: kfree(s); kfree(t); kfree(n); if (!enforcing_enabled(state)) return 0; return -EACCES; } static void filename_compute_type(struct policydb *policydb, struct context *newcontext, u32 stype, u32 ttype, u16 tclass, const char *objname) { struct filename_trans_key ft; struct filename_trans_datum *datum; /* * Most filename trans rules are going to live in specific directories * like /dev or /var/run. This bitmap will quickly skip rule searches * if the ttype does not contain any rules. */ if (!ebitmap_get_bit(&policydb->filename_trans_ttypes, ttype)) return; ft.ttype = ttype; ft.tclass = tclass; ft.name = objname; datum = policydb_filenametr_search(policydb, &ft); while (datum) { if (ebitmap_get_bit(&datum->stypes, stype - 1)) { newcontext->type = datum->otype; return; } datum = datum->next; } } static int security_compute_sid(struct selinux_state *state, u32 ssid, u32 tsid, u16 orig_tclass, u32 specified, const char *objname, u32 *out_sid, bool kern) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct class_datum *cladatum; struct context *scontext, *tcontext, newcontext; struct sidtab_entry *sentry, *tentry; struct avtab_key avkey; struct avtab_datum *avdatum; struct avtab_node *node; u16 tclass; int rc = 0; bool sock; if (!selinux_initialized(state)) { switch (orig_tclass) { case SECCLASS_PROCESS: /* kernel value */ *out_sid = ssid; break; default: *out_sid = tsid; break; } goto out; } retry: cladatum = NULL; context_init(&newcontext); rcu_read_lock(); policy = rcu_dereference(state->policy); if (kern) { tclass = unmap_class(&policy->map, orig_tclass); sock = security_is_socket_class(orig_tclass); } else { tclass = orig_tclass; sock = security_is_socket_class(map_class(&policy->map, tclass)); } policydb = &policy->policydb; sidtab = policy->sidtab; sentry = sidtab_search_entry(sidtab, ssid); if (!sentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, ssid); rc = -EINVAL; goto out_unlock; } tentry = sidtab_search_entry(sidtab, tsid); if (!tentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tsid); rc = -EINVAL; goto out_unlock; } scontext = &sentry->context; tcontext = &tentry->context; if (tclass && tclass <= policydb->p_classes.nprim) cladatum = policydb->class_val_to_struct[tclass - 1]; /* Set the user identity. */ switch (specified) { case AVTAB_TRANSITION: case AVTAB_CHANGE: if (cladatum && cladatum->default_user == DEFAULT_TARGET) { newcontext.user = tcontext->user; } else { /* notice this gets both DEFAULT_SOURCE and unset */ /* Use the process user identity. */ newcontext.user = scontext->user; } break; case AVTAB_MEMBER: /* Use the related object owner. */ newcontext.user = tcontext->user; break; } /* Set the role to default values. */ if (cladatum && cladatum->default_role == DEFAULT_SOURCE) { newcontext.role = scontext->role; } else if (cladatum && cladatum->default_role == DEFAULT_TARGET) { newcontext.role = tcontext->role; } else { if ((tclass == policydb->process_class) || sock) newcontext.role = scontext->role; else newcontext.role = OBJECT_R_VAL; } /* Set the type to default values. */ if (cladatum && cladatum->default_type == DEFAULT_SOURCE) { newcontext.type = scontext->type; } else if (cladatum && cladatum->default_type == DEFAULT_TARGET) { newcontext.type = tcontext->type; } else { if ((tclass == policydb->process_class) || sock) { /* Use the type of process. */ newcontext.type = scontext->type; } else { /* Use the type of the related object. */ newcontext.type = tcontext->type; } } /* Look for a type transition/member/change rule. */ avkey.source_type = scontext->type; avkey.target_type = tcontext->type; avkey.target_class = tclass; avkey.specified = specified; avdatum = avtab_search(&policydb->te_avtab, &avkey); /* If no permanent rule, also check for enabled conditional rules */ if (!avdatum) { node = avtab_search_node(&policydb->te_cond_avtab, &avkey); for (; node; node = avtab_search_node_next(node, specified)) { if (node->key.specified & AVTAB_ENABLED) { avdatum = &node->datum; break; } } } if (avdatum) { /* Use the type from the type transition/member/change rule. */ newcontext.type = avdatum->u.data; } /* if we have a objname this is a file trans check so check those rules */ if (objname) filename_compute_type(policydb, &newcontext, scontext->type, tcontext->type, tclass, objname); /* Check for class-specific changes. */ if (specified & AVTAB_TRANSITION) { /* Look for a role transition rule. */ struct role_trans_datum *rtd; struct role_trans_key rtk = { .role = scontext->role, .type = tcontext->type, .tclass = tclass, }; rtd = policydb_roletr_search(policydb, &rtk); if (rtd) newcontext.role = rtd->new_role; } /* Set the MLS attributes. This is done last because it may allocate memory. */ rc = mls_compute_sid(policydb, scontext, tcontext, tclass, specified, &newcontext, sock); if (rc) goto out_unlock; /* Check the validity of the context. */ if (!policydb_context_isvalid(policydb, &newcontext)) { rc = compute_sid_handle_invalid_context(state, policy, sentry, tentry, tclass, &newcontext); if (rc) goto out_unlock; } /* Obtain the sid for the context. */ rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); context_destroy(&newcontext); goto retry; } out_unlock: rcu_read_unlock(); context_destroy(&newcontext); out: return rc; } /** * security_transition_sid - Compute the SID for a new subject/object. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @out_sid: security identifier for new subject/object * * Compute a SID to use for labeling a new subject or object in the * class @tclass based on a SID pair (@ssid, @tsid). * Return -%EINVAL if any of the parameters are invalid, -%ENOMEM * if insufficient memory is available, or %0 if the new SID was * computed successfully. */ int security_transition_sid(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, const struct qstr *qstr, u32 *out_sid) { return security_compute_sid(state, ssid, tsid, tclass, AVTAB_TRANSITION, qstr ? qstr->name : NULL, out_sid, true); } int security_transition_sid_user(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, const char *objname, u32 *out_sid) { return security_compute_sid(state, ssid, tsid, tclass, AVTAB_TRANSITION, objname, out_sid, false); } /** * security_member_sid - Compute the SID for member selection. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @out_sid: security identifier for selected member * * Compute a SID to use when selecting a member of a polyinstantiated * object of class @tclass based on a SID pair (@ssid, @tsid). * Return -%EINVAL if any of the parameters are invalid, -%ENOMEM * if insufficient memory is available, or %0 if the SID was * computed successfully. */ int security_member_sid(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 *out_sid) { return security_compute_sid(state, ssid, tsid, tclass, AVTAB_MEMBER, NULL, out_sid, false); } /** * security_change_sid - Compute the SID for object relabeling. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @out_sid: security identifier for selected member * * Compute a SID to use for relabeling an object of class @tclass * based on a SID pair (@ssid, @tsid). * Return -%EINVAL if any of the parameters are invalid, -%ENOMEM * if insufficient memory is available, or %0 if the SID was * computed successfully. */ int security_change_sid(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 *out_sid) { return security_compute_sid(state, ssid, tsid, tclass, AVTAB_CHANGE, NULL, out_sid, false); } static inline int convert_context_handle_invalid_context( struct selinux_state *state, struct policydb *policydb, struct context *context) { char *s; u32 len; if (enforcing_enabled(state)) return -EINVAL; if (!context_struct_to_string(policydb, context, &s, &len)) { pr_warn("SELinux: Context %s would be invalid if enforcing\n", s); kfree(s); } return 0; } /* * Convert the values in the security context * structure `oldc' from the values specified * in the policy `p->oldp' to the values specified * in the policy `p->newp', storing the new context * in `newc'. Verify that the context is valid * under the new policy. */ static int convert_context(struct context *oldc, struct context *newc, void *p, gfp_t gfp_flags) { struct convert_context_args *args; struct ocontext *oc; struct role_datum *role; struct type_datum *typdatum; struct user_datum *usrdatum; char *s; u32 len; int rc; args = p; if (oldc->str) { s = kstrdup(oldc->str, gfp_flags); if (!s) return -ENOMEM; rc = string_to_context_struct(args->newp, NULL, s, newc, SECSID_NULL); if (rc == -EINVAL) { /* * Retain string representation for later mapping. * * IMPORTANT: We need to copy the contents of oldc->str * back into s again because string_to_context_struct() * may have garbled it. */ memcpy(s, oldc->str, oldc->len); context_init(newc); newc->str = s; newc->len = oldc->len; return 0; } kfree(s); if (rc) { /* Other error condition, e.g. ENOMEM. */ pr_err("SELinux: Unable to map context %s, rc = %d.\n", oldc->str, -rc); return rc; } pr_info("SELinux: Context %s became valid (mapped).\n", oldc->str); return 0; } context_init(newc); /* Convert the user. */ rc = -EINVAL; usrdatum = symtab_search(&args->newp->p_users, sym_name(args->oldp, SYM_USERS, oldc->user - 1)); if (!usrdatum) goto bad; newc->user = usrdatum->value; /* Convert the role. */ rc = -EINVAL; role = symtab_search(&args->newp->p_roles, sym_name(args->oldp, SYM_ROLES, oldc->role - 1)); if (!role) goto bad; newc->role = role->value; /* Convert the type. */ rc = -EINVAL; typdatum = symtab_search(&args->newp->p_types, sym_name(args->oldp, SYM_TYPES, oldc->type - 1)); if (!typdatum) goto bad; newc->type = typdatum->value; /* Convert the MLS fields if dealing with MLS policies */ if (args->oldp->mls_enabled && args->newp->mls_enabled) { rc = mls_convert_context(args->oldp, args->newp, oldc, newc); if (rc) goto bad; } else if (!args->oldp->mls_enabled && args->newp->mls_enabled) { /* * Switching between non-MLS and MLS policy: * ensure that the MLS fields of the context for all * existing entries in the sidtab are filled in with a * suitable default value, likely taken from one of the * initial SIDs. */ oc = args->newp->ocontexts[OCON_ISID]; while (oc && oc->sid[0] != SECINITSID_UNLABELED) oc = oc->next; rc = -EINVAL; if (!oc) { pr_err("SELinux: unable to look up" " the initial SIDs list\n"); goto bad; } rc = mls_range_set(newc, &oc->context[0].range); if (rc) goto bad; } /* Check the validity of the new context. */ if (!policydb_context_isvalid(args->newp, newc)) { rc = convert_context_handle_invalid_context(args->state, args->oldp, oldc); if (rc) goto bad; } return 0; bad: /* Map old representation to string and save it. */ rc = context_struct_to_string(args->oldp, oldc, &s, &len); if (rc) return rc; context_destroy(newc); newc->str = s; newc->len = len; pr_info("SELinux: Context %s became invalid (unmapped).\n", newc->str); return 0; } static void security_load_policycaps(struct selinux_state *state, struct selinux_policy *policy) { struct policydb *p; unsigned int i; struct ebitmap_node *node; p = &policy->policydb; for (i = 0; i < ARRAY_SIZE(state->policycap); i++) WRITE_ONCE(state->policycap[i], ebitmap_get_bit(&p->policycaps, i)); for (i = 0; i < ARRAY_SIZE(selinux_policycap_names); i++) pr_info("SELinux: policy capability %s=%d\n", selinux_policycap_names[i], ebitmap_get_bit(&p->policycaps, i)); ebitmap_for_each_positive_bit(&p->policycaps, node, i) { if (i >= ARRAY_SIZE(selinux_policycap_names)) pr_info("SELinux: unknown policy capability %u\n", i); } } static int security_preserve_bools(struct selinux_policy *oldpolicy, struct selinux_policy *newpolicy); static void selinux_policy_free(struct selinux_policy *policy) { if (!policy) return; sidtab_destroy(policy->sidtab); kfree(policy->map.mapping); policydb_destroy(&policy->policydb); kfree(policy->sidtab); kfree(policy); } static void selinux_policy_cond_free(struct selinux_policy *policy) { cond_policydb_destroy_dup(&policy->policydb); kfree(policy); } void selinux_policy_cancel(struct selinux_state *state, struct selinux_load_state *load_state) { struct selinux_policy *oldpolicy; oldpolicy = rcu_dereference_protected(state->policy, lockdep_is_held(&state->policy_mutex)); sidtab_cancel_convert(oldpolicy->sidtab); selinux_policy_free(load_state->policy); kfree(load_state->convert_data); } static void selinux_notify_policy_change(struct selinux_state *state, u32 seqno) { /* Flush external caches and notify userspace of policy load */ avc_ss_reset(state->avc, seqno); selnl_notify_policyload(seqno); selinux_status_update_policyload(state, seqno); selinux_netlbl_cache_invalidate(); selinux_xfrm_notify_policyload(); } void selinux_policy_commit(struct selinux_state *state, struct selinux_load_state *load_state) { struct selinux_policy *oldpolicy, *newpolicy = load_state->policy; unsigned long flags; u32 seqno; oldpolicy = rcu_dereference_protected(state->policy, lockdep_is_held(&state->policy_mutex)); /* If switching between different policy types, log MLS status */ if (oldpolicy) { if (oldpolicy->policydb.mls_enabled && !newpolicy->policydb.mls_enabled) pr_info("SELinux: Disabling MLS support...\n"); else if (!oldpolicy->policydb.mls_enabled && newpolicy->policydb.mls_enabled) pr_info("SELinux: Enabling MLS support...\n"); } /* Set latest granting seqno for new policy. */ if (oldpolicy) newpolicy->latest_granting = oldpolicy->latest_granting + 1; else newpolicy->latest_granting = 1; seqno = newpolicy->latest_granting; /* Install the new policy. */ if (oldpolicy) { sidtab_freeze_begin(oldpolicy->sidtab, &flags); rcu_assign_pointer(state->policy, newpolicy); sidtab_freeze_end(oldpolicy->sidtab, &flags); } else { rcu_assign_pointer(state->policy, newpolicy); } /* Load the policycaps from the new policy */ security_load_policycaps(state, newpolicy); if (!selinux_initialized(state)) { /* * After first policy load, the security server is * marked as initialized and ready to handle requests and * any objects created prior to policy load are then labeled. */ selinux_mark_initialized(state); selinux_complete_init(); } /* Free the old policy */ synchronize_rcu(); selinux_policy_free(oldpolicy); kfree(load_state->convert_data); /* Notify others of the policy change */ selinux_notify_policy_change(state, seqno); } /** * security_load_policy - Load a security policy configuration. * @data: binary policy data * @len: length of data in bytes * * Load a new set of security policy configuration data, * validate it and convert the SID table as necessary. * This function will flush the access vector cache after * loading the new policy. */ int security_load_policy(struct selinux_state *state, void *data, size_t len, struct selinux_load_state *load_state) { struct selinux_policy *newpolicy, *oldpolicy; struct selinux_policy_convert_data *convert_data; int rc = 0; struct policy_file file = { data, len }, *fp = &file; newpolicy = kzalloc(sizeof(*newpolicy), GFP_KERNEL); if (!newpolicy) return -ENOMEM; newpolicy->sidtab = kzalloc(sizeof(*newpolicy->sidtab), GFP_KERNEL); if (!newpolicy->sidtab) { rc = -ENOMEM; goto err_policy; } rc = policydb_read(&newpolicy->policydb, fp); if (rc) goto err_sidtab; newpolicy->policydb.len = len; rc = selinux_set_mapping(&newpolicy->policydb, secclass_map, &newpolicy->map); if (rc) goto err_policydb; rc = policydb_load_isids(&newpolicy->policydb, newpolicy->sidtab); if (rc) { pr_err("SELinux: unable to load the initial SIDs\n"); goto err_mapping; } if (!selinux_initialized(state)) { /* First policy load, so no need to preserve state from old policy */ load_state->policy = newpolicy; load_state->convert_data = NULL; return 0; } oldpolicy = rcu_dereference_protected(state->policy, lockdep_is_held(&state->policy_mutex)); /* Preserve active boolean values from the old policy */ rc = security_preserve_bools(oldpolicy, newpolicy); if (rc) { pr_err("SELinux: unable to preserve booleans\n"); goto err_free_isids; } convert_data = kmalloc(sizeof(*convert_data), GFP_KERNEL); if (!convert_data) { rc = -ENOMEM; goto err_free_isids; } /* * Convert the internal representations of contexts * in the new SID table. */ convert_data->args.state = state; convert_data->args.oldp = &oldpolicy->policydb; convert_data->args.newp = &newpolicy->policydb; convert_data->sidtab_params.func = convert_context; convert_data->sidtab_params.args = &convert_data->args; convert_data->sidtab_params.target = newpolicy->sidtab; rc = sidtab_convert(oldpolicy->sidtab, &convert_data->sidtab_params); if (rc) { pr_err("SELinux: unable to convert the internal" " representation of contexts in the new SID" " table\n"); goto err_free_convert_data; } load_state->policy = newpolicy; load_state->convert_data = convert_data; return 0; err_free_convert_data: kfree(convert_data); err_free_isids: sidtab_destroy(newpolicy->sidtab); err_mapping: kfree(newpolicy->map.mapping); err_policydb: policydb_destroy(&newpolicy->policydb); err_sidtab: kfree(newpolicy->sidtab); err_policy: kfree(newpolicy); return rc; } /** * ocontext_to_sid - Helper to safely get sid for an ocontext * @sidtab: SID table * @c: ocontext structure * @index: index of the context entry (0 or 1) * @out_sid: pointer to the resulting SID value * * For all ocontexts except OCON_ISID the SID fields are populated * on-demand when needed. Since updating the SID value is an SMP-sensitive * operation, this helper must be used to do that safely. * * WARNING: This function may return -ESTALE, indicating that the caller * must retry the operation after re-acquiring the policy pointer! */ static int ocontext_to_sid(struct sidtab *sidtab, struct ocontext *c, size_t index, u32 *out_sid) { int rc; u32 sid; /* Ensure the associated sidtab entry is visible to this thread. */ sid = smp_load_acquire(&c->sid[index]); if (!sid) { rc = sidtab_context_to_sid(sidtab, &c->context[index], &sid); if (rc) return rc; /* * Ensure the new sidtab entry is visible to other threads * when they see the SID. */ smp_store_release(&c->sid[index], sid); } *out_sid = sid; return 0; } /** * security_port_sid - Obtain the SID for a port. * @protocol: protocol number * @port: port number * @out_sid: security identifier */ int security_port_sid(struct selinux_state *state, u8 protocol, u16 port, u32 *out_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; int rc; if (!selinux_initialized(state)) { *out_sid = SECINITSID_PORT; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_PORT]; while (c) { if (c->u.port.protocol == protocol && c->u.port.low_port <= port && c->u.port.high_port >= port) break; c = c->next; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else { *out_sid = SECINITSID_PORT; } out: rcu_read_unlock(); return rc; } /** * security_pkey_sid - Obtain the SID for a pkey. * @subnet_prefix: Subnet Prefix * @pkey_num: pkey number * @out_sid: security identifier */ int security_ib_pkey_sid(struct selinux_state *state, u64 subnet_prefix, u16 pkey_num, u32 *out_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; int rc; if (!selinux_initialized(state)) { *out_sid = SECINITSID_UNLABELED; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_IBPKEY]; while (c) { if (c->u.ibpkey.low_pkey <= pkey_num && c->u.ibpkey.high_pkey >= pkey_num && c->u.ibpkey.subnet_prefix == subnet_prefix) break; c = c->next; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else *out_sid = SECINITSID_UNLABELED; out: rcu_read_unlock(); return rc; } /** * security_ib_endport_sid - Obtain the SID for a subnet management interface. * @dev_name: device name * @port: port number * @out_sid: security identifier */ int security_ib_endport_sid(struct selinux_state *state, const char *dev_name, u8 port_num, u32 *out_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; int rc; if (!selinux_initialized(state)) { *out_sid = SECINITSID_UNLABELED; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_IBENDPORT]; while (c) { if (c->u.ibendport.port == port_num && !strncmp(c->u.ibendport.dev_name, dev_name, IB_DEVICE_NAME_MAX)) break; c = c->next; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else *out_sid = SECINITSID_UNLABELED; out: rcu_read_unlock(); return rc; } /** * security_netif_sid - Obtain the SID for a network interface. * @name: interface name * @if_sid: interface SID */ int security_netif_sid(struct selinux_state *state, char *name, u32 *if_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct ocontext *c; if (!selinux_initialized(state)) { *if_sid = SECINITSID_NETIF; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_NETIF]; while (c) { if (strcmp(name, c->u.name) == 0) break; c = c->next; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, if_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else *if_sid = SECINITSID_NETIF; out: rcu_read_unlock(); return rc; } static int match_ipv6_addrmask(u32 *input, u32 *addr, u32 *mask) { int i, fail = 0; for (i = 0; i < 4; i++) if (addr[i] != (input[i] & mask[i])) { fail = 1; break; } return !fail; } /** * security_node_sid - Obtain the SID for a node (host). * @domain: communication domain aka address family * @addrp: address * @addrlen: address length in bytes * @out_sid: security identifier */ int security_node_sid(struct selinux_state *state, u16 domain, void *addrp, u32 addrlen, u32 *out_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct ocontext *c; if (!selinux_initialized(state)) { *out_sid = SECINITSID_NODE; return 0; } retry: rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; switch (domain) { case AF_INET: { u32 addr; rc = -EINVAL; if (addrlen != sizeof(u32)) goto out; addr = *((u32 *)addrp); c = policydb->ocontexts[OCON_NODE]; while (c) { if (c->u.node.addr == (addr & c->u.node.mask)) break; c = c->next; } break; } case AF_INET6: rc = -EINVAL; if (addrlen != sizeof(u64) * 2) goto out; c = policydb->ocontexts[OCON_NODE6]; while (c) { if (match_ipv6_addrmask(addrp, c->u.node6.addr, c->u.node6.mask)) break; c = c->next; } break; default: rc = 0; *out_sid = SECINITSID_NODE; goto out; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else { *out_sid = SECINITSID_NODE; } rc = 0; out: rcu_read_unlock(); return rc; } #define SIDS_NEL 25 /** * security_get_user_sids - Obtain reachable SIDs for a user. * @fromsid: starting SID * @username: username * @sids: array of reachable SIDs for user * @nel: number of elements in @sids * * Generate the set of SIDs for legal security contexts * for a given user that can be reached by @fromsid. * Set *@sids to point to a dynamically allocated * array containing the set of SIDs. Set *@nel to the * number of elements in the array. */ int security_get_user_sids(struct selinux_state *state, u32 fromsid, char *username, u32 **sids, u32 *nel) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct context *fromcon, usercon; u32 *mysids = NULL, *mysids2, sid; u32 i, j, mynel, maxnel = SIDS_NEL; struct user_datum *user; struct role_datum *role; struct ebitmap_node *rnode, *tnode; int rc; *sids = NULL; *nel = 0; if (!selinux_initialized(state)) return 0; mysids = kcalloc(maxnel, sizeof(*mysids), GFP_KERNEL); if (!mysids) return -ENOMEM; retry: mynel = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; context_init(&usercon); rc = -EINVAL; fromcon = sidtab_search(sidtab, fromsid); if (!fromcon) goto out_unlock; rc = -EINVAL; user = symtab_search(&policydb->p_users, username); if (!user) goto out_unlock; usercon.user = user->value; ebitmap_for_each_positive_bit(&user->roles, rnode, i) { role = policydb->role_val_to_struct[i]; usercon.role = i + 1; ebitmap_for_each_positive_bit(&role->types, tnode, j) { usercon.type = j + 1; if (mls_setup_user_range(policydb, fromcon, user, &usercon)) continue; rc = sidtab_context_to_sid(sidtab, &usercon, &sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out_unlock; if (mynel < maxnel) { mysids[mynel++] = sid; } else { rc = -ENOMEM; maxnel += SIDS_NEL; mysids2 = kcalloc(maxnel, sizeof(*mysids2), GFP_ATOMIC); if (!mysids2) goto out_unlock; memcpy(mysids2, mysids, mynel * sizeof(*mysids2)); kfree(mysids); mysids = mysids2; mysids[mynel++] = sid; } } } rc = 0; out_unlock: rcu_read_unlock(); if (rc || !mynel) { kfree(mysids); return rc; } rc = -ENOMEM; mysids2 = kcalloc(mynel, sizeof(*mysids2), GFP_KERNEL); if (!mysids2) { kfree(mysids); return rc; } for (i = 0, j = 0; i < mynel; i++) { struct av_decision dummy_avd; rc = avc_has_perm_noaudit(state, fromsid, mysids[i], SECCLASS_PROCESS, /* kernel value */ PROCESS__TRANSITION, AVC_STRICT, &dummy_avd); if (!rc) mysids2[j++] = mysids[i]; cond_resched(); } kfree(mysids); *sids = mysids2; *nel = j; return 0; } /** * __security_genfs_sid - Helper to obtain a SID for a file in a filesystem * @fstype: filesystem type * @path: path from root of mount * @sclass: file security class * @sid: SID for path * * Obtain a SID to use for a file in a filesystem that * cannot support xattr or use a fixed labeling behavior like * transition SIDs or task SIDs. * * WARNING: This function may return -ESTALE, indicating that the caller * must retry the operation after re-acquiring the policy pointer! */ static inline int __security_genfs_sid(struct selinux_policy *policy, const char *fstype, char *path, u16 orig_sclass, u32 *sid) { struct policydb *policydb = &policy->policydb; struct sidtab *sidtab = policy->sidtab; int len; u16 sclass; struct genfs *genfs; struct ocontext *c; int cmp = 0; while (path[0] == '/' && path[1] == '/') path++; sclass = unmap_class(&policy->map, orig_sclass); *sid = SECINITSID_UNLABELED; for (genfs = policydb->genfs; genfs; genfs = genfs->next) { cmp = strcmp(fstype, genfs->fstype); if (cmp <= 0) break; } if (!genfs || cmp) return -ENOENT; for (c = genfs->head; c; c = c->next) { len = strlen(c->u.name); if ((!c->v.sclass || sclass == c->v.sclass) && (strncmp(c->u.name, path, len) == 0)) break; } if (!c) return -ENOENT; return ocontext_to_sid(sidtab, c, 0, sid); } /** * security_genfs_sid - Obtain a SID for a file in a filesystem * @fstype: filesystem type * @path: path from root of mount * @sclass: file security class * @sid: SID for path * * Acquire policy_rwlock before calling __security_genfs_sid() and release * it afterward. */ int security_genfs_sid(struct selinux_state *state, const char *fstype, char *path, u16 orig_sclass, u32 *sid) { struct selinux_policy *policy; int retval; if (!selinux_initialized(state)) { *sid = SECINITSID_UNLABELED; return 0; } do { rcu_read_lock(); policy = rcu_dereference(state->policy); retval = __security_genfs_sid(policy, fstype, path, orig_sclass, sid); rcu_read_unlock(); } while (retval == -ESTALE); return retval; } int selinux_policy_genfs_sid(struct selinux_policy *policy, const char *fstype, char *path, u16 orig_sclass, u32 *sid) { /* no lock required, policy is not yet accessible by other threads */ return __security_genfs_sid(policy, fstype, path, orig_sclass, sid); } /** * security_fs_use - Determine how to handle labeling for a filesystem. * @sb: superblock in question */ int security_fs_use(struct selinux_state *state, struct super_block *sb) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct ocontext *c; struct superblock_security_struct *sbsec = sb->s_security; const char *fstype = sb->s_type->name; if (!selinux_initialized(state)) { sbsec->behavior = SECURITY_FS_USE_NONE; sbsec->sid = SECINITSID_UNLABELED; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_FSUSE]; while (c) { if (strcmp(fstype, c->u.name) == 0) break; c = c->next; } if (c) { sbsec->behavior = c->v.behavior; rc = ocontext_to_sid(sidtab, c, 0, &sbsec->sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else { rc = __security_genfs_sid(policy, fstype, "/", SECCLASS_DIR, &sbsec->sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) { sbsec->behavior = SECURITY_FS_USE_NONE; rc = 0; } else { sbsec->behavior = SECURITY_FS_USE_GENFS; } } out: rcu_read_unlock(); return rc; } int security_get_bools(struct selinux_policy *policy, u32 *len, char ***names, int **values) { struct policydb *policydb; u32 i; int rc; policydb = &policy->policydb; *names = NULL; *values = NULL; rc = 0; *len = policydb->p_bools.nprim; if (!*len) goto out; rc = -ENOMEM; *names = kcalloc(*len, sizeof(char *), GFP_ATOMIC); if (!*names) goto err; rc = -ENOMEM; *values = kcalloc(*len, sizeof(int), GFP_ATOMIC); if (!*values) goto err; for (i = 0; i < *len; i++) { (*values)[i] = policydb->bool_val_to_struct[i]->state; rc = -ENOMEM; (*names)[i] = kstrdup(sym_name(policydb, SYM_BOOLS, i), GFP_ATOMIC); if (!(*names)[i]) goto err; } rc = 0; out: return rc; err: if (*names) { for (i = 0; i < *len; i++) kfree((*names)[i]); kfree(*names); } kfree(*values); *len = 0; *names = NULL; *values = NULL; goto out; } int security_set_bools(struct selinux_state *state, u32 len, int *values) { struct selinux_policy *newpolicy, *oldpolicy; int rc; u32 i, seqno = 0; if (!selinux_initialized(state)) return -EINVAL; oldpolicy = rcu_dereference_protected(state->policy, lockdep_is_held(&state->policy_mutex)); /* Consistency check on number of booleans, should never fail */ if (WARN_ON(len != oldpolicy->policydb.p_bools.nprim)) return -EINVAL; newpolicy = kmemdup(oldpolicy, sizeof(*newpolicy), GFP_KERNEL); if (!newpolicy) return -ENOMEM; /* * Deep copy only the parts of the policydb that might be * modified as a result of changing booleans. */ rc = cond_policydb_dup(&newpolicy->policydb, &oldpolicy->policydb); if (rc) { kfree(newpolicy); return -ENOMEM; } /* Update the boolean states in the copy */ for (i = 0; i < len; i++) { int new_state = !!values[i]; int old_state = newpolicy->policydb.bool_val_to_struct[i]->state; if (new_state != old_state) { audit_log(audit_context(), GFP_ATOMIC, AUDIT_MAC_CONFIG_CHANGE, "bool=%s val=%d old_val=%d auid=%u ses=%u", sym_name(&newpolicy->policydb, SYM_BOOLS, i), new_state, old_state, from_kuid(&init_user_ns, audit_get_loginuid(current)), audit_get_sessionid(current)); newpolicy->policydb.bool_val_to_struct[i]->state = new_state; } } /* Re-evaluate the conditional rules in the copy */ evaluate_cond_nodes(&newpolicy->policydb); /* Set latest granting seqno for new policy */ newpolicy->latest_granting = oldpolicy->latest_granting + 1; seqno = newpolicy->latest_granting; /* Install the new policy */ rcu_assign_pointer(state->policy, newpolicy); /* * Free the conditional portions of the old policydb * that were copied for the new policy, and the oldpolicy * structure itself but not what it references. */ synchronize_rcu(); selinux_policy_cond_free(oldpolicy); /* Notify others of the policy change */ selinux_notify_policy_change(state, seqno); return 0; } int security_get_bool_value(struct selinux_state *state, u32 index) { struct selinux_policy *policy; struct policydb *policydb; int rc; u32 len; if (!selinux_initialized(state)) return 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; rc = -EFAULT; len = policydb->p_bools.nprim; if (index >= len) goto out; rc = policydb->bool_val_to_struct[index]->state; out: rcu_read_unlock(); return rc; } static int security_preserve_bools(struct selinux_policy *oldpolicy, struct selinux_policy *newpolicy) { int rc, *bvalues = NULL; char **bnames = NULL; struct cond_bool_datum *booldatum; u32 i, nbools = 0; rc = security_get_bools(oldpolicy, &nbools, &bnames, &bvalues); if (rc) goto out; for (i = 0; i < nbools; i++) { booldatum = symtab_search(&newpolicy->policydb.p_bools, bnames[i]); if (booldatum) booldatum->state = bvalues[i]; } evaluate_cond_nodes(&newpolicy->policydb); out: if (bnames) { for (i = 0; i < nbools; i++) kfree(bnames[i]); } kfree(bnames); kfree(bvalues); return rc; } /* * security_sid_mls_copy() - computes a new sid based on the given * sid and the mls portion of mls_sid. */ int security_sid_mls_copy(struct selinux_state *state, u32 sid, u32 mls_sid, u32 *new_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct context *context1; struct context *context2; struct context newcon; char *s; u32 len; int rc; if (!selinux_initialized(state)) { *new_sid = sid; return 0; } retry: rc = 0; context_init(&newcon); rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; if (!policydb->mls_enabled) { *new_sid = sid; goto out_unlock; } rc = -EINVAL; context1 = sidtab_search(sidtab, sid); if (!context1) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, sid); goto out_unlock; } rc = -EINVAL; context2 = sidtab_search(sidtab, mls_sid); if (!context2) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, mls_sid); goto out_unlock; } newcon.user = context1->user; newcon.role = context1->role; newcon.type = context1->type; rc = mls_context_cpy(&newcon, context2); if (rc) goto out_unlock; /* Check the validity of the new context. */ if (!policydb_context_isvalid(policydb, &newcon)) { rc = convert_context_handle_invalid_context(state, policydb, &newcon); if (rc) { if (!context_struct_to_string(policydb, &newcon, &s, &len)) { struct audit_buffer *ab; ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); audit_log_format(ab, "op=security_sid_mls_copy invalid_context="); /* don't record NUL with untrusted strings */ audit_log_n_untrustedstring(ab, s, len - 1); audit_log_end(ab); kfree(s); } goto out_unlock; } } rc = sidtab_context_to_sid(sidtab, &newcon, new_sid); if (rc == -ESTALE) { rcu_read_unlock(); context_destroy(&newcon); goto retry; } out_unlock: rcu_read_unlock(); context_destroy(&newcon); return rc; } /** * security_net_peersid_resolve - Compare and resolve two network peer SIDs * @nlbl_sid: NetLabel SID * @nlbl_type: NetLabel labeling protocol type * @xfrm_sid: XFRM SID * * Description: * Compare the @nlbl_sid and @xfrm_sid values and if the two SIDs can be * resolved into a single SID it is returned via @peer_sid and the function * returns zero. Otherwise @peer_sid is set to SECSID_NULL and the function * returns a negative value. A table summarizing the behavior is below: * * | function return | @sid * ------------------------------+-----------------+----------------- * no peer labels | 0 | SECSID_NULL * single peer label | 0 | <peer_label> * multiple, consistent labels | 0 | <peer_label> * multiple, inconsistent labels | -<errno> | SECSID_NULL * */ int security_net_peersid_resolve(struct selinux_state *state, u32 nlbl_sid, u32 nlbl_type, u32 xfrm_sid, u32 *peer_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct context *nlbl_ctx; struct context *xfrm_ctx; *peer_sid = SECSID_NULL; /* handle the common (which also happens to be the set of easy) cases * right away, these two if statements catch everything involving a * single or absent peer SID/label */ if (xfrm_sid == SECSID_NULL) { *peer_sid = nlbl_sid; return 0; } /* NOTE: an nlbl_type == NETLBL_NLTYPE_UNLABELED is a "fallback" label * and is treated as if nlbl_sid == SECSID_NULL when a XFRM SID/label * is present */ if (nlbl_sid == SECSID_NULL || nlbl_type == NETLBL_NLTYPE_UNLABELED) { *peer_sid = xfrm_sid; return 0; } if (!selinux_initialized(state)) return 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; /* * We don't need to check initialized here since the only way both * nlbl_sid and xfrm_sid are not equal to SECSID_NULL would be if the * security server was initialized and state->initialized was true. */ if (!policydb->mls_enabled) { rc = 0; goto out; } rc = -EINVAL; nlbl_ctx = sidtab_search(sidtab, nlbl_sid); if (!nlbl_ctx) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, nlbl_sid); goto out; } rc = -EINVAL; xfrm_ctx = sidtab_search(sidtab, xfrm_sid); if (!xfrm_ctx) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, xfrm_sid); goto out; } rc = (mls_context_cmp(nlbl_ctx, xfrm_ctx) ? 0 : -EACCES); if (rc) goto out; /* at present NetLabel SIDs/labels really only carry MLS * information so if the MLS portion of the NetLabel SID * matches the MLS portion of the labeled XFRM SID/label * then pass along the XFRM SID as it is the most * expressive */ *peer_sid = xfrm_sid; out: rcu_read_unlock(); return rc; } static int get_classes_callback(void *k, void *d, void *args) { struct class_datum *datum = d; char *name = k, **classes = args; int value = datum->value - 1; classes[value] = kstrdup(name, GFP_ATOMIC); if (!classes[value]) return -ENOMEM; return 0; } int security_get_classes(struct selinux_policy *policy, char ***classes, int *nclasses) { struct policydb *policydb; int rc; policydb = &policy->policydb; rc = -ENOMEM; *nclasses = policydb->p_classes.nprim; *classes = kcalloc(*nclasses, sizeof(**classes), GFP_ATOMIC); if (!*classes) goto out; rc = hashtab_map(&policydb->p_classes.table, get_classes_callback, *classes); if (rc) { int i; for (i = 0; i < *nclasses; i++) kfree((*classes)[i]); kfree(*classes); } out: return rc; } static int get_permissions_callback(void *k, void *d, void *args) { struct perm_datum *datum = d; char *name = k, **perms = args; int value = datum->value - 1; perms[value] = kstrdup(name, GFP_ATOMIC); if (!perms[value]) return -ENOMEM; return 0; } int security_get_permissions(struct selinux_policy *policy, char *class, char ***perms, int *nperms) { struct policydb *policydb; int rc, i; struct class_datum *match; policydb = &policy->policydb; rc = -EINVAL; match = symtab_search(&policydb->p_classes, class); if (!match) { pr_err("SELinux: %s: unrecognized class %s\n", __func__, class); goto out; } rc = -ENOMEM; *nperms = match->permissions.nprim; *perms = kcalloc(*nperms, sizeof(**perms), GFP_ATOMIC); if (!*perms) goto out; if (match->comdatum) { rc = hashtab_map(&match->comdatum->permissions.table, get_permissions_callback, *perms); if (rc) goto err; } rc = hashtab_map(&match->permissions.table, get_permissions_callback, *perms); if (rc) goto err; out: return rc; err: for (i = 0; i < *nperms; i++) kfree((*perms)[i]); kfree(*perms); return rc; } int security_get_reject_unknown(struct selinux_state *state) { struct selinux_policy *policy; int value; if (!selinux_initialized(state)) return 0; rcu_read_lock(); policy = rcu_dereference(state->policy); value = policy->policydb.reject_unknown; rcu_read_unlock(); return value; } int security_get_allow_unknown(struct selinux_state *state) { struct selinux_policy *policy; int value; if (!selinux_initialized(state)) return 0; rcu_read_lock(); policy = rcu_dereference(state->policy); value = policy->policydb.allow_unknown; rcu_read_unlock(); return value; } /** * security_policycap_supported - Check for a specific policy capability * @req_cap: capability * * Description: * This function queries the currently loaded policy to see if it supports the * capability specified by @req_cap. Returns true (1) if the capability is * supported, false (0) if it isn't supported. * */ int security_policycap_supported(struct selinux_state *state, unsigned int req_cap) { struct selinux_policy *policy; int rc; if (!selinux_initialized(state)) return 0; rcu_read_lock(); policy = rcu_dereference(state->policy); rc = ebitmap_get_bit(&policy->policydb.policycaps, req_cap); rcu_read_unlock(); return rc; } struct selinux_audit_rule { u32 au_seqno; struct context au_ctxt; }; void selinux_audit_rule_free(void *vrule) { struct selinux_audit_rule *rule = vrule; if (rule) { context_destroy(&rule->au_ctxt); kfree(rule); } } int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, gfp_t gfp) { struct selinux_state *state = &selinux_state; struct selinux_policy *policy; struct policydb *policydb; struct selinux_audit_rule *tmprule; struct role_datum *roledatum; struct type_datum *typedatum; struct user_datum *userdatum; struct selinux_audit_rule **rule = (struct selinux_audit_rule **)vrule; int rc = 0; *rule = NULL; if (!selinux_initialized(state)) return -EOPNOTSUPP; switch (field) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: /* only 'equals' and 'not equals' fit user, role, and type */ if (op != Audit_equal && op != Audit_not_equal) return -EINVAL; break; case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: /* we do not allow a range, indicated by the presence of '-' */ if (strchr(rulestr, '-')) return -EINVAL; break; default: /* only the above fields are valid */ return -EINVAL; } tmprule = kzalloc(sizeof(struct selinux_audit_rule), gfp); if (!tmprule) return -ENOMEM; context_init(&tmprule->au_ctxt); rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; tmprule->au_seqno = policy->latest_granting; switch (field) { case AUDIT_SUBJ_USER: case AUDIT_OBJ_USER: rc = -EINVAL; userdatum = symtab_search(&policydb->p_users, rulestr); if (!userdatum) goto out; tmprule->au_ctxt.user = userdatum->value; break; case AUDIT_SUBJ_ROLE: case AUDIT_OBJ_ROLE: rc = -EINVAL; roledatum = symtab_search(&policydb->p_roles, rulestr); if (!roledatum) goto out; tmprule->au_ctxt.role = roledatum->value; break; case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_TYPE: rc = -EINVAL; typedatum = symtab_search(&policydb->p_types, rulestr); if (!typedatum) goto out; tmprule->au_ctxt.type = typedatum->value; break; case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: rc = mls_from_string(policydb, rulestr, &tmprule->au_ctxt, GFP_ATOMIC); if (rc) goto out; break; } rc = 0; out: rcu_read_unlock(); if (rc) { selinux_audit_rule_free(tmprule); tmprule = NULL; } *rule = tmprule; return rc; } /* Check to see if the rule contains any selinux fields */ int selinux_audit_rule_known(struct audit_krule *rule) { int i; for (i = 0; i < rule->field_count; i++) { struct audit_field *f = &rule->fields[i]; switch (f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: return 1; } } return 0; } int selinux_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule) { struct selinux_state *state = &selinux_state; struct selinux_policy *policy; struct context *ctxt; struct mls_level *level; struct selinux_audit_rule *rule = vrule; int match = 0; if (unlikely(!rule)) { WARN_ONCE(1, "selinux_audit_rule_match: missing rule\n"); return -ENOENT; } if (!selinux_initialized(state)) return 0; rcu_read_lock(); policy = rcu_dereference(state->policy); if (rule->au_seqno < policy->latest_granting) { match = -ESTALE; goto out; } ctxt = sidtab_search(policy->sidtab, sid); if (unlikely(!ctxt)) { WARN_ONCE(1, "selinux_audit_rule_match: unrecognized SID %d\n", sid); match = -ENOENT; goto out; } /* a field/op pair that is not caught here will simply fall through without a match */ switch (field) { case AUDIT_SUBJ_USER: case AUDIT_OBJ_USER: switch (op) { case Audit_equal: match = (ctxt->user == rule->au_ctxt.user); break; case Audit_not_equal: match = (ctxt->user != rule->au_ctxt.user); break; } break; case AUDIT_SUBJ_ROLE: case AUDIT_OBJ_ROLE: switch (op) { case Audit_equal: match = (ctxt->role == rule->au_ctxt.role); break; case Audit_not_equal: match = (ctxt->role != rule->au_ctxt.role); break; } break; case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_TYPE: switch (op) { case Audit_equal: match = (ctxt->type == rule->au_ctxt.type); break; case Audit_not_equal: match = (ctxt->type != rule->au_ctxt.type); break; } break; case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: level = ((field == AUDIT_SUBJ_SEN || field == AUDIT_OBJ_LEV_LOW) ? &ctxt->range.level[0] : &ctxt->range.level[1]); switch (op) { case Audit_equal: match = mls_level_eq(&rule->au_ctxt.range.level[0], level); break; case Audit_not_equal: match = !mls_level_eq(&rule->au_ctxt.range.level[0], level); break; case Audit_lt: match = (mls_level_dom(&rule->au_ctxt.range.level[0], level) && !mls_level_eq(&rule->au_ctxt.range.level[0], level)); break; case Audit_le: match = mls_level_dom(&rule->au_ctxt.range.level[0], level); break; case Audit_gt: match = (mls_level_dom(level, &rule->au_ctxt.range.level[0]) && !mls_level_eq(level, &rule->au_ctxt.range.level[0])); break; case Audit_ge: match = mls_level_dom(level, &rule->au_ctxt.range.level[0]); break; } } out: rcu_read_unlock(); return match; } static int (*aurule_callback)(void) = audit_update_lsm_rules; static int aurule_avc_callback(u32 event) { int err = 0; if (event == AVC_CALLBACK_RESET && aurule_callback) err = aurule_callback(); return err; } static int __init aurule_init(void) { int err; err = avc_add_callback(aurule_avc_callback, AVC_CALLBACK_RESET); if (err) panic("avc_add_callback() failed, error %d\n", err); return err; } __initcall(aurule_init); #ifdef CONFIG_NETLABEL /** * security_netlbl_cache_add - Add an entry to the NetLabel cache * @secattr: the NetLabel packet security attributes * @sid: the SELinux SID * * Description: * Attempt to cache the context in @ctx, which was derived from the packet in * @skb, in the NetLabel subsystem cache. This function assumes @secattr has * already been initialized. * */ static void security_netlbl_cache_add(struct netlbl_lsm_secattr *secattr, u32 sid) { u32 *sid_cache; sid_cache = kmalloc(sizeof(*sid_cache), GFP_ATOMIC); if (sid_cache == NULL) return; secattr->cache = netlbl_secattr_cache_alloc(GFP_ATOMIC); if (secattr->cache == NULL) { kfree(sid_cache); return; } *sid_cache = sid; secattr->cache->free = kfree; secattr->cache->data = sid_cache; secattr->flags |= NETLBL_SECATTR_CACHE; } /** * security_netlbl_secattr_to_sid - Convert a NetLabel secattr to a SELinux SID * @secattr: the NetLabel packet security attributes * @sid: the SELinux SID * * Description: * Convert the given NetLabel security attributes in @secattr into a * SELinux SID. If the @secattr field does not contain a full SELinux * SID/context then use SECINITSID_NETMSG as the foundation. If possible the * 'cache' field of @secattr is set and the CACHE flag is set; this is to * allow the @secattr to be used by NetLabel to cache the secattr to SID * conversion for future lookups. Returns zero on success, negative values on * failure. * */ int security_netlbl_secattr_to_sid(struct selinux_state *state, struct netlbl_lsm_secattr *secattr, u32 *sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct context *ctx; struct context ctx_new; if (!selinux_initialized(state)) { *sid = SECSID_NULL; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; sidtab = policy->sidtab; if (secattr->flags & NETLBL_SECATTR_CACHE) *sid = *(u32 *)secattr->cache->data; else if (secattr->flags & NETLBL_SECATTR_SECID) *sid = secattr->attr.secid; else if (secattr->flags & NETLBL_SECATTR_MLS_LVL) { rc = -EIDRM; ctx = sidtab_search(sidtab, SECINITSID_NETMSG); if (ctx == NULL) goto out; context_init(&ctx_new); ctx_new.user = ctx->user; ctx_new.role = ctx->role; ctx_new.type = ctx->type; mls_import_netlbl_lvl(policydb, &ctx_new, secattr); if (secattr->flags & NETLBL_SECATTR_MLS_CAT) { rc = mls_import_netlbl_cat(policydb, &ctx_new, secattr); if (rc) goto out; } rc = -EIDRM; if (!mls_context_isvalid(policydb, &ctx_new)) { ebitmap_destroy(&ctx_new.range.level[0].cat); goto out; } rc = sidtab_context_to_sid(sidtab, &ctx_new, sid); ebitmap_destroy(&ctx_new.range.level[0].cat); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; security_netlbl_cache_add(secattr, *sid); } else *sid = SECSID_NULL; out: rcu_read_unlock(); return rc; } /** * security_netlbl_sid_to_secattr - Convert a SELinux SID to a NetLabel secattr * @sid: the SELinux SID * @secattr: the NetLabel packet security attributes * * Description: * Convert the given SELinux SID in @sid into a NetLabel security attribute. * Returns zero on success, negative values on failure. * */ int security_netlbl_sid_to_secattr(struct selinux_state *state, u32 sid, struct netlbl_lsm_secattr *secattr) { struct selinux_policy *policy; struct policydb *policydb; int rc; struct context *ctx; if (!selinux_initialized(state)) return 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; rc = -ENOENT; ctx = sidtab_search(policy->sidtab, sid); if (ctx == NULL) goto out; rc = -ENOMEM; secattr->domain = kstrdup(sym_name(policydb, SYM_TYPES, ctx->type - 1), GFP_ATOMIC); if (secattr->domain == NULL) goto out; secattr->attr.secid = sid; secattr->flags |= NETLBL_SECATTR_DOMAIN_CPY | NETLBL_SECATTR_SECID; mls_export_netlbl_lvl(policydb, ctx, secattr); rc = mls_export_netlbl_cat(policydb, ctx, secattr); out: rcu_read_unlock(); return rc; } #endif /* CONFIG_NETLABEL */ /** * security_read_policy - read the policy. * @data: binary policy data * @len: length of data in bytes * */ int security_read_policy(struct selinux_state *state, void **data, size_t *len) { struct selinux_policy *policy; int rc; struct policy_file fp; policy = rcu_dereference_protected( state->policy, lockdep_is_held(&state->policy_mutex)); if (!policy) return -EINVAL; *len = policy->policydb.len; *data = vmalloc_user(*len); if (!*data) return -ENOMEM; fp.data = *data; fp.len = *len; rc = policydb_write(&policy->policydb, &fp); if (rc) return rc; *len = (unsigned long)fp.data - (unsigned long)*data; return 0; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 | /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/posix_acl.h (C) 2002 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ #ifndef __LINUX_POSIX_ACL_H #define __LINUX_POSIX_ACL_H #include <linux/bug.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <uapi/linux/posix_acl.h> struct posix_acl_entry { short e_tag; unsigned short e_perm; union { kuid_t e_uid; kgid_t e_gid; }; }; struct posix_acl { refcount_t a_refcount; struct rcu_head a_rcu; unsigned int a_count; struct posix_acl_entry a_entries[]; }; #define FOREACH_ACL_ENTRY(pa, acl, pe) \ for(pa=(acl)->a_entries, pe=pa+(acl)->a_count; pa<pe; pa++) /* * Duplicate an ACL handle. */ static inline struct posix_acl * posix_acl_dup(struct posix_acl *acl) { if (acl) refcount_inc(&acl->a_refcount); return acl; } /* * Free an ACL handle. */ static inline void posix_acl_release(struct posix_acl *acl) { if (acl && refcount_dec_and_test(&acl->a_refcount)) kfree_rcu(acl, a_rcu); } /* posix_acl.c */ extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(int, gfp_t); extern int posix_acl_valid(struct user_namespace *, const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); #ifdef CONFIG_FS_POSIX_ACL extern int posix_acl_chmod(struct inode *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); extern int posix_acl_update_mode(struct inode *, umode_t *, struct posix_acl **); extern int simple_set_acl(struct inode *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); struct posix_acl *get_cached_acl(struct inode *inode, int type); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl); void forget_cached_acl(struct inode *inode, int type); void forget_all_cached_acls(struct inode *inode); static inline void cache_no_acl(struct inode *inode) { inode->i_acl = NULL; inode->i_default_acl = NULL; } #else static inline int posix_acl_chmod(struct inode *inode, umode_t mode) { return 0; } #define simple_set_acl NULL static inline int simple_acl_create(struct inode *dir, struct inode *inode) { return 0; } static inline void cache_no_acl(struct inode *inode) { } static inline int posix_acl_create(struct inode *inode, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { *default_acl = *acl = NULL; return 0; } static inline void forget_all_cached_acls(struct inode *inode) { } #endif /* CONFIG_FS_POSIX_ACL */ struct posix_acl *get_acl(struct inode *inode, int type); #endif /* __LINUX_POSIX_ACL_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_H #define _ASM_X86_UACCESS_H /* * User space memory access functions */ #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/string.h> #include <asm/asm.h> #include <asm/page.h> #include <asm/smap.h> #include <asm/extable.h> /* * Test whether a block of memory is a valid user space address. * Returns 0 if the range is valid, nonzero otherwise. */ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit) { /* * If we have used "sizeof()" for the size, * we know it won't overflow the limit (but * it might overflow the 'addr', so it's * important to subtract the size from the * limit, not add it to the address). */ if (__builtin_constant_p(size)) return unlikely(addr > limit - size); /* Arbitrary sizes? Be careful about overflow */ addr += size; if (unlikely(addr < size)) return true; return unlikely(addr > limit); } #define __range_not_ok(addr, size, limit) \ ({ \ __chk_user_ptr(addr); \ __chk_range_not_ok((unsigned long __force)(addr), size, limit); \ }) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP static inline bool pagefault_disabled(void); # define WARN_ON_IN_IRQ() \ WARN_ON_ONCE(!in_task() && !pagefault_disabled()) #else # define WARN_ON_IN_IRQ() #endif /** * access_ok - Checks if a user space pointer is valid * @addr: User space pointer to start of block to check * @size: Size of block to check * * Context: User context only. This function may sleep if pagefaults are * enabled. * * Checks if a pointer to a block of memory in user space is valid. * * Note that, depending on architecture, this function probably just * checks that the pointer is in the user space range - after calling * this function, memory access functions may still return -EFAULT. * * Return: true (nonzero) if the memory block may be valid, false (zero) * if it is definitely invalid. */ #define access_ok(addr, size) \ ({ \ WARN_ON_IN_IRQ(); \ likely(!__range_not_ok(addr, size, TASK_SIZE_MAX)); \ }) extern int __get_user_1(void); extern int __get_user_2(void); extern int __get_user_4(void); extern int __get_user_8(void); extern int __get_user_nocheck_1(void); extern int __get_user_nocheck_2(void); extern int __get_user_nocheck_4(void); extern int __get_user_nocheck_8(void); extern int __get_user_bad(void); #define __uaccess_begin() stac() #define __uaccess_end() clac() #define __uaccess_begin_nospec() \ ({ \ stac(); \ barrier_nospec(); \ }) /* * This is the smallest unsigned integer type that can fit a value * (up to 'long long') */ #define __inttype(x) __typeof__( \ __typefits(x,char, \ __typefits(x,short, \ __typefits(x,int, \ __typefits(x,long,0ULL))))) #define __typefits(x,type,not) \ __builtin_choose_expr(sizeof(x)<=sizeof(type),(unsigned type)0,not) /* * This is used for both get_user() and __get_user() to expand to * the proper special function call that has odd calling conventions * due to returning both a value and an error, and that depends on * the size of the pointer passed in. * * Careful: we have to cast the result to the type of the pointer * for sign reasons. * * The use of _ASM_DX as the register specifier is a bit of a * simplification, as gcc only cares about it as the starting point * and not size: for a 64-bit value it will use %ecx:%edx on 32 bits * (%ecx being the next register in gcc's x86 register sequence), and * %rdx on 64 bits. * * Clang/LLVM cares about the size of the register, but still wants * the base register for something that ends up being a pair. */ #define do_get_user_call(fn,x,ptr) \ ({ \ int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ asm volatile("call __" #fn "_%P4" \ : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ : "0" (ptr), "i" (sizeof(*(ptr)))); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ }) /** * get_user - Get a simple variable from user space. * @x: Variable to store result. * @ptr: Source address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and the result of * dereferencing @ptr must be assignable to @x without a cast. * * Return: zero on success, or -EFAULT on error. * On error, the variable @x is set to zero. */ #define get_user(x,ptr) ({ might_fault(); do_get_user_call(get_user,x,ptr); }) /** * __get_user - Get a simple variable from user space, with less checking. * @x: Variable to store result. * @ptr: Source address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and the result of * dereferencing @ptr must be assignable to @x without a cast. * * Caller must check the pointer with access_ok() before calling this * function. * * Return: zero on success, or -EFAULT on error. * On error, the variable @x is set to zero. */ #define __get_user(x,ptr) do_get_user_call(get_user_nocheck,x,ptr) #ifdef CONFIG_X86_32 #define __put_user_goto_u64(x, addr, label) \ asm_volatile_goto("\n" \ "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ _ASM_EXTABLE_UA(1b, %l2) \ _ASM_EXTABLE_UA(2b, %l2) \ : : "A" (x), "r" (addr) \ : : label) #else #define __put_user_goto_u64(x, ptr, label) \ __put_user_goto(x, ptr, "q", "er", label) #endif extern void __put_user_bad(void); /* * Strange magic calling convention: pointer in %ecx, * value in %eax(:%edx), return value in %ecx. clobbers %rbx */ extern void __put_user_1(void); extern void __put_user_2(void); extern void __put_user_4(void); extern void __put_user_8(void); extern void __put_user_nocheck_1(void); extern void __put_user_nocheck_2(void); extern void __put_user_nocheck_4(void); extern void __put_user_nocheck_8(void); /* * ptr must be evaluated and assigned to the temporary __ptr_pu before * the assignment of x to __val_pu, to avoid any function calls * involved in the ptr expression (possibly implicitly generated due * to KASAN) from clobbering %ax. */ #define do_put_user_call(fn,x,ptr) \ ({ \ int __ret_pu; \ void __user *__ptr_pu; \ register __typeof__(*(ptr)) __val_pu asm("%"_ASM_AX); \ __chk_user_ptr(ptr); \ __ptr_pu = (ptr); \ __val_pu = (x); \ asm volatile("call __" #fn "_%P[size]" \ : "=c" (__ret_pu), \ ASM_CALL_CONSTRAINT \ : "0" (__ptr_pu), \ "r" (__val_pu), \ [size] "i" (sizeof(*(ptr))) \ :"ebx"); \ __builtin_expect(__ret_pu, 0); \ }) /** * put_user - Write a simple value into user space. * @x: Value to copy to user space. * @ptr: Destination address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and @x must be assignable * to the result of dereferencing @ptr. * * Return: zero on success, or -EFAULT on error. */ #define put_user(x, ptr) ({ might_fault(); do_put_user_call(put_user,x,ptr); }) /** * __put_user - Write a simple value into user space, with less checking. * @x: Value to copy to user space. * @ptr: Destination address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and @x must be assignable * to the result of dereferencing @ptr. * * Caller must check the pointer with access_ok() before calling this * function. * * Return: zero on success, or -EFAULT on error. */ #define __put_user(x, ptr) do_put_user_call(put_user_nocheck,x,ptr) #define __put_user_size(x, ptr, size, label) \ do { \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ __put_user_goto(x, ptr, "b", "iq", label); \ break; \ case 2: \ __put_user_goto(x, ptr, "w", "ir", label); \ break; \ case 4: \ __put_user_goto(x, ptr, "l", "ir", label); \ break; \ case 8: \ __put_user_goto_u64(x, ptr, label); \ break; \ default: \ __put_user_bad(); \ } \ } while (0) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #ifdef CONFIG_X86_32 #define __get_user_asm_u64(x, ptr, label) do { \ unsigned int __gu_low, __gu_high; \ const unsigned int __user *__gu_ptr; \ __gu_ptr = (const void __user *)(ptr); \ __get_user_asm(__gu_low, __gu_ptr, "l", "=r", label); \ __get_user_asm(__gu_high, __gu_ptr+1, "l", "=r", label); \ (x) = ((unsigned long long)__gu_high << 32) | __gu_low; \ } while (0) #else #define __get_user_asm_u64(x, ptr, label) \ __get_user_asm(x, ptr, "q", "=r", label) #endif #define __get_user_size(x, ptr, size, label) \ do { \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: { \ unsigned char x_u8__; \ __get_user_asm(x_u8__, ptr, "b", "=q", label); \ (x) = x_u8__; \ break; \ } \ case 2: \ __get_user_asm(x, ptr, "w", "=r", label); \ break; \ case 4: \ __get_user_asm(x, ptr, "l", "=r", label); \ break; \ case 8: \ __get_user_asm_u64(x, ptr, label); \ break; \ default: \ (x) = __get_user_bad(); \ } \ } while (0) #define __get_user_asm(x, addr, itype, ltype, label) \ asm_volatile_goto("\n" \ "1: mov"itype" %[umem],%[output]\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : [output] ltype(x) \ : [umem] "m" (__m(addr)) \ : : label) #else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #ifdef CONFIG_X86_32 #define __get_user_asm_u64(x, ptr, retval) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ asm volatile("\n" \ "1: movl %[lowbits],%%eax\n" \ "2: movl %[highbits],%%edx\n" \ "3:\n" \ ".section .fixup,\"ax\"\n" \ "4: mov %[efault],%[errout]\n" \ " xorl %%eax,%%eax\n" \ " xorl %%edx,%%edx\n" \ " jmp 3b\n" \ ".previous\n" \ _ASM_EXTABLE_UA(1b, 4b) \ _ASM_EXTABLE_UA(2b, 4b) \ : [errout] "=r" (retval), \ [output] "=&A"(x) \ : [lowbits] "m" (__m(__ptr)), \ [highbits] "m" __m(((u32 __user *)(__ptr)) + 1), \ [efault] "i" (-EFAULT), "0" (retval)); \ }) #else #define __get_user_asm_u64(x, ptr, retval) \ __get_user_asm(x, ptr, retval, "q", "=r") #endif #define __get_user_size(x, ptr, size, retval) \ do { \ unsigned char x_u8__; \ \ retval = 0; \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ __get_user_asm(x_u8__, ptr, retval, "b", "=q"); \ (x) = x_u8__; \ break; \ case 2: \ __get_user_asm(x, ptr, retval, "w", "=r"); \ break; \ case 4: \ __get_user_asm(x, ptr, retval, "l", "=r"); \ break; \ case 8: \ __get_user_asm_u64(x, ptr, retval); \ break; \ default: \ (x) = __get_user_bad(); \ } \ } while (0) #define __get_user_asm(x, addr, err, itype, ltype) \ asm volatile("\n" \ "1: mov"itype" %[umem],%[output]\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: mov %[efault],%[errout]\n" \ " xorl %k[output],%k[output]\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE_UA(1b, 3b) \ : [errout] "=r" (err), \ [output] ltype(x) \ : [umem] "m" (__m(addr)), \ [efault] "i" (-EFAULT), "0" (err)) #endif // CONFIG_CC_ASM_GOTO_OUTPUT #ifdef CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT #define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm_volatile_goto("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ : "memory" \ : label); \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #ifdef CONFIG_X86_32 #define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm_volatile_goto("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ "+A" (__old), \ [ptr] "+m" (*_ptr) \ : "b" ((u32)__new), \ "c" ((u32)((u64)__new >> 32)) \ : "memory" \ : label); \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #endif // CONFIG_X86_32 #else // !CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT #define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ int __err = 0; \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm volatile("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ CC_SET(z) \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, \ %[errout]) \ : CC_OUT(z) (success), \ [errout] "+r" (__err), \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ : "memory"); \ if (unlikely(__err)) \ goto label; \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #ifdef CONFIG_X86_32 /* * Unlike the normal CMPXCHG, hardcode ECX for both success/fail and error. * There are only six GPRs available and four (EAX, EBX, ECX, and EDX) are * hardcoded by CMPXCHG8B, leaving only ESI and EDI. If the compiler uses * both ESI and EDI for the memory operand, compilation will fail if the error * is an input+output as there will be no register available for input. */ #define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ int __result; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm volatile("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ "mov $0, %%ecx\n\t" \ "setz %%cl\n" \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %%ecx) \ : [result]"=c" (__result), \ "+A" (__old), \ [ptr] "+m" (*_ptr) \ : "b" ((u32)__new), \ "c" ((u32)((u64)__new >> 32)) \ : "memory", "cc"); \ if (unlikely(__result < 0)) \ goto label; \ if (unlikely(!__result)) \ *_old = __old; \ likely(__result); }) #endif // CONFIG_X86_32 #endif // CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT /* FIXME: this hack is definitely wrong -AK */ struct __large_struct { unsigned long buf[100]; }; #define __m(x) (*(struct __large_struct __user *)(x)) /* * Tell gcc we read from memory instead of writing: this is because * we do not write to any memory gcc knows about, so there are no * aliasing issues. */ #define __put_user_goto(x, addr, itype, ltype, label) \ asm_volatile_goto("\n" \ "1: mov"itype" %0,%1\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : : ltype(x), "m" (__m(addr)) \ : : label) extern unsigned long copy_from_user_nmi(void *to, const void __user *from, unsigned long n); extern __must_check long strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); unsigned long __must_check clear_user(void __user *mem, unsigned long len); unsigned long __must_check __clear_user(void __user *mem, unsigned long len); #ifdef CONFIG_ARCH_HAS_COPY_MC unsigned long __must_check copy_mc_to_kernel(void *to, const void *from, unsigned len); #define copy_mc_to_kernel copy_mc_to_kernel unsigned long __must_check copy_mc_to_user(void __user *to, const void *from, unsigned len); #endif /* * movsl can be slow when source and dest are not both 8-byte aligned */ #ifdef CONFIG_X86_INTEL_USERCOPY extern struct movsl_mask { int mask; } ____cacheline_aligned_in_smp movsl_mask; #endif #define ARCH_HAS_NOCACHE_UACCESS 1 #ifdef CONFIG_X86_32 # include <asm/uaccess_32.h> #else # include <asm/uaccess_64.h> #endif /* * The "unsafe" user accesses aren't really "unsafe", but the naming * is a big fat warning: you have to not only do the access_ok() * checking before using them, but you have to surround them with the * user_access_begin/end() pair. */ static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) { if (unlikely(!access_ok(ptr,len))) return 0; __uaccess_begin_nospec(); return 1; } #define user_access_begin(a,b) user_access_begin(a,b) #define user_access_end() __uaccess_end() #define user_access_save() smap_save() #define user_access_restore(x) smap_restore(x) #define unsafe_put_user(x, ptr, label) \ __put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label) #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define unsafe_get_user(x, ptr, err_label) \ do { \ __inttype(*(ptr)) __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), err_label); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) #else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define unsafe_get_user(x, ptr, err_label) \ do { \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ if (unlikely(__gu_err)) goto err_label; \ } while (0) #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT extern void __try_cmpxchg_user_wrong_size(void); #ifndef CONFIG_X86_32 #define __try_cmpxchg64_user_asm(_ptr, _oldp, _nval, _label) \ __try_cmpxchg_user_asm("q", "r", (_ptr), (_oldp), (_nval), _label) #endif /* * Force the pointer to u<size> to match the size expected by the asm helper. * clang/LLVM compiles all cases and only discards the unused paths after * processing errors, which breaks i386 if the pointer is an 8-byte value. */ #define unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ bool __ret; \ __chk_user_ptr(_ptr); \ switch (sizeof(*(_ptr))) { \ case 1: __ret = __try_cmpxchg_user_asm("b", "q", \ (__force u8 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 2: __ret = __try_cmpxchg_user_asm("w", "r", \ (__force u16 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 4: __ret = __try_cmpxchg_user_asm("l", "r", \ (__force u32 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 8: __ret = __try_cmpxchg64_user_asm((__force u64 *)(_ptr), (_oldp),\ (_nval), _label); \ break; \ default: __try_cmpxchg_user_wrong_size(); \ } \ __ret; }) /* "Returns" 0 on success, 1 on failure, -EFAULT if the access faults. */ #define __try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ int __ret = -EFAULT; \ __uaccess_begin_nospec(); \ __ret = !unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label); \ _label: \ __uaccess_end(); \ __ret; \ }) /* * We want the unsafe accessors to always be inlined and use * the error labels - thus the macro games. */ #define unsafe_copy_loop(dst, src, len, type, label) \ while (len >= sizeof(type)) { \ unsafe_put_user(*(type *)(src),(type __user *)(dst),label); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ } #define unsafe_copy_to_user(_dst,_src,_len,label) \ do { \ char __user *__ucu_dst = (_dst); \ const char *__ucu_src = (_src); \ size_t __ucu_len = (_len); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u64, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u32, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u16, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u8, label); \ } while (0) #define HAVE_GET_KERNEL_NOFAULT #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_kernel_nofault(dst, src, type, err_label) \ __get_user_size(*((type *)(dst)), (__force type __user *)(src), \ sizeof(type), err_label) #else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_kernel_nofault(dst, src, type, err_label) \ do { \ int __kr_err; \ \ __get_user_size(*((type *)(dst)), (__force type __user *)(src), \ sizeof(type), __kr_err); \ if (unlikely(__kr_err)) \ goto err_label; \ } while (0) #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __put_kernel_nofault(dst, src, type, err_label) \ __put_user_size(*((type *)(src)), (__force type __user *)(dst), \ sizeof(type), err_label) #endif /* _ASM_X86_UACCESS_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Queued spinlock * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * * Authors: Waiman Long <waiman.long@hpe.com> */ #ifndef __ASM_GENERIC_QSPINLOCK_H #define __ASM_GENERIC_QSPINLOCK_H #include <asm-generic/qspinlock_types.h> #include <linux/atomic.h> #ifndef queued_spin_is_locked /** * queued_spin_is_locked - is the spinlock locked? * @lock: Pointer to queued spinlock structure * Return: 1 if it is locked, 0 otherwise */ static __always_inline int queued_spin_is_locked(struct qspinlock *lock) { /* * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL * isn't immediately observable. */ return atomic_read(&lock->val); } #endif /** * queued_spin_value_unlocked - is the spinlock structure unlocked? * @lock: queued spinlock structure * Return: 1 if it is unlocked, 0 otherwise * * N.B. Whenever there are tasks waiting for the lock, it is considered * locked wrt the lockref code to avoid lock stealing by the lockref * code and change things underneath the lock. This also allows some * optimizations to be applied without conflict with lockref. */ static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) { return !lock.val.counter; } /** * queued_spin_is_contended - check if the lock is contended * @lock : Pointer to queued spinlock structure * Return: 1 if lock contended, 0 otherwise */ static __always_inline int queued_spin_is_contended(struct qspinlock *lock) { return atomic_read(&lock->val) & ~_Q_LOCKED_MASK; } /** * queued_spin_trylock - try to acquire the queued spinlock * @lock : Pointer to queued spinlock structure * Return: 1 if lock acquired, 0 if failed */ static __always_inline int queued_spin_trylock(struct qspinlock *lock) { u32 val = atomic_read(&lock->val); if (unlikely(val)) return 0; return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)); } extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); #ifndef queued_spin_lock /** * queued_spin_lock - acquire a queued spinlock * @lock: Pointer to queued spinlock structure */ static __always_inline void queued_spin_lock(struct qspinlock *lock) { u32 val = 0; if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL))) return; queued_spin_lock_slowpath(lock, val); } #endif #ifndef queued_spin_unlock /** * queued_spin_unlock - release a queued spinlock * @lock : Pointer to queued spinlock structure */ static __always_inline void queued_spin_unlock(struct qspinlock *lock) { /* * unlock() needs release semantics: */ smp_store_release(&lock->locked, 0); } #endif #ifndef virt_spin_lock static __always_inline bool virt_spin_lock(struct qspinlock *lock) { return false; } #endif /* * Remapping spinlock architecture specific functions to the corresponding * queued spinlock functions. */ #define arch_spin_is_locked(l) queued_spin_is_locked(l) #define arch_spin_is_contended(l) queued_spin_is_contended(l) #define arch_spin_value_unlocked(l) queued_spin_value_unlocked(l) #define arch_spin_lock(l) queued_spin_lock(l) #define arch_spin_trylock(l) queued_spin_trylock(l) #define arch_spin_unlock(l) queued_spin_unlock(l) #endif /* __ASM_GENERIC_QSPINLOCK_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_BL_H #define _LINUX_RCULIST_BL_H /* * RCU-protected bl list version. See include/linux/list_bl.h. */ #include <linux/list_bl.h> #include <linux/rcupdate.h> static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); rcu_assign_pointer(h->first, (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK)); } static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)rcu_dereference_check(h->first, hlist_bl_is_locked(h)) & ~LIST_BL_LOCKMASK); } /** * hlist_bl_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: hlist_bl_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry(). */ static inline void hlist_bl_del_rcu(struct hlist_bl_node *n) { __hlist_bl_del(n); n->pprev = LIST_POISON2; } /** * hlist_bl_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist_bl, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first; /* don't need hlist_bl_first_rcu because we're under lock */ first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; /* need _rcu because we can have concurrent lock free readers */ hlist_bl_set_first_rcu(h, n); } /** * hlist_bl_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_bl_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_bl_node within the struct. * */ #define hlist_bl_for_each_entry_rcu(tpos, pos, head, member) \ for (pos = hlist_bl_first_rcu(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(pos->next)) #endif |
| 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | // SPDX-License-Identifier: GPL-2.0 /* * Implementations of the security context functions. * * Author: Ondrej Mosnacek <omosnacek@gmail.com> * Copyright (C) 2020 Red Hat, Inc. */ #include <linux/jhash.h> #include "context.h" #include "mls.h" u32 context_compute_hash(const struct context *c) { u32 hash = 0; /* * If a context is invalid, it will always be represented by a * context struct with only the len & str set (and vice versa) * under a given policy. Since context structs from different * policies should never meet, it is safe to hash valid and * invalid contexts differently. The context_cmp() function * already operates under the same assumption. */ if (c->len) return full_name_hash(NULL, c->str, c->len); hash = jhash_3words(c->user, c->role, c->type, hash); hash = mls_range_hash(&c->range, hash); return hash; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SIGNAL_H #define _LINUX_SIGNAL_H #include <linux/bug.h> #include <linux/signal_types.h> #include <linux/string.h> struct task_struct; /* for sysctl */ extern int print_fatal_signals; static inline void copy_siginfo(kernel_siginfo_t *to, const kernel_siginfo_t *from) { memcpy(to, from, sizeof(*to)); } static inline void clear_siginfo(kernel_siginfo_t *info) { memset(info, 0, sizeof(*info)); } #define SI_EXPANSION_SIZE (sizeof(struct siginfo) - sizeof(struct kernel_siginfo)) static inline void copy_siginfo_to_external(siginfo_t *to, const kernel_siginfo_t *from) { memcpy(to, from, sizeof(*from)); memset(((char *)to) + sizeof(struct kernel_siginfo), 0, SI_EXPANSION_SIZE); } int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from); int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from); enum siginfo_layout { SIL_KILL, SIL_TIMER, SIL_POLL, SIL_FAULT, SIL_FAULT_MCEERR, SIL_FAULT_BNDERR, SIL_FAULT_PKUERR, SIL_CHLD, SIL_RT, SIL_SYS, }; enum siginfo_layout siginfo_layout(unsigned sig, int si_code); /* * Define some primitives to manipulate sigset_t. */ #ifndef __HAVE_ARCH_SIG_BITOPS #include <linux/bitops.h> /* We don't use <linux/bitops.h> for these because there is no need to be atomic. */ static inline void sigaddset(sigset_t *set, int _sig) { unsigned long sig = _sig - 1; if (_NSIG_WORDS == 1) set->sig[0] |= 1UL << sig; else set->sig[sig / _NSIG_BPW] |= 1UL << (sig % _NSIG_BPW); } static inline void sigdelset(sigset_t *set, int _sig) { unsigned long sig = _sig - 1; if (_NSIG_WORDS == 1) set->sig[0] &= ~(1UL << sig); else set->sig[sig / _NSIG_BPW] &= ~(1UL << (sig % _NSIG_BPW)); } static inline int sigismember(sigset_t *set, int _sig) { unsigned long sig = _sig - 1; if (_NSIG_WORDS == 1) return 1 & (set->sig[0] >> sig); else return 1 & (set->sig[sig / _NSIG_BPW] >> (sig % _NSIG_BPW)); } #endif /* __HAVE_ARCH_SIG_BITOPS */ static inline int sigisemptyset(sigset_t *set) { switch (_NSIG_WORDS) { case 4: return (set->sig[3] | set->sig[2] | set->sig[1] | set->sig[0]) == 0; case 2: return (set->sig[1] | set->sig[0]) == 0; case 1: return set->sig[0] == 0; default: BUILD_BUG(); return 0; } } static inline int sigequalsets(const sigset_t *set1, const sigset_t *set2) { switch (_NSIG_WORDS) { case 4: return (set1->sig[3] == set2->sig[3]) && (set1->sig[2] == set2->sig[2]) && (set1->sig[1] == set2->sig[1]) && (set1->sig[0] == set2->sig[0]); case 2: return (set1->sig[1] == set2->sig[1]) && (set1->sig[0] == set2->sig[0]); case 1: return set1->sig[0] == set2->sig[0]; } return 0; } #define sigmask(sig) (1UL << ((sig) - 1)) #ifndef __HAVE_ARCH_SIG_SETOPS #include <linux/string.h> #define _SIG_SET_BINOP(name, op) \ static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \ { \ unsigned long a0, a1, a2, a3, b0, b1, b2, b3; \ \ switch (_NSIG_WORDS) { \ case 4: \ a3 = a->sig[3]; a2 = a->sig[2]; \ b3 = b->sig[3]; b2 = b->sig[2]; \ r->sig[3] = op(a3, b3); \ r->sig[2] = op(a2, b2); \ fallthrough; \ case 2: \ a1 = a->sig[1]; b1 = b->sig[1]; \ r->sig[1] = op(a1, b1); \ fallthrough; \ case 1: \ a0 = a->sig[0]; b0 = b->sig[0]; \ r->sig[0] = op(a0, b0); \ break; \ default: \ BUILD_BUG(); \ } \ } #define _sig_or(x,y) ((x) | (y)) _SIG_SET_BINOP(sigorsets, _sig_or) #define _sig_and(x,y) ((x) & (y)) _SIG_SET_BINOP(sigandsets, _sig_and) #define _sig_andn(x,y) ((x) & ~(y)) _SIG_SET_BINOP(sigandnsets, _sig_andn) #undef _SIG_SET_BINOP #undef _sig_or #undef _sig_and #undef _sig_andn #define _SIG_SET_OP(name, op) \ static inline void name(sigset_t *set) \ { \ switch (_NSIG_WORDS) { \ case 4: set->sig[3] = op(set->sig[3]); \ set->sig[2] = op(set->sig[2]); \ fallthrough; \ case 2: set->sig[1] = op(set->sig[1]); \ fallthrough; \ case 1: set->sig[0] = op(set->sig[0]); \ break; \ default: \ BUILD_BUG(); \ } \ } #define _sig_not(x) (~(x)) _SIG_SET_OP(signotset, _sig_not) #undef _SIG_SET_OP #undef _sig_not static inline void sigemptyset(sigset_t *set) { switch (_NSIG_WORDS) { default: memset(set, 0, sizeof(sigset_t)); break; case 2: set->sig[1] = 0; fallthrough; case 1: set->sig[0] = 0; break; } } static inline void sigfillset(sigset_t *set) { switch (_NSIG_WORDS) { default: memset(set, -1, sizeof(sigset_t)); break; case 2: set->sig[1] = -1; fallthrough; case 1: set->sig[0] = -1; break; } } /* Some extensions for manipulating the low 32 signals in particular. */ static inline void sigaddsetmask(sigset_t *set, unsigned long mask) { set->sig[0] |= mask; } static inline void sigdelsetmask(sigset_t *set, unsigned long mask) { set->sig[0] &= ~mask; } static inline int sigtestsetmask(sigset_t *set, unsigned long mask) { return (set->sig[0] & mask) != 0; } static inline void siginitset(sigset_t *set, unsigned long mask) { set->sig[0] = mask; switch (_NSIG_WORDS) { default: memset(&set->sig[1], 0, sizeof(long)*(_NSIG_WORDS-1)); break; case 2: set->sig[1] = 0; break; case 1: ; } } static inline void siginitsetinv(sigset_t *set, unsigned long mask) { set->sig[0] = ~mask; switch (_NSIG_WORDS) { default: memset(&set->sig[1], -1, sizeof(long)*(_NSIG_WORDS-1)); break; case 2: set->sig[1] = -1; break; case 1: ; } } #endif /* __HAVE_ARCH_SIG_SETOPS */ static inline void init_sigpending(struct sigpending *sig) { sigemptyset(&sig->signal); INIT_LIST_HEAD(&sig->list); } extern void flush_sigqueue(struct sigpending *queue); /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ static inline int valid_signal(unsigned long sig) { return sig <= _NSIG ? 1 : 0; } struct timespec; struct pt_regs; enum pid_type; extern int next_signal(struct sigpending *pending, sigset_t *mask); extern int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type); extern int __group_send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; extern bool get_signal(struct ksignal *ksig); extern void signal_setup_done(int failed, struct ksignal *ksig, int stepping); extern void exit_signals(struct task_struct *tsk); extern void kernel_sigaction(int, __sighandler_t); #define SIG_KTHREAD ((__force __sighandler_t)2) #define SIG_KTHREAD_KERNEL ((__force __sighandler_t)3) static inline void allow_signal(int sig) { /* * Kernel threads handle their own signals. Let the signal code * know it'll be handled, so that they don't get converted to * SIGKILL or just silently dropped. */ kernel_sigaction(sig, SIG_KTHREAD); } static inline void allow_kernel_signal(int sig) { /* * Kernel threads handle their own signals. Let the signal code * know signals sent by the kernel will be handled, so that they * don't get silently dropped. */ kernel_sigaction(sig, SIG_KTHREAD_KERNEL); } static inline void disallow_signal(int sig) { kernel_sigaction(sig, SIG_IGN); } extern struct kmem_cache *sighand_cachep; extern bool unhandled_signal(struct task_struct *tsk, int sig); /* * In POSIX a signal is sent either to a specific thread (Linux task) * or to the process as a whole (Linux thread group). How the signal * is sent determines whether it's to one thread or the whole group, * which determines which signal mask(s) are involved in blocking it * from being delivered until later. When the signal is delivered, * either it's caught or ignored by a user handler or it has a default * effect that applies to the whole thread group (POSIX process). * * The possible effects an unblocked signal set to SIG_DFL can have are: * ignore - Nothing Happens * terminate - kill the process, i.e. all threads in the group, * similar to exit_group. The group leader (only) reports * WIFSIGNALED status to its parent. * coredump - write a core dump file describing all threads using * the same mm and then kill all those threads * stop - stop all the threads in the group, i.e. TASK_STOPPED state * * SIGKILL and SIGSTOP cannot be caught, blocked, or ignored. * Other signals when not blocked and set to SIG_DFL behaves as follows. * The job control signals also have other special effects. * * +--------------------+------------------+ * | POSIX signal | default action | * +--------------------+------------------+ * | SIGHUP | terminate | * | SIGINT | terminate | * | SIGQUIT | coredump | * | SIGILL | coredump | * | SIGTRAP | coredump | * | SIGABRT/SIGIOT | coredump | * | SIGBUS | coredump | * | SIGFPE | coredump | * | SIGKILL | terminate(+) | * | SIGUSR1 | terminate | * | SIGSEGV | coredump | * | SIGUSR2 | terminate | * | SIGPIPE | terminate | * | SIGALRM | terminate | * | SIGTERM | terminate | * | SIGCHLD | ignore | * | SIGCONT | ignore(*) | * | SIGSTOP | stop(*)(+) | * | SIGTSTP | stop(*) | * | SIGTTIN | stop(*) | * | SIGTTOU | stop(*) | * | SIGURG | ignore | * | SIGXCPU | coredump | * | SIGXFSZ | coredump | * | SIGVTALRM | terminate | * | SIGPROF | terminate | * | SIGPOLL/SIGIO | terminate | * | SIGSYS/SIGUNUSED | coredump | * | SIGSTKFLT | terminate | * | SIGWINCH | ignore | * | SIGPWR | terminate | * | SIGRTMIN-SIGRTMAX | terminate | * +--------------------+------------------+ * | non-POSIX signal | default action | * +--------------------+------------------+ * | SIGEMT | coredump | * +--------------------+------------------+ * * (+) For SIGKILL and SIGSTOP the action is "always", not just "default". * (*) Special job control effects: * When SIGCONT is sent, it resumes the process (all threads in the group) * from TASK_STOPPED state and also clears any pending/queued stop signals * (any of those marked with "stop(*)"). This happens regardless of blocking, * catching, or ignoring SIGCONT. When any stop signal is sent, it clears * any pending/queued SIGCONT signals; this happens regardless of blocking, * catching, or ignored the stop signal, though (except for SIGSTOP) the * default action of stopping the process may happen later or never. */ #ifdef SIGEMT #define SIGEMT_MASK rt_sigmask(SIGEMT) #else #define SIGEMT_MASK 0 #endif #if SIGRTMIN > BITS_PER_LONG #define rt_sigmask(sig) (1ULL << ((sig)-1)) #else #define rt_sigmask(sig) sigmask(sig) #endif #define siginmask(sig, mask) \ ((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) #define SIG_KERNEL_ONLY_MASK (\ rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP)) #define SIG_KERNEL_STOP_MASK (\ rt_sigmask(SIGSTOP) | rt_sigmask(SIGTSTP) | \ rt_sigmask(SIGTTIN) | rt_sigmask(SIGTTOU) ) #define SIG_KERNEL_COREDUMP_MASK (\ rt_sigmask(SIGQUIT) | rt_sigmask(SIGILL) | \ rt_sigmask(SIGTRAP) | rt_sigmask(SIGABRT) | \ rt_sigmask(SIGFPE) | rt_sigmask(SIGSEGV) | \ rt_sigmask(SIGBUS) | rt_sigmask(SIGSYS) | \ rt_sigmask(SIGXCPU) | rt_sigmask(SIGXFSZ) | \ SIGEMT_MASK ) #define SIG_KERNEL_IGNORE_MASK (\ rt_sigmask(SIGCONT) | rt_sigmask(SIGCHLD) | \ rt_sigmask(SIGWINCH) | rt_sigmask(SIGURG) ) #define SIG_SPECIFIC_SICODES_MASK (\ rt_sigmask(SIGILL) | rt_sigmask(SIGFPE) | \ rt_sigmask(SIGSEGV) | rt_sigmask(SIGBUS) | \ rt_sigmask(SIGTRAP) | rt_sigmask(SIGCHLD) | \ rt_sigmask(SIGPOLL) | rt_sigmask(SIGSYS) | \ SIGEMT_MASK ) #define sig_kernel_only(sig) siginmask(sig, SIG_KERNEL_ONLY_MASK) #define sig_kernel_coredump(sig) siginmask(sig, SIG_KERNEL_COREDUMP_MASK) #define sig_kernel_ignore(sig) siginmask(sig, SIG_KERNEL_IGNORE_MASK) #define sig_kernel_stop(sig) siginmask(sig, SIG_KERNEL_STOP_MASK) #define sig_specific_sicodes(sig) siginmask(sig, SIG_SPECIFIC_SICODES_MASK) #define sig_fatal(t, signr) \ (!siginmask(signr, SIG_KERNEL_IGNORE_MASK|SIG_KERNEL_STOP_MASK) && \ (t)->sighand->action[(signr)-1].sa.sa_handler == SIG_DFL) void signals_init(void); int restore_altstack(const stack_t __user *); int __save_altstack(stack_t __user *, unsigned long); #define unsafe_save_altstack(uss, sp, label) do { \ stack_t __user *__uss = uss; \ struct task_struct *t = current; \ unsafe_put_user((void __user *)t->sas_ss_sp, &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ if (t->sas_ss_flags & SS_AUTODISARM) \ sas_ss_reset(t); \ } while (0); #ifdef CONFIG_PROC_FS struct seq_file; extern void render_sigset_t(struct seq_file *, const char *, sigset_t *); #endif #endif /* _LINUX_SIGNAL_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 | /* * Resizable virtual memory filesystem for Linux. * * Copyright (C) 2000 Linus Torvalds. * 2000 Transmeta Corp. * 2000-2001 Christoph Rohland * 2000-2001 SAP AG * 2002 Red Hat Inc. * Copyright (C) 2002-2011 Hugh Dickins. * Copyright (C) 2011 Google Inc. * Copyright (C) 2002-2005 VERITAS Software Corporation. * Copyright (C) 2004 Andi Kleen, SuSE Labs * * Extended attribute support for tmpfs: * Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net> * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> * * tiny-shmem: * Copyright (c) 2004, 2008 Matt Mackall <mpm@selenic.com> * * This file is released under the GPL. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/vfs.h> #include <linux/mount.h> #include <linux/ramfs.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/random.h> #include <linux/sched/signal.h> #include <linux/export.h> #include <linux/swap.h> #include <linux/uio.h> #include <linux/khugepaged.h> #include <linux/hugetlb.h> #include <linux/frontswap.h> #include <linux/fs_parser.h> #include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */ static struct vfsmount *shm_mnt; #ifdef CONFIG_SHMEM /* * This virtual memory filesystem is heavily based on the ramfs. It * extends ramfs by the ability to use swap and honor resource limits * which makes it a completely usable filesystem. */ #include <linux/xattr.h> #include <linux/exportfs.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/mman.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/shmem_fs.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/pagevec.h> #include <linux/percpu_counter.h> #include <linux/falloc.h> #include <linux/splice.h> #include <linux/security.h> #include <linux/swapops.h> #include <linux/mempolicy.h> #include <linux/namei.h> #include <linux/ctype.h> #include <linux/migrate.h> #include <linux/highmem.h> #include <linux/seq_file.h> #include <linux/magic.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <uapi/linux/memfd.h> #include <linux/userfaultfd_k.h> #include <linux/rmap.h> #include <linux/uuid.h> #include <linux/uaccess.h> #include "internal.h" #define BLOCKS_PER_PAGE (PAGE_SIZE/512) #define VM_ACCT(size) (PAGE_ALIGN(size) >> PAGE_SHIFT) /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 /* Symlink up to this size is kmalloc'ed instead of using a swappable page */ #define SHORT_SYMLINK_LEN 128 /* * shmem_fallocate communicates with shmem_fault or shmem_writepage via * inode->i_private (with i_mutex making sure that it has only one user at * a time): we would prefer not to enlarge the shmem inode just for that. */ struct shmem_falloc { wait_queue_head_t *waitq; /* faults into hole wait for punch to end */ pgoff_t start; /* start of range currently being fallocated */ pgoff_t next; /* the next page offset to be fallocated */ pgoff_t nr_falloced; /* how many new pages have been fallocated */ pgoff_t nr_unswapped; /* how often writepage refused to swap out */ }; struct shmem_options { unsigned long long blocks; unsigned long long inodes; struct mempolicy *mpol; kuid_t uid; kgid_t gid; umode_t mode; bool full_inums; int huge; int seen; #define SHMEM_SEEN_BLOCKS 1 #define SHMEM_SEEN_INODES 2 #define SHMEM_SEEN_HUGE 4 #define SHMEM_SEEN_INUMS 8 }; #ifdef CONFIG_TMPFS static unsigned long shmem_default_max_blocks(void) { return totalram_pages() / 2; } static unsigned long shmem_default_max_inodes(void) { unsigned long nr_pages = totalram_pages(); return min(nr_pages - totalhigh_pages(), nr_pages / 2); } #endif static bool shmem_should_replace_page(struct page *page, gfp_t gfp); static int shmem_replace_page(struct page **pagep, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index); static int shmem_swapin_page(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, vm_fault_t *fault_type); static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, struct vm_fault *vmf, vm_fault_t *fault_type); int shmem_getpage(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp) { return shmem_getpage_gfp(inode, index, pagep, sgp, mapping_gfp_mask(inode->i_mapping), NULL, NULL, NULL); } static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) { return sb->s_fs_info; } /* * shmem_file_setup pre-accounts the whole fixed size of a VM object, * for shared memory and for shared anonymous (/dev/zero) mappings * (unless MAP_NORESERVE and sysctl_overcommit_memory <= 1), * consistent with the pre-accounting of private mappings ... */ static inline int shmem_acct_size(unsigned long flags, loff_t size) { return (flags & VM_NORESERVE) ? 0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(size)); } static inline void shmem_unacct_size(unsigned long flags, loff_t size) { if (!(flags & VM_NORESERVE)) vm_unacct_memory(VM_ACCT(size)); } static inline int shmem_reacct_size(unsigned long flags, loff_t oldsize, loff_t newsize) { if (!(flags & VM_NORESERVE)) { if (VM_ACCT(newsize) > VM_ACCT(oldsize)) return security_vm_enough_memory_mm(current->mm, VM_ACCT(newsize) - VM_ACCT(oldsize)); else if (VM_ACCT(newsize) < VM_ACCT(oldsize)) vm_unacct_memory(VM_ACCT(oldsize) - VM_ACCT(newsize)); } return 0; } /* * ... whereas tmpfs objects are accounted incrementally as * pages are allocated, in order to allow large sparse files. * shmem_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM, * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM. */ static inline int shmem_acct_block(unsigned long flags, long pages) { if (!(flags & VM_NORESERVE)) return 0; return security_vm_enough_memory_mm(current->mm, pages * VM_ACCT(PAGE_SIZE)); } static inline void shmem_unacct_blocks(unsigned long flags, long pages) { if (flags & VM_NORESERVE) vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE)); } static inline bool shmem_inode_acct_block(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (shmem_acct_block(info->flags, pages)) return false; if (sbinfo->max_blocks) { if (percpu_counter_compare(&sbinfo->used_blocks, sbinfo->max_blocks - pages) > 0) goto unacct; percpu_counter_add(&sbinfo->used_blocks, pages); } return true; unacct: shmem_unacct_blocks(info->flags, pages); return false; } static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (sbinfo->max_blocks) percpu_counter_sub(&sbinfo->used_blocks, pages); shmem_unacct_blocks(info->flags, pages); } static const struct super_operations shmem_ops; static const struct address_space_operations shmem_aops; static const struct file_operations shmem_file_operations; static const struct inode_operations shmem_inode_operations; static const struct inode_operations shmem_dir_inode_operations; static const struct inode_operations shmem_special_inode_operations; static const struct vm_operations_struct shmem_vm_ops; static struct file_system_type shmem_fs_type; bool vma_is_shmem(struct vm_area_struct *vma) { return vma->vm_ops == &shmem_vm_ops; } static LIST_HEAD(shmem_swaplist); static DEFINE_MUTEX(shmem_swaplist_mutex); /* * shmem_reserve_inode() performs bookkeeping to reserve a shmem inode, and * produces a novel ino for the newly allocated inode. * * It may also be called when making a hard link to permit the space needed by * each dentry. However, in that case, no new inode number is needed since that * internally draws from another pool of inode numbers (currently global * get_next_ino()). This case is indicated by passing NULL as inop. */ #define SHMEM_INO_BATCH 1024 static int shmem_reserve_inode(struct super_block *sb, ino_t *inop) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); ino_t ino; if (!(sb->s_flags & SB_KERNMOUNT)) { spin_lock(&sbinfo->stat_lock); if (sbinfo->max_inodes) { if (!sbinfo->free_inodes) { spin_unlock(&sbinfo->stat_lock); return -ENOSPC; } sbinfo->free_inodes--; } if (inop) { ino = sbinfo->next_ino++; if (unlikely(is_zero_ino(ino))) ino = sbinfo->next_ino++; if (unlikely(!sbinfo->full_inums && ino > UINT_MAX)) { /* * Emulate get_next_ino uint wraparound for * compatibility */ if (IS_ENABLED(CONFIG_64BIT)) pr_warn("%s: inode number overflow on device %d, consider using inode64 mount option\n", __func__, MINOR(sb->s_dev)); sbinfo->next_ino = 1; ino = sbinfo->next_ino++; } *inop = ino; } spin_unlock(&sbinfo->stat_lock); } else if (inop) { /* * __shmem_file_setup, one of our callers, is lock-free: it * doesn't hold stat_lock in shmem_reserve_inode since * max_inodes is always 0, and is called from potentially * unknown contexts. As such, use a per-cpu batched allocator * which doesn't require the per-sb stat_lock unless we are at * the batch boundary. * * We don't need to worry about inode{32,64} since SB_KERNMOUNT * shmem mounts are not exposed to userspace, so we don't need * to worry about things like glibc compatibility. */ ino_t *next_ino; next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu()); ino = *next_ino; if (unlikely(ino % SHMEM_INO_BATCH == 0)) { spin_lock(&sbinfo->stat_lock); ino = sbinfo->next_ino; sbinfo->next_ino += SHMEM_INO_BATCH; spin_unlock(&sbinfo->stat_lock); if (unlikely(is_zero_ino(ino))) ino++; } *inop = ino; *next_ino = ++ino; put_cpu(); } return 0; } static void shmem_free_inode(struct super_block *sb) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (sbinfo->max_inodes) { spin_lock(&sbinfo->stat_lock); sbinfo->free_inodes++; spin_unlock(&sbinfo->stat_lock); } } /** * shmem_recalc_inode - recalculate the block usage of an inode * @inode: inode to recalc * * We have to calculate the free blocks since the mm can drop * undirtied hole pages behind our back. * * But normally info->alloced == inode->i_mapping->nrpages + info->swapped * So mm freed is info->alloced - (inode->i_mapping->nrpages + info->swapped) * * It has to be called with the spinlock held. */ static void shmem_recalc_inode(struct inode *inode) { struct shmem_inode_info *info = SHMEM_I(inode); long freed; freed = info->alloced - info->swapped - inode->i_mapping->nrpages; if (freed > 0) { info->alloced -= freed; inode->i_blocks -= freed * BLOCKS_PER_PAGE; shmem_inode_unacct_blocks(inode, freed); } } bool shmem_charge(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); unsigned long flags; if (!shmem_inode_acct_block(inode, pages)) return false; /* nrpages adjustment first, then shmem_recalc_inode() when balanced */ inode->i_mapping->nrpages += pages; spin_lock_irqsave(&info->lock, flags); info->alloced += pages; inode->i_blocks += pages * BLOCKS_PER_PAGE; shmem_recalc_inode(inode); spin_unlock_irqrestore(&info->lock, flags); return true; } void shmem_uncharge(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); unsigned long flags; /* nrpages adjustment done by __delete_from_page_cache() or caller */ spin_lock_irqsave(&info->lock, flags); info->alloced -= pages; inode->i_blocks -= pages * BLOCKS_PER_PAGE; shmem_recalc_inode(inode); spin_unlock_irqrestore(&info->lock, flags); shmem_inode_unacct_blocks(inode, pages); } /* * Replace item expected in xarray by a new item, while holding xa_lock. */ static int shmem_replace_entry(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { XA_STATE(xas, &mapping->i_pages, index); void *item; VM_BUG_ON(!expected); VM_BUG_ON(!replacement); item = xas_load(&xas); if (item != expected) return -ENOENT; xas_store(&xas, replacement); return 0; } /* * Sometimes, before we decide whether to proceed or to fail, we must check * that an entry was not already brought back from swap by a racing thread. * * Checking page is not enough: by the time a SwapCache page is locked, it * might be reused, and again be SwapCache, using the same swap as before. */ static bool shmem_confirm_swap(struct address_space *mapping, pgoff_t index, swp_entry_t swap) { return xa_load(&mapping->i_pages, index) == swp_to_radix_entry(swap); } /* * Definitions for "huge tmpfs": tmpfs mounted with the huge= option * * SHMEM_HUGE_NEVER: * disables huge pages for the mount; * SHMEM_HUGE_ALWAYS: * enables huge pages for the mount; * SHMEM_HUGE_WITHIN_SIZE: * only allocate huge pages if the page will be fully within i_size, * also respect fadvise()/madvise() hints; * SHMEM_HUGE_ADVISE: * only allocate huge pages if requested with fadvise()/madvise(); */ #define SHMEM_HUGE_NEVER 0 #define SHMEM_HUGE_ALWAYS 1 #define SHMEM_HUGE_WITHIN_SIZE 2 #define SHMEM_HUGE_ADVISE 3 /* * Special values. * Only can be set via /sys/kernel/mm/transparent_hugepage/shmem_enabled: * * SHMEM_HUGE_DENY: * disables huge on shm_mnt and all mounts, for emergency use; * SHMEM_HUGE_FORCE: * enables huge on shm_mnt and all mounts, w/o needing option, for testing; * */ #define SHMEM_HUGE_DENY (-1) #define SHMEM_HUGE_FORCE (-2) #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* ifdef here to avoid bloating shmem.o when not necessary */ static int shmem_huge __read_mostly; #if defined(CONFIG_SYSFS) static int shmem_parse_huge(const char *str) { if (!strcmp(str, "never")) return SHMEM_HUGE_NEVER; if (!strcmp(str, "always")) return SHMEM_HUGE_ALWAYS; if (!strcmp(str, "within_size")) return SHMEM_HUGE_WITHIN_SIZE; if (!strcmp(str, "advise")) return SHMEM_HUGE_ADVISE; if (!strcmp(str, "deny")) return SHMEM_HUGE_DENY; if (!strcmp(str, "force")) return SHMEM_HUGE_FORCE; return -EINVAL; } #endif #if defined(CONFIG_SYSFS) || defined(CONFIG_TMPFS) static const char *shmem_format_huge(int huge) { switch (huge) { case SHMEM_HUGE_NEVER: return "never"; case SHMEM_HUGE_ALWAYS: return "always"; case SHMEM_HUGE_WITHIN_SIZE: return "within_size"; case SHMEM_HUGE_ADVISE: return "advise"; case SHMEM_HUGE_DENY: return "deny"; case SHMEM_HUGE_FORCE: return "force"; default: VM_BUG_ON(1); return "bad_val"; } } #endif static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { LIST_HEAD(list), *pos, *next; LIST_HEAD(to_remove); struct inode *inode; struct shmem_inode_info *info; struct page *page; unsigned long batch = sc ? sc->nr_to_scan : 128; int split = 0; if (list_empty(&sbinfo->shrinklist)) return SHRINK_STOP; spin_lock(&sbinfo->shrinklist_lock); list_for_each_safe(pos, next, &sbinfo->shrinklist) { info = list_entry(pos, struct shmem_inode_info, shrinklist); /* pin the inode */ inode = igrab(&info->vfs_inode); /* inode is about to be evicted */ if (!inode) { list_del_init(&info->shrinklist); goto next; } /* Check if there's anything to gain */ if (round_up(inode->i_size, PAGE_SIZE) == round_up(inode->i_size, HPAGE_PMD_SIZE)) { list_move(&info->shrinklist, &to_remove); goto next; } list_move(&info->shrinklist, &list); next: sbinfo->shrinklist_len--; if (!--batch) break; } spin_unlock(&sbinfo->shrinklist_lock); list_for_each_safe(pos, next, &to_remove) { info = list_entry(pos, struct shmem_inode_info, shrinklist); inode = &info->vfs_inode; list_del_init(&info->shrinklist); iput(inode); } list_for_each_safe(pos, next, &list) { int ret; info = list_entry(pos, struct shmem_inode_info, shrinklist); inode = &info->vfs_inode; if (nr_to_split && split >= nr_to_split) goto move_back; page = find_get_page(inode->i_mapping, (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT); if (!page) goto drop; /* No huge page at the end of the file: nothing to split */ if (!PageTransHuge(page)) { put_page(page); goto drop; } /* * Move the inode on the list back to shrinklist if we failed * to lock the page at this time. * * Waiting for the lock may lead to deadlock in the * reclaim path. */ if (!trylock_page(page)) { put_page(page); goto move_back; } ret = split_huge_page(page); unlock_page(page); put_page(page); /* If split failed move the inode on the list back to shrinklist */ if (ret) goto move_back; split++; drop: list_del_init(&info->shrinklist); goto put; move_back: /* * Make sure the inode is either on the global list or deleted * from any local list before iput() since it could be deleted * in another thread once we put the inode (then the local list * is corrupted). */ spin_lock(&sbinfo->shrinklist_lock); list_move(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; spin_unlock(&sbinfo->shrinklist_lock); put: iput(inode); } return split; } static long shmem_unused_huge_scan(struct super_block *sb, struct shrink_control *sc) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (!READ_ONCE(sbinfo->shrinklist_len)) return SHRINK_STOP; return shmem_unused_huge_shrink(sbinfo, sc, 0); } static long shmem_unused_huge_count(struct super_block *sb, struct shrink_control *sc) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); return READ_ONCE(sbinfo->shrinklist_len); } #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ #define shmem_huge SHMEM_HUGE_DENY static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo) { if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && (shmem_huge == SHMEM_HUGE_FORCE || sbinfo->huge) && shmem_huge != SHMEM_HUGE_DENY) return true; return false; } /* * Like add_to_page_cache_locked, but error if expected item has gone. */ static int shmem_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t index, void *expected, gfp_t gfp, struct mm_struct *charge_mm) { XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page)); unsigned long i = 0; unsigned long nr = compound_nr(page); int error; VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(index != round_down(index, nr), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageSwapBacked(page), page); VM_BUG_ON(expected && PageTransHuge(page)); page_ref_add(page, nr); page->mapping = mapping; page->index = index; if (!PageSwapCache(page)) { error = mem_cgroup_charge(page, charge_mm, gfp); if (error) { if (PageTransHuge(page)) { count_vm_event(THP_FILE_FALLBACK); count_vm_event(THP_FILE_FALLBACK_CHARGE); } goto error; } } cgroup_throttle_swaprate(page, gfp); do { void *entry; xas_lock_irq(&xas); entry = xas_find_conflict(&xas); if (entry != expected) xas_set_err(&xas, -EEXIST); xas_create_range(&xas); if (xas_error(&xas)) goto unlock; next: xas_store(&xas, page); if (++i < nr) { xas_next(&xas); goto next; } if (PageTransHuge(page)) { count_vm_event(THP_FILE_ALLOC); __inc_node_page_state(page, NR_SHMEM_THPS); } mapping->nrpages += nr; __mod_lruvec_page_state(page, NR_FILE_PAGES, nr); __mod_lruvec_page_state(page, NR_SHMEM, nr); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { error = xas_error(&xas); goto error; } return 0; error: page->mapping = NULL; page_ref_sub(page, nr); return error; } /* * Like delete_from_page_cache, but substitutes swap for page. */ static void shmem_delete_from_page_cache(struct page *page, void *radswap) { struct address_space *mapping = page->mapping; int error; VM_BUG_ON_PAGE(PageCompound(page), page); xa_lock_irq(&mapping->i_pages); error = shmem_replace_entry(mapping, page->index, page, radswap); page->mapping = NULL; mapping->nrpages--; __dec_lruvec_page_state(page, NR_FILE_PAGES); __dec_lruvec_page_state(page, NR_SHMEM); xa_unlock_irq(&mapping->i_pages); put_page(page); BUG_ON(error); } /* * Remove swap entry from page cache, free the swap and its page cache. */ static int shmem_free_swap(struct address_space *mapping, pgoff_t index, void *radswap) { void *old; old = xa_cmpxchg_irq(&mapping->i_pages, index, radswap, NULL, 0); if (old != radswap) return -ENOENT; free_swap_and_cache(radix_to_swp_entry(radswap)); return 0; } /* * Determine (in bytes) how many of the shmem object's pages mapped by the * given offsets are swapped out. * * This is safe to call without i_mutex or the i_pages lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned long swapped = 0; rcu_read_lock(); xas_for_each(&xas, page, end - 1) { if (xas_retry(&xas, page)) continue; if (xa_is_value(page)) swapped++; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); return swapped << PAGE_SHIFT; } /* * Determine (in bytes) how many of the shmem object's pages mapped by the * given vma is swapped out. * * This is safe to call without i_mutex or the i_pages lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ unsigned long shmem_swap_usage(struct vm_area_struct *vma) { struct inode *inode = file_inode(vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); struct address_space *mapping = inode->i_mapping; unsigned long swapped; /* Be careful as we don't hold info->lock */ swapped = READ_ONCE(info->swapped); /* * The easier cases are when the shmem object has nothing in swap, or * the vma maps it whole. Then we can simply use the stats that we * already track. */ if (!swapped) return 0; if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size) return swapped << PAGE_SHIFT; /* Here comes the more involved part */ return shmem_partial_swap_usage(mapping, linear_page_index(vma, vma->vm_start), linear_page_index(vma, vma->vm_end)); } /* * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. */ void shmem_unlock_mapping(struct address_space *mapping) { struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index = 0; pagevec_init(&pvec); /* * Minor point, but we might as well stop if someone else SHM_LOCKs it. */ while (!mapping_unevictable(mapping)) { /* * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it * has finished, if it hits a row of PAGEVEC_SIZE swap entries. */ pvec.nr = find_get_entries(mapping, index, PAGEVEC_SIZE, pvec.pages, indices); if (!pvec.nr) break; index = indices[pvec.nr - 1] + 1; pagevec_remove_exceptionals(&pvec); check_move_unevictable_pages(&pvec); pagevec_release(&pvec); cond_resched(); } } /* * Check whether a hole-punch or truncation needs to split a huge page, * returning true if no split was required, or the split has been successful. * * Eviction (or truncation to 0 size) should never need to split a huge page; * but in rare cases might do so, if shmem_undo_range() failed to trylock on * head, and then succeeded to trylock on tail. * * A split can only succeed when there are no additional references on the * huge page: so the split below relies upon find_get_entries() having stopped * when it found a subpage of the huge page, without getting further references. */ static bool shmem_punch_compound(struct page *page, pgoff_t start, pgoff_t end) { if (!PageTransCompound(page)) return true; /* Just proceed to delete a huge page wholly within the range punched */ if (PageHead(page) && page->index >= start && page->index + HPAGE_PMD_NR <= end) return true; /* Try to split huge page, so we can truly punch the hole or truncate */ return split_huge_page(page) >= 0; } /* * Remove range of pages and swap entries from page cache, and free them. * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate. */ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, bool unfalloc) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; pgoff_t end = (lend + 1) >> PAGE_SHIFT; unsigned int partial_start = lstart & (PAGE_SIZE - 1); unsigned int partial_end = (lend + 1) & (PAGE_SIZE - 1); struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; long nr_swaps_freed = 0; pgoff_t index; int i; if (lend == -1) end = -1; /* unsigned, so actually very big */ pagevec_init(&pvec); index = start; while (index < end) { pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), pvec.pages, indices); if (!pvec.nr) break; for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; index = indices[i]; if (index >= end) break; if (xa_is_value(page)) { if (unfalloc) continue; nr_swaps_freed += !shmem_free_swap(mapping, index, page); continue; } VM_BUG_ON_PAGE(page_to_pgoff(page) != index, page); if (!trylock_page(page)) continue; if ((!unfalloc || !PageUptodate(page)) && page_mapping(page) == mapping) { VM_BUG_ON_PAGE(PageWriteback(page), page); if (shmem_punch_compound(page, start, end)) truncate_inode_page(mapping, page); } unlock_page(page); } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); cond_resched(); index++; } if (partial_start) { struct page *page = NULL; shmem_getpage(inode, start - 1, &page, SGP_READ); if (page) { unsigned int top = PAGE_SIZE; if (start > end) { top = partial_end; partial_end = 0; } zero_user_segment(page, partial_start, top); set_page_dirty(page); unlock_page(page); put_page(page); } } if (partial_end) { struct page *page = NULL; shmem_getpage(inode, end, &page, SGP_READ); if (page) { zero_user_segment(page, 0, partial_end); set_page_dirty(page); unlock_page(page); put_page(page); } } if (start >= end) return; index = start; while (index < end) { cond_resched(); pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), pvec.pages, indices); if (!pvec.nr) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) break; /* But if truncating, restart to make sure all gone */ index = start; continue; } for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; index = indices[i]; if (index >= end) break; if (xa_is_value(page)) { if (unfalloc) continue; if (shmem_free_swap(mapping, index, page)) { /* Swap was replaced by page: retry */ index--; break; } nr_swaps_freed++; continue; } lock_page(page); if (!unfalloc || !PageUptodate(page)) { if (page_mapping(page) != mapping) { /* Page was replaced by swap: retry */ unlock_page(page); index--; break; } VM_BUG_ON_PAGE(PageWriteback(page), page); if (shmem_punch_compound(page, start, end)) truncate_inode_page(mapping, page); else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { /* Wipe the page and don't get stuck */ clear_highpage(page); flush_dcache_page(page); set_page_dirty(page); if (index < round_up(start, HPAGE_PMD_NR)) start = index + 1; } } unlock_page(page); } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); index++; } spin_lock_irq(&info->lock); info->swapped -= nr_swaps_freed; shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); } void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { shmem_undo_range(inode, lstart, lend, false); inode->i_ctime = inode->i_mtime = current_time(inode); } EXPORT_SYMBOL_GPL(shmem_truncate_range); static int shmem_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = path->dentry->d_inode; struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sb_info = SHMEM_SB(inode->i_sb); if (info->alloced - info->swapped != inode->i_mapping->nrpages) { spin_lock_irq(&info->lock); shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); } generic_fillattr(inode, stat); if (is_huge_enabled(sb_info)) stat->blksize = HPAGE_PMD_SIZE; return 0; } static int shmem_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); int error; error = setattr_prepare(dentry, attr); if (error) return error; if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { loff_t oldsize = inode->i_size; loff_t newsize = attr->ia_size; /* protected by i_mutex */ if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) || (newsize > oldsize && (info->seals & F_SEAL_GROW))) return -EPERM; if (newsize != oldsize) { error = shmem_reacct_size(SHMEM_I(inode)->flags, oldsize, newsize); if (error) return error; i_size_write(inode, newsize); inode->i_ctime = inode->i_mtime = current_time(inode); } if (newsize <= oldsize) { loff_t holebegin = round_up(newsize, PAGE_SIZE); if (oldsize > holebegin) unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); if (info->alloced) shmem_truncate_range(inode, newsize, (loff_t)-1); /* unmap again to remove racily COWed private pages */ if (oldsize > holebegin) unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); /* * Part of the huge page can be beyond i_size: subject * to shrink under memory pressure. */ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { spin_lock(&sbinfo->shrinklist_lock); /* * _careful to defend against unlocked access to * ->shrink_list in shmem_unused_huge_shrink() */ if (list_empty_careful(&info->shrinklist)) { list_add_tail(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; } spin_unlock(&sbinfo->shrinklist_lock); } } } setattr_copy(inode, attr); if (attr->ia_valid & ATTR_MODE) error = posix_acl_chmod(inode, inode->i_mode); return error; } static void shmem_evict_inode(struct inode *inode) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); if (inode->i_mapping->a_ops == &shmem_aops) { shmem_unacct_size(info->flags, inode->i_size); inode->i_size = 0; shmem_truncate_range(inode, 0, (loff_t)-1); if (!list_empty(&info->shrinklist)) { spin_lock(&sbinfo->shrinklist_lock); if (!list_empty(&info->shrinklist)) { list_del_init(&info->shrinklist); sbinfo->shrinklist_len--; } spin_unlock(&sbinfo->shrinklist_lock); } while (!list_empty(&info->swaplist)) { /* Wait while shmem_unuse() is scanning this inode... */ wait_var_event(&info->stop_eviction, !atomic_read(&info->stop_eviction)); mutex_lock(&shmem_swaplist_mutex); /* ...but beware of the race if we peeked too early */ if (!atomic_read(&info->stop_eviction)) list_del_init(&info->swaplist); mutex_unlock(&shmem_swaplist_mutex); } } simple_xattrs_free(&info->xattrs); WARN_ON(inode->i_blocks); shmem_free_inode(inode->i_sb); clear_inode(inode); } extern struct swap_info_struct *swap_info[]; static int shmem_find_swap_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices, unsigned int type, bool frontswap) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; swp_entry_t entry; unsigned int ret = 0; if (!nr_entries) return 0; rcu_read_lock(); xas_for_each(&xas, page, ULONG_MAX) { if (xas_retry(&xas, page)) continue; if (!xa_is_value(page)) continue; entry = radix_to_swp_entry(page); if (swp_type(entry) != type) continue; if (frontswap && !frontswap_test(swap_info[type], swp_offset(entry))) continue; indices[ret] = xas.xa_index; entries[ret] = page; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } if (++ret == nr_entries) break; } rcu_read_unlock(); return ret; } /* * Move the swapped pages for an inode to page cache. Returns the count * of pages swapped in, or the error in case of failure. */ static int shmem_unuse_swap_entries(struct inode *inode, struct pagevec pvec, pgoff_t *indices) { int i = 0; int ret = 0; int error = 0; struct address_space *mapping = inode->i_mapping; for (i = 0; i < pvec.nr; i++) { struct page *page = pvec.pages[i]; if (!xa_is_value(page)) continue; error = shmem_swapin_page(inode, indices[i], &page, SGP_CACHE, mapping_gfp_mask(mapping), NULL, NULL); if (error == 0) { unlock_page(page); put_page(page); ret++; } if (error == -ENOMEM) break; error = 0; } return error ? error : ret; } /* * If swap found in inode, free it and move page from swapcache to filecache. */ static int shmem_unuse_inode(struct inode *inode, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct address_space *mapping = inode->i_mapping; pgoff_t start = 0; struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; bool frontswap_partial = (frontswap && *fs_pages_to_unuse > 0); int ret = 0; pagevec_init(&pvec); do { unsigned int nr_entries = PAGEVEC_SIZE; if (frontswap_partial && *fs_pages_to_unuse < PAGEVEC_SIZE) nr_entries = *fs_pages_to_unuse; pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries, pvec.pages, indices, type, frontswap); if (pvec.nr == 0) { ret = 0; break; } ret = shmem_unuse_swap_entries(inode, pvec, indices); if (ret < 0) break; if (frontswap_partial) { *fs_pages_to_unuse -= ret; if (*fs_pages_to_unuse == 0) { ret = FRONTSWAP_PAGES_UNUSED; break; } } start = indices[pvec.nr - 1]; } while (true); return ret; } /* * Read all the shared memory data that resides in the swap * device 'type' back into memory, so the swap device can be * unused. */ int shmem_unuse(unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct shmem_inode_info *info, *next; int error = 0; if (list_empty(&shmem_swaplist)) return 0; mutex_lock(&shmem_swaplist_mutex); list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) { if (!info->swapped) { list_del_init(&info->swaplist); continue; } /* * Drop the swaplist mutex while searching the inode for swap; * but before doing so, make sure shmem_evict_inode() will not * remove placeholder inode from swaplist, nor let it be freed * (igrab() would protect from unlink, but not from unmount). */ atomic_inc(&info->stop_eviction); mutex_unlock(&shmem_swaplist_mutex); error = shmem_unuse_inode(&info->vfs_inode, type, frontswap, fs_pages_to_unuse); cond_resched(); mutex_lock(&shmem_swaplist_mutex); next = list_next_entry(info, swaplist); if (!info->swapped) list_del_init(&info->swaplist); if (atomic_dec_and_test(&info->stop_eviction)) wake_up_var(&info->stop_eviction); if (error) break; } mutex_unlock(&shmem_swaplist_mutex); return error; } /* * Move the page from the page cache to the swap cache. */ static int shmem_writepage(struct page *page, struct writeback_control *wbc) { struct shmem_inode_info *info; struct address_space *mapping; struct inode *inode; swp_entry_t swap; pgoff_t index; VM_BUG_ON_PAGE(PageCompound(page), page); BUG_ON(!PageLocked(page)); mapping = page->mapping; index = page->index; inode = mapping->host; info = SHMEM_I(inode); if (info->flags & VM_LOCKED) goto redirty; if (!total_swap_pages) goto redirty; /* * Our capabilities prevent regular writeback or sync from ever calling * shmem_writepage; but a stacking filesystem might use ->writepage of * its underlying filesystem, in which case tmpfs should write out to * swap only in response to memory pressure, and not for the writeback * threads or sync. */ if (!wbc->for_reclaim) { WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ goto redirty; } /* * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC * value into swapfile.c, the only way we can correctly account for a * fallocated page arriving here is now to initialize it and write it. * * That's okay for a page already fallocated earlier, but if we have * not yet completed the fallocation, then (a) we want to keep track * of this page in case we have to undo it, and (b) it may not be a * good idea to continue anyway, once we're pushing into swap. So * reactivate the page, and let shmem_fallocate() quit when too many. */ if (!PageUptodate(page)) { if (inode->i_private) { struct shmem_falloc *shmem_falloc; spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) shmem_falloc->nr_unswapped++; else shmem_falloc = NULL; spin_unlock(&inode->i_lock); if (shmem_falloc) goto redirty; } clear_highpage(page); flush_dcache_page(page); SetPageUptodate(page); } swap = get_swap_page(page); if (!swap.val) goto redirty; /* * Add inode to shmem_unuse()'s list of swapped-out inodes, * if it's not already there. Do it now before the page is * moved to swap cache, when its pagelock no longer protects * the inode from eviction. But don't unlock the mutex until * we've incremented swapped, because shmem_unuse_inode() will * prune a !swapped inode from the swaplist under this mutex. */ mutex_lock(&shmem_swaplist_mutex); if (list_empty(&info->swaplist)) list_add(&info->swaplist, &shmem_swaplist); if (add_to_swap_cache(page, swap, __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN, NULL) == 0) { spin_lock_irq(&info->lock); shmem_recalc_inode(inode); info->swapped++; spin_unlock_irq(&info->lock); swap_shmem_alloc(swap); shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); mutex_unlock(&shmem_swaplist_mutex); BUG_ON(page_mapped(page)); swap_writepage(page, wbc); return 0; } mutex_unlock(&shmem_swaplist_mutex); put_swap_page(page, swap); redirty: set_page_dirty(page); if (wbc->for_reclaim) return AOP_WRITEPAGE_ACTIVATE; /* Return with page locked */ unlock_page(page); return 0; } #if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS) static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { char buffer[64]; if (!mpol || mpol->mode == MPOL_DEFAULT) return; /* show nothing */ mpol_to_str(buffer, sizeof(buffer), mpol); seq_printf(seq, ",mpol=%s", buffer); } static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { struct mempolicy *mpol = NULL; if (sbinfo->mpol) { spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */ mpol = sbinfo->mpol; mpol_get(mpol); spin_unlock(&sbinfo->stat_lock); } return mpol; } #else /* !CONFIG_NUMA || !CONFIG_TMPFS */ static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { } static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { return NULL; } #endif /* CONFIG_NUMA && CONFIG_TMPFS */ #ifndef CONFIG_NUMA #define vm_policy vm_private_data #endif static void shmem_pseudo_vma_init(struct vm_area_struct *vma, struct shmem_inode_info *info, pgoff_t index) { /* Create a pseudo vma that just contains the policy */ vma_init(vma, NULL); /* Bias interleave by inode number to distribute better across nodes */ vma->vm_pgoff = index + info->vfs_inode.i_ino; vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); } static void shmem_pseudo_vma_destroy(struct vm_area_struct *vma) { /* Drop reference taken by mpol_shared_policy_lookup() */ mpol_cond_put(vma->vm_policy); } static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct page *page; struct vm_fault vmf; shmem_pseudo_vma_init(&pvma, info, index); vmf.vma = &pvma; vmf.address = 0; page = swap_cluster_readahead(swap, gfp, &vmf); shmem_pseudo_vma_destroy(&pvma); return page; } static struct page *shmem_alloc_hugepage(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct address_space *mapping = info->vfs_inode.i_mapping; pgoff_t hindex; struct page *page; hindex = round_down(index, HPAGE_PMD_NR); if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1, XA_PRESENT)) return NULL; shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); else count_vm_event(THP_FILE_FALLBACK); return page; } static struct page *shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; struct page *page; shmem_pseudo_vma_init(&pvma, info, index); page = alloc_page_vma(gfp, &pvma, 0); shmem_pseudo_vma_destroy(&pvma); return page; } static struct page *shmem_alloc_and_acct_page(gfp_t gfp, struct inode *inode, pgoff_t index, bool huge) { struct shmem_inode_info *info = SHMEM_I(inode); struct page *page; int nr; int err = -ENOSPC; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) huge = false; nr = huge ? HPAGE_PMD_NR : 1; if (!shmem_inode_acct_block(inode, nr)) goto failed; if (huge) page = shmem_alloc_hugepage(gfp, info, index); else page = shmem_alloc_page(gfp, info, index); if (page) { __SetPageLocked(page); __SetPageSwapBacked(page); return page; } err = -ENOMEM; shmem_inode_unacct_blocks(inode, nr); failed: return ERR_PTR(err); } /* * When a page is moved from swapcache to shmem filecache (either by the * usual swapin of shmem_getpage_gfp(), or by the less common swapoff of * shmem_unuse_inode()), it may have been read in earlier from swap, in * ignorance of the mapping it belongs to. If that mapping has special * constraints (like the gma500 GEM driver, which requires RAM below 4GB), * we may need to copy to a suitable page before moving to filecache. * * In a future release, this may well be extended to respect cpuset and * NUMA mempolicy, and applied also to anonymous pages in do_swap_page(); * but for now it is a simple matter of zone. */ static bool shmem_should_replace_page(struct page *page, gfp_t gfp) { return page_zonenum(page) > gfp_zone(gfp); } static int shmem_replace_page(struct page **pagep, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct page *oldpage, *newpage; struct address_space *swap_mapping; swp_entry_t entry; pgoff_t swap_index; int error; oldpage = *pagep; entry.val = page_private(oldpage); swap_index = swp_offset(entry); swap_mapping = page_mapping(oldpage); /* * We have arrived here because our zones are constrained, so don't * limit chance of success by further cpuset and node constraints. */ gfp &= ~GFP_CONSTRAINT_MASK; newpage = shmem_alloc_page(gfp, info, index); if (!newpage) return -ENOMEM; get_page(newpage); copy_highpage(newpage, oldpage); flush_dcache_page(newpage); __SetPageLocked(newpage); __SetPageSwapBacked(newpage); SetPageUptodate(newpage); set_page_private(newpage, entry.val); SetPageSwapCache(newpage); /* * Our caller will very soon move newpage out of swapcache, but it's * a nice clean interface for us to replace oldpage by newpage there. */ xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage); if (!error) { mem_cgroup_migrate(oldpage, newpage); __inc_lruvec_page_state(newpage, NR_FILE_PAGES); __dec_lruvec_page_state(oldpage, NR_FILE_PAGES); } xa_unlock_irq(&swap_mapping->i_pages); if (unlikely(error)) { /* * Is this possible? I think not, now that our callers check * both PageSwapCache and page_private after getting page lock; * but be defensive. Reverse old to newpage for clear and free. */ oldpage = newpage; } else { lru_cache_add(newpage); *pagep = newpage; } ClearPageSwapCache(oldpage); set_page_private(oldpage, 0); unlock_page(oldpage); put_page(oldpage); put_page(oldpage); return error; } /* * Swap in the page pointed to by *pagep. * Caller has to make sure that *pagep contains a valid swapped page. * Returns 0 and the page in pagep if success. On failure, returns the * error code and NULL in *pagep. */ static int shmem_swapin_page(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, vm_fault_t *fault_type) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm; struct page *page; swp_entry_t swap; int error; VM_BUG_ON(!*pagep || !xa_is_value(*pagep)); swap = radix_to_swp_entry(*pagep); *pagep = NULL; /* Look it up and read it in.. */ page = lookup_swap_cache(swap, NULL, 0); if (!page) { /* Or update major stats only when swapin succeeds?? */ if (fault_type) { *fault_type |= VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(charge_mm, PGMAJFAULT); } /* Here we actually start the io */ page = shmem_swapin(swap, gfp, info, index); if (!page) { error = -ENOMEM; goto failed; } } /* We have to do this with page locked to prevent races */ lock_page(page); if (!PageSwapCache(page) || page_private(page) != swap.val || !shmem_confirm_swap(mapping, index, swap)) { error = -EEXIST; goto unlock; } if (!PageUptodate(page)) { error = -EIO; goto failed; } wait_on_page_writeback(page); /* * Some architectures may have to restore extra metadata to the * physical page after reading from swap. */ arch_swap_restore(swap, page); if (shmem_should_replace_page(page, gfp)) { error = shmem_replace_page(&page, gfp, info, index); if (error) goto failed; } error = shmem_add_to_page_cache(page, mapping, index, swp_to_radix_entry(swap), gfp, charge_mm); if (error) goto failed; spin_lock_irq(&info->lock); info->swapped--; shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); if (sgp == SGP_WRITE) mark_page_accessed(page); delete_from_swap_cache(page); set_page_dirty(page); swap_free(swap); *pagep = page; return 0; failed: if (!shmem_confirm_swap(mapping, index, swap)) error = -EEXIST; unlock: if (page) { unlock_page(page); put_page(page); } return error; } /* * shmem_getpage_gfp - find page in cache, or get from swap, or allocate * * If we allocate a new one we do not mark it dirty. That's up to the * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache. * * vmf and fault_type are only supplied by shmem_fault: * otherwise they are NULL. */ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, struct vm_fault *vmf, vm_fault_t *fault_type) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo; struct mm_struct *charge_mm; struct page *page; enum sgp_type sgp_huge = sgp; pgoff_t hindex = index; int error; int once = 0; int alloced = 0; if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) return -EFBIG; if (sgp == SGP_NOHUGE || sgp == SGP_HUGE) sgp = SGP_CACHE; repeat: if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { return -EINVAL; } sbinfo = SHMEM_SB(inode->i_sb); charge_mm = vma ? vma->vm_mm : current->mm; page = find_lock_entry(mapping, index); if (xa_is_value(page)) { error = shmem_swapin_page(inode, index, &page, sgp, gfp, vma, fault_type); if (error == -EEXIST) goto repeat; *pagep = page; return error; } if (page) hindex = page->index; if (page && sgp == SGP_WRITE) mark_page_accessed(page); /* fallocated page? */ if (page && !PageUptodate(page)) { if (sgp != SGP_READ) goto clear; unlock_page(page); put_page(page); page = NULL; hindex = index; } if (page || sgp == SGP_READ) goto out; /* * Fast cache lookup did not find it: * bring it back from swap or allocate. */ if (vma && userfaultfd_missing(vma)) { *fault_type = handle_userfault(vmf, VM_UFFD_MISSING); return 0; } /* shmem_symlink() */ if (mapping->a_ops != &shmem_aops) goto alloc_nohuge; if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE) goto alloc_nohuge; if (shmem_huge == SHMEM_HUGE_FORCE) goto alloc_huge; switch (sbinfo->huge) { case SHMEM_HUGE_NEVER: goto alloc_nohuge; case SHMEM_HUGE_WITHIN_SIZE: { loff_t i_size; pgoff_t off; off = round_up(index, HPAGE_PMD_NR); i_size = round_up(i_size_read(inode), PAGE_SIZE); if (i_size >= HPAGE_PMD_SIZE && i_size >> PAGE_SHIFT >= off) goto alloc_huge; fallthrough; } case SHMEM_HUGE_ADVISE: if (sgp_huge == SGP_HUGE) goto alloc_huge; /* TODO: implement fadvise() hints */ goto alloc_nohuge; } alloc_huge: page = shmem_alloc_and_acct_page(gfp, inode, index, true); if (IS_ERR(page)) { alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, inode, index, false); } if (IS_ERR(page)) { int retry = 5; error = PTR_ERR(page); page = NULL; if (error != -ENOSPC) goto unlock; /* * Try to reclaim some space by splitting a huge page * beyond i_size on the filesystem. */ while (retry--) { int ret; ret = shmem_unused_huge_shrink(sbinfo, NULL, 1); if (ret == SHRINK_STOP) break; if (ret) goto alloc_nohuge; } goto unlock; } if (PageTransHuge(page)) hindex = round_down(index, HPAGE_PMD_NR); else hindex = index; if (sgp == SGP_WRITE) __SetPageReferenced(page); error = shmem_add_to_page_cache(page, mapping, hindex, NULL, gfp & GFP_RECLAIM_MASK, charge_mm); if (error) goto unacct; lru_cache_add(page); spin_lock_irq(&info->lock); info->alloced += compound_nr(page); inode->i_blocks += BLOCKS_PER_PAGE << compound_order(page); shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); alloced = true; if (PageTransHuge(page) && DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE) < hindex + HPAGE_PMD_NR - 1) { /* * Part of the huge page is beyond i_size: subject * to shrink under memory pressure. */ spin_lock(&sbinfo->shrinklist_lock); /* * _careful to defend against unlocked access to * ->shrink_list in shmem_unused_huge_shrink() */ if (list_empty_careful(&info->shrinklist)) { list_add_tail(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; } spin_unlock(&sbinfo->shrinklist_lock); } /* * Let SGP_FALLOC use the SGP_WRITE optimization on a new page. */ if (sgp == SGP_FALLOC) sgp = SGP_WRITE; clear: /* * Let SGP_WRITE caller clear ends if write does not fill page; * but SGP_FALLOC on a page fallocated earlier must initialize * it now, lest undo on failure cancel our earlier guarantee. */ if (sgp != SGP_WRITE && !PageUptodate(page)) { int i; for (i = 0; i < compound_nr(page); i++) { clear_highpage(page + i); flush_dcache_page(page + i); } SetPageUptodate(page); } /* Perhaps the file has been truncated since we checked */ if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { if (alloced) { ClearPageDirty(page); delete_from_page_cache(page); spin_lock_irq(&info->lock); shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); } error = -EINVAL; goto unlock; } out: *pagep = page + index - hindex; return 0; /* * Error recovery. */ unacct: shmem_inode_unacct_blocks(inode, compound_nr(page)); if (PageTransHuge(page)) { unlock_page(page); put_page(page); goto alloc_nohuge; } unlock: if (page) { unlock_page(page); put_page(page); } if (error == -ENOSPC && !once++) { spin_lock_irq(&info->lock); shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); goto repeat; } if (error == -EEXIST) goto repeat; return error; } /* * This is like autoremove_wake_function, but it removes the wait queue * entry unconditionally - even if something else had already woken the * target. */ static int synchronous_wake_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { int ret = default_wake_function(wait, mode, sync, key); list_del_init(&wait->entry); return ret; } static vm_fault_t shmem_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct inode *inode = file_inode(vma->vm_file); gfp_t gfp = mapping_gfp_mask(inode->i_mapping); enum sgp_type sgp; int err; vm_fault_t ret = VM_FAULT_LOCKED; /* * Trinity finds that probing a hole which tmpfs is punching can * prevent the hole-punch from ever completing: which in turn * locks writers out with its hold on i_mutex. So refrain from * faulting pages into the hole while it's being punched. Although * shmem_undo_range() does remove the additions, it may be unable to * keep up, as each new page needs its own unmap_mapping_range() call, * and the i_mmap tree grows ever slower to scan if new vmas are added. * * It does not matter if we sometimes reach this check just before the * hole-punch begins, so that one fault then races with the punch: * we just need to make racing faults a rare case. * * The implementation below would be much simpler if we just used a * standard mutex or completion: but we cannot take i_mutex in fault, * and bloating every shmem inode for this unlikely case would be sad. */ if (unlikely(inode->i_private)) { struct shmem_falloc *shmem_falloc; spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && shmem_falloc->waitq && vmf->pgoff >= shmem_falloc->start && vmf->pgoff < shmem_falloc->next) { struct file *fpin; wait_queue_head_t *shmem_falloc_waitq; DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function); ret = VM_FAULT_NOPAGE; fpin = maybe_unlock_mmap_for_io(vmf, NULL); if (fpin) ret = VM_FAULT_RETRY; shmem_falloc_waitq = shmem_falloc->waitq; prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); schedule(); /* * shmem_falloc_waitq points into the shmem_fallocate() * stack of the hole-punching task: shmem_falloc_waitq * is usually invalid by the time we reach here, but * finish_wait() does not dereference it in that case; * though i_lock needed lest racing with wake_up_all(). */ spin_lock(&inode->i_lock); finish_wait(shmem_falloc_waitq, &shmem_fault_wait); spin_unlock(&inode->i_lock); if (fpin) fput(fpin); return ret; } spin_unlock(&inode->i_lock); } sgp = SGP_CACHE; if ((vma->vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) sgp = SGP_NOHUGE; else if (vma->vm_flags & VM_HUGEPAGE) sgp = SGP_HUGE; err = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp, gfp, vma, vmf, &ret); if (err) return vmf_error(err); return ret; } unsigned long shmem_get_unmapped_area(struct file *file, unsigned long uaddr, unsigned long len, unsigned long pgoff, unsigned long flags) { unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); unsigned long addr; unsigned long offset; unsigned long inflated_len; unsigned long inflated_addr; unsigned long inflated_offset; if (len > TASK_SIZE) return -ENOMEM; get_area = current->mm->get_unmapped_area; addr = get_area(file, uaddr, len, pgoff, flags); if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return addr; if (IS_ERR_VALUE(addr)) return addr; if (addr & ~PAGE_MASK) return addr; if (addr > TASK_SIZE - len) return addr; if (shmem_huge == SHMEM_HUGE_DENY) return addr; if (len < HPAGE_PMD_SIZE) return addr; if (flags & MAP_FIXED) return addr; /* * Our priority is to support MAP_SHARED mapped hugely; * and support MAP_PRIVATE mapped hugely too, until it is COWed. * But if caller specified an address hint and we allocated area there * successfully, respect that as before. */ if (uaddr == addr) return addr; if (shmem_huge != SHMEM_HUGE_FORCE) { struct super_block *sb; if (file) { VM_BUG_ON(file->f_op != &shmem_file_operations); sb = file_inode(file)->i_sb; } else { /* * Called directly from mm/mmap.c, or drivers/char/mem.c * for "/dev/zero", to create a shared anonymous object. */ if (IS_ERR(shm_mnt)) return addr; sb = shm_mnt->mnt_sb; } if (SHMEM_SB(sb)->huge == SHMEM_HUGE_NEVER) return addr; } offset = (pgoff << PAGE_SHIFT) & (HPAGE_PMD_SIZE-1); if (offset && offset + len < 2 * HPAGE_PMD_SIZE) return addr; if ((addr & (HPAGE_PMD_SIZE-1)) == offset) return addr; inflated_len = len + HPAGE_PMD_SIZE - PAGE_SIZE; if (inflated_len > TASK_SIZE) return addr; if (inflated_len < len) return addr; inflated_addr = get_area(NULL, uaddr, inflated_len, 0, flags); if (IS_ERR_VALUE(inflated_addr)) return addr; if (inflated_addr & ~PAGE_MASK) return addr; inflated_offset = inflated_addr & (HPAGE_PMD_SIZE-1); inflated_addr += offset - inflated_offset; if (inflated_offset > offset) inflated_addr += HPAGE_PMD_SIZE; if (inflated_addr > TASK_SIZE - len) return addr; return inflated_addr; } #ifdef CONFIG_NUMA static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) { struct inode *inode = file_inode(vma->vm_file); return mpol_set_shared_policy(&SHMEM_I(inode)->policy, vma, mpol); } static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, unsigned long addr) { struct inode *inode = file_inode(vma->vm_file); pgoff_t index; index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; return mpol_shared_policy_lookup(&SHMEM_I(inode)->policy, index); } #endif int shmem_lock(struct file *file, int lock, struct user_struct *user) { struct inode *inode = file_inode(file); struct shmem_inode_info *info = SHMEM_I(inode); int retval = -ENOMEM; /* * What serializes the accesses to info->flags? * ipc_lock_object() when called from shmctl_do_lock(), * no serialization needed when called from shm_destroy(). */ if (lock && !(info->flags & VM_LOCKED)) { if (!user_shm_lock(inode->i_size, user)) goto out_nomem; info->flags |= VM_LOCKED; mapping_set_unevictable(file->f_mapping); } if (!lock && (info->flags & VM_LOCKED) && user) { user_shm_unlock(inode->i_size, user); info->flags &= ~VM_LOCKED; mapping_clear_unevictable(file->f_mapping); } retval = 0; out_nomem: return retval; } static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { struct shmem_inode_info *info = SHMEM_I(file_inode(file)); int ret; ret = seal_check_write(info->seals, vma); if (ret) return ret; file_accessed(file); vma->vm_ops = &shmem_vm_ops; if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < (vma->vm_end & HPAGE_PMD_MASK)) { khugepaged_enter(vma, vma->vm_flags); } return 0; } static struct inode *shmem_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode, dev_t dev, unsigned long flags) { struct inode *inode; struct shmem_inode_info *info; struct shmem_sb_info *sbinfo = SHMEM_SB(sb); ino_t ino; if (shmem_reserve_inode(sb, &ino)) return NULL; inode = new_inode(sb); if (inode) { inode->i_ino = ino; inode_init_owner(inode, dir, mode); inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inode->i_generation = prandom_u32(); info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); atomic_set(&info->stop_eviction, 0); info->seals = F_SEAL_SEAL; info->flags = flags & VM_NORESERVE; INIT_LIST_HEAD(&info->shrinklist); INIT_LIST_HEAD(&info->swaplist); simple_xattrs_init(&info->xattrs); cache_no_acl(inode); switch (mode & S_IFMT) { default: inode->i_op = &shmem_special_inode_operations; init_special_inode(inode, mode, dev); break; case S_IFREG: inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_inode_operations; inode->i_fop = &shmem_file_operations; mpol_shared_policy_init(&info->policy, shmem_get_sbmpol(sbinfo)); break; case S_IFDIR: inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ inode->i_size = 2 * BOGO_DIRENT_SIZE; inode->i_op = &shmem_dir_inode_operations; inode->i_fop = &simple_dir_operations; break; case S_IFLNK: /* * Must not load anything in the rbtree, * mpol_free_shared_policy will not be called. */ mpol_shared_policy_init(&info->policy, NULL); break; } lockdep_annotate_inode_mutex_key(inode); } else shmem_free_inode(sb); return inode; } bool shmem_mapping(struct address_space *mapping) { return mapping->a_ops == &shmem_aops; } static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, bool zeropage, struct page **pagep) { struct inode *inode = file_inode(dst_vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); struct address_space *mapping = inode->i_mapping; gfp_t gfp = mapping_gfp_mask(mapping); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); spinlock_t *ptl; void *page_kaddr; struct page *page; pte_t _dst_pte, *dst_pte; int ret; pgoff_t offset, max_off; ret = -ENOMEM; if (!shmem_inode_acct_block(inode, 1)) { /* * We may have got a page, returned -ENOENT triggering a retry, * and now we find ourselves with -ENOMEM. Release the page, to * avoid a BUG_ON in our caller. */ if (unlikely(*pagep)) { put_page(*pagep); *pagep = NULL; } goto out; } if (!*pagep) { page = shmem_alloc_page(gfp, info, pgoff); if (!page) goto out_unacct_blocks; if (!zeropage) { /* mcopy_atomic */ page_kaddr = kmap_atomic(page); ret = copy_from_user(page_kaddr, (const void __user *)src_addr, PAGE_SIZE); kunmap_atomic(page_kaddr); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { *pagep = page; shmem_inode_unacct_blocks(inode, 1); /* don't free the page */ return -ENOENT; } } else { /* mfill_zeropage_atomic */ clear_highpage(page); } } else { page = *pagep; *pagep = NULL; } VM_BUG_ON(PageLocked(page) || PageSwapBacked(page)); __SetPageLocked(page); __SetPageSwapBacked(page); __SetPageUptodate(page); ret = -EFAULT; offset = linear_page_index(dst_vma, dst_addr); max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) goto out_release; ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL, gfp & GFP_RECLAIM_MASK, dst_mm); if (ret) goto out_release; _dst_pte = mk_pte(page, dst_vma->vm_page_prot); if (dst_vma->vm_flags & VM_WRITE) _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte)); else { /* * We don't set the pte dirty if the vma has no * VM_WRITE permission, so mark the page dirty or it * could be freed from under us. We could do it * unconditionally before unlock_page(), but doing it * only if VM_WRITE is not set is faster. */ set_page_dirty(page); } dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); ret = -EFAULT; max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(offset >= max_off)) goto out_release_unlock; ret = -EEXIST; if (!pte_none(*dst_pte)) goto out_release_unlock; lru_cache_add(page); spin_lock_irq(&info->lock); info->alloced++; inode->i_blocks += BLOCKS_PER_PAGE; shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); inc_mm_counter(dst_mm, mm_counter_file(page)); page_add_file_rmap(page, false); set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); pte_unmap_unlock(dst_pte, ptl); unlock_page(page); ret = 0; out: return ret; out_release_unlock: pte_unmap_unlock(dst_pte, ptl); ClearPageDirty(page); delete_from_page_cache(page); out_release: unlock_page(page); put_page(page); out_unacct_blocks: shmem_inode_unacct_blocks(inode, 1); goto out; } int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, struct page **pagep) { return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, false, pagep); } int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr) { struct page *page = NULL; return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, 0, true, &page); } #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; #ifdef CONFIG_TMPFS_XATTR static int shmem_initxattrs(struct inode *, const struct xattr *, void *); #else #define shmem_initxattrs NULL #endif static int shmem_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t index = pos >> PAGE_SHIFT; /* i_mutex is held by caller */ if (unlikely(info->seals & (F_SEAL_GROW | F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))) { if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) return -EPERM; if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size) return -EPERM; } return shmem_getpage(inode, index, pagep, SGP_WRITE); } static int shmem_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = mapping->host; if (pos + copied > inode->i_size) i_size_write(inode, pos + copied); if (!PageUptodate(page)) { struct page *head = compound_head(page); if (PageTransCompound(page)) { int i; for (i = 0; i < HPAGE_PMD_NR; i++) { if (head + i == page) continue; clear_highpage(head + i); flush_dcache_page(head + i); } } if (copied < PAGE_SIZE) { unsigned from = pos & (PAGE_SIZE - 1); zero_user_segments(page, 0, from, from + copied, PAGE_SIZE); } SetPageUptodate(head); } set_page_dirty(page); unlock_page(page); put_page(page); return copied; } static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; pgoff_t index; unsigned long offset; enum sgp_type sgp = SGP_READ; int error = 0; ssize_t retval = 0; loff_t *ppos = &iocb->ki_pos; /* * Might this read be for a stacking filesystem? Then when reading * holes of a sparse file, we actually need to allocate those pages, * and even mark them dirty, so it cannot exceed the max_blocks limit. */ if (!iter_is_iovec(to)) sgp = SGP_CACHE; index = *ppos >> PAGE_SHIFT; offset = *ppos & ~PAGE_MASK; for (;;) { struct page *page = NULL; pgoff_t end_index; unsigned long nr, ret; loff_t i_size = i_size_read(inode); end_index = i_size >> PAGE_SHIFT; if (index > end_index) break; if (index == end_index) { nr = i_size & ~PAGE_MASK; if (nr <= offset) break; } error = shmem_getpage(inode, index, &page, sgp); if (error) { if (error == -EINVAL) error = 0; break; } if (page) { if (sgp == SGP_CACHE) set_page_dirty(page); unlock_page(page); } /* * We must evaluate after, since reads (unlike writes) * are called without i_mutex protection against truncate */ nr = PAGE_SIZE; i_size = i_size_read(inode); end_index = i_size >> PAGE_SHIFT; if (index == end_index) { nr = i_size & ~PAGE_MASK; if (nr <= offset) { if (page) put_page(page); break; } } nr -= offset; if (page) { /* * If users can be writing to this page using arbitrary * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ if (mapping_writably_mapped(mapping)) flush_dcache_page(page); /* * Mark the page accessed if we read the beginning. */ if (!offset) mark_page_accessed(page); } else { page = ZERO_PAGE(0); get_page(page); } /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... */ ret = copy_page_to_iter(page, offset, nr, to); retval += ret; offset += ret; index += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; put_page(page); if (!iov_iter_count(to)) break; if (ret < nr) { error = -EFAULT; break; } cond_resched(); } *ppos = ((loff_t) index << PAGE_SHIFT) + offset; file_accessed(file); return retval ? retval : error; } /* * llseek SEEK_DATA or SEEK_HOLE through the page cache. */ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, pgoff_t index, pgoff_t end, int whence) { struct page *page; struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; bool done = false; int i; pagevec_init(&pvec); pvec.nr = 1; /* start small: we may be there already */ while (!done) { pvec.nr = find_get_entries(mapping, index, pvec.nr, pvec.pages, indices); if (!pvec.nr) { if (whence == SEEK_DATA) index = end; break; } for (i = 0; i < pvec.nr; i++, index++) { if (index < indices[i]) { if (whence == SEEK_HOLE) { done = true; break; } index = indices[i]; } page = pvec.pages[i]; if (page && !xa_is_value(page)) { if (!PageUptodate(page)) page = NULL; } if (index >= end || (page && whence == SEEK_DATA) || (!page && whence == SEEK_HOLE)) { done = true; break; } } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); pvec.nr = PAGEVEC_SIZE; cond_resched(); } return index; } static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) { struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; pgoff_t start, end; loff_t new_offset; if (whence != SEEK_DATA && whence != SEEK_HOLE) return generic_file_llseek_size(file, offset, whence, MAX_LFS_FILESIZE, i_size_read(inode)); inode_lock(inode); /* We're holding i_mutex so we can access i_size directly */ if (offset < 0 || offset >= inode->i_size) offset = -ENXIO; else { start = offset >> PAGE_SHIFT; end = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; new_offset = shmem_seek_hole_data(mapping, start, end, whence); new_offset <<= PAGE_SHIFT; if (new_offset > offset) { if (new_offset < inode->i_size) offset = new_offset; else if (whence == SEEK_DATA) offset = -ENXIO; else offset = inode->i_size; } } if (offset >= 0) offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE); inode_unlock(inode); return offset; } static long shmem_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_falloc shmem_falloc; pgoff_t start, index, end; int error; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; inode_lock(inode); if (mode & FALLOC_FL_PUNCH_HOLE) { struct address_space *mapping = file->f_mapping; loff_t unmap_start = round_up(offset, PAGE_SIZE); loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq); /* protected by i_mutex */ if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { error = -EPERM; goto out; } shmem_falloc.waitq = &shmem_falloc_waitq; shmem_falloc.start = (u64)unmap_start >> PAGE_SHIFT; shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; spin_lock(&inode->i_lock); inode->i_private = &shmem_falloc; spin_unlock(&inode->i_lock); if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); shmem_truncate_range(inode, offset, offset + len - 1); /* No need to unmap again: hole-punching leaves COWed pages */ spin_lock(&inode->i_lock); inode->i_private = NULL; wake_up_all(&shmem_falloc_waitq); WARN_ON_ONCE(!list_empty(&shmem_falloc_waitq.head)); spin_unlock(&inode->i_lock); error = 0; goto out; } /* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */ error = inode_newsize_ok(inode, offset + len); if (error) goto out; if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) { error = -EPERM; goto out; } start = offset >> PAGE_SHIFT; end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Try to avoid a swapstorm if len is impossible to satisfy */ if (sbinfo->max_blocks && end - start > sbinfo->max_blocks) { error = -ENOSPC; goto out; } shmem_falloc.waitq = NULL; shmem_falloc.start = start; shmem_falloc.next = start; shmem_falloc.nr_falloced = 0; shmem_falloc.nr_unswapped = 0; spin_lock(&inode->i_lock); inode->i_private = &shmem_falloc; spin_unlock(&inode->i_lock); for (index = start; index < end; index++) { struct page *page; /* * Good, the fallocate(2) manpage permits EINTR: we may have * been interrupted because we are using up too much memory. */ if (signal_pending(current)) error = -EINTR; else if (shmem_falloc.nr_unswapped > shmem_falloc.nr_falloced) error = -ENOMEM; else error = shmem_getpage(inode, index, &page, SGP_FALLOC); if (error) { /* Remove the !PageUptodate pages we added */ if (index > start) { shmem_undo_range(inode, (loff_t)start << PAGE_SHIFT, ((loff_t)index << PAGE_SHIFT) - 1, true); } goto undone; } /* * Inform shmem_writepage() how far we have reached. * No need for lock or barrier: we have the page lock. */ shmem_falloc.next++; if (!PageUptodate(page)) shmem_falloc.nr_falloced++; /* * If !PageUptodate, leave it that way so that freeable pages * can be recognized if we need to rollback on error later. * But set_page_dirty so that memory pressure will swap rather * than free the pages we are allocating (and SGP_CACHE pages * might still be clean: we now need to mark those dirty too). */ set_page_dirty(page); unlock_page(page); put_page(page); cond_resched(); } if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); inode->i_ctime = current_time(inode); undone: spin_lock(&inode->i_lock); inode->i_private = NULL; spin_unlock(&inode->i_lock); out: inode_unlock(inode); return error; } static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) { struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb); buf->f_type = TMPFS_MAGIC; buf->f_bsize = PAGE_SIZE; buf->f_namelen = NAME_MAX; if (sbinfo->max_blocks) { buf->f_blocks = sbinfo->max_blocks; buf->f_bavail = buf->f_bfree = sbinfo->max_blocks - percpu_counter_sum(&sbinfo->used_blocks); } if (sbinfo->max_inodes) { buf->f_files = sbinfo->max_inodes; buf->f_ffree = sbinfo->free_inodes; } /* else leave those fields 0 like simple_statfs */ return 0; } /* * File creation. Allocate an inode, and we're done.. */ static int shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { struct inode *inode; int error = -ENOSPC; inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { error = simple_acl_create(dir, inode); if (error) goto out_iput; error = security_inode_init_security(inode, dir, &dentry->d_name, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) goto out_iput; error = 0; dir->i_size += BOGO_DIRENT_SIZE; dir->i_ctime = dir->i_mtime = current_time(dir); d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ } return error; out_iput: iput(inode); return error; } static int shmem_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; int error = -ENOSPC; inode = shmem_get_inode(dir->i_sb, dir, mode, 0, VM_NORESERVE); if (inode) { error = security_inode_init_security(inode, dir, NULL, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) goto out_iput; error = simple_acl_create(dir, inode); if (error) goto out_iput; d_tmpfile(dentry, inode); } return error; out_iput: iput(inode); return error; } static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { int error; if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0))) return error; inc_nlink(dir); return 0; } static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return shmem_mknod(dir, dentry, mode | S_IFREG, 0); } /* * Link a file.. */ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); int ret = 0; /* * No ordinary (disk based) filesystem counts links as inodes; * but each new link needs a new dentry, pinning lowmem, and * tmpfs dentries cannot be pruned until they are unlinked. * But if an O_TMPFILE file is linked into the tmpfs, the * first link must skip that, to get the accounting right. */ if (inode->i_nlink) { ret = shmem_reserve_inode(inode->i_sb, NULL); if (ret) goto out; } dir->i_size += BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode); inc_nlink(inode); ihold(inode); /* New dentry reference */ dget(dentry); /* Extra pinning count for the created dentry */ d_instantiate(dentry, inode); out: return ret; } static int shmem_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) shmem_free_inode(inode->i_sb); dir->i_size -= BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode); drop_nlink(inode); dput(dentry); /* Undo the count from "create" - this does all the work */ return 0; } static int shmem_rmdir(struct inode *dir, struct dentry *dentry) { if (!simple_empty(dentry)) return -ENOTEMPTY; drop_nlink(d_inode(dentry)); drop_nlink(dir); return shmem_unlink(dir, dentry); } static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { bool old_is_dir = d_is_dir(old_dentry); bool new_is_dir = d_is_dir(new_dentry); if (old_dir != new_dir && old_is_dir != new_is_dir) { if (old_is_dir) { drop_nlink(old_dir); inc_nlink(new_dir); } else { drop_nlink(new_dir); inc_nlink(old_dir); } } old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime = new_dir->i_mtime = d_inode(old_dentry)->i_ctime = d_inode(new_dentry)->i_ctime = current_time(old_dir); return 0; } static int shmem_whiteout(struct inode *old_dir, struct dentry *old_dentry) { struct dentry *whiteout; int error; whiteout = d_alloc(old_dentry->d_parent, &old_dentry->d_name); if (!whiteout) return -ENOMEM; error = shmem_mknod(old_dir, whiteout, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); dput(whiteout); if (error) return error; /* * Cheat and hash the whiteout while the old dentry is still in * place, instead of playing games with FS_RENAME_DOES_D_MOVE. * * d_lookup() will consistently find one of them at this point, * not sure which one, but that isn't even important. */ d_rehash(whiteout); return 0; } /* * The VFS layer already does all the dentry stuff for rename, * we just have to decrement the usage count for the target if * it exists so that the VFS layer correctly free's it when it * gets overwritten. */ static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *inode = d_inode(old_dentry); int they_are_dirs = S_ISDIR(inode->i_mode); if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; if (flags & RENAME_EXCHANGE) return shmem_exchange(old_dir, old_dentry, new_dir, new_dentry); if (!simple_empty(new_dentry)) return -ENOTEMPTY; if (flags & RENAME_WHITEOUT) { int error; error = shmem_whiteout(old_dir, old_dentry); if (error) return error; } if (d_really_is_positive(new_dentry)) { (void) shmem_unlink(new_dir, new_dentry); if (they_are_dirs) { drop_nlink(d_inode(new_dentry)); drop_nlink(old_dir); } } else if (they_are_dirs) { drop_nlink(old_dir); inc_nlink(new_dir); } old_dir->i_size -= BOGO_DIRENT_SIZE; new_dir->i_size += BOGO_DIRENT_SIZE; old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime = new_dir->i_mtime = inode->i_ctime = current_time(old_dir); return 0; } static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *symname) { int error; int len; struct inode *inode; struct page *page; len = strlen(symname) + 1; if (len > PAGE_SIZE) return -ENAMETOOLONG; inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK | 0777, 0, VM_NORESERVE); if (!inode) return -ENOSPC; error = security_inode_init_security(inode, dir, &dentry->d_name, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) { iput(inode); return error; } inode->i_size = len-1; if (len <= SHORT_SYMLINK_LEN) { inode->i_link = kmemdup(symname, len, GFP_KERNEL); if (!inode->i_link) { iput(inode); return -ENOMEM; } inode->i_op = &shmem_short_symlink_operations; } else { inode_nohighmem(inode); error = shmem_getpage(inode, 0, &page, SGP_WRITE); if (error) { iput(inode); return error; } inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_symlink_inode_operations; memcpy(page_address(page), symname, len); SetPageUptodate(page); set_page_dirty(page); unlock_page(page); put_page(page); } dir->i_size += BOGO_DIRENT_SIZE; dir->i_ctime = dir->i_mtime = current_time(dir); d_instantiate(dentry, inode); dget(dentry); return 0; } static void shmem_put_link(void *arg) { mark_page_accessed(arg); put_page(arg); } static const char *shmem_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct page *page = NULL; int error; if (!dentry) { page = find_get_page(inode->i_mapping, 0); if (!page) return ERR_PTR(-ECHILD); if (!PageUptodate(page)) { put_page(page); return ERR_PTR(-ECHILD); } } else { error = shmem_getpage(inode, 0, &page, SGP_READ); if (error) return ERR_PTR(error); unlock_page(page); } set_delayed_call(done, shmem_put_link, page); return page_address(page); } #ifdef CONFIG_TMPFS_XATTR /* * Superblocks without xattr inode operations may get some security.* xattr * support from the LSM "for free". As soon as we have any other xattrs * like ACLs, we also need to implement the security.* handlers at * filesystem level, though. */ /* * Callback for security_inode_init_security() for acquiring xattrs. */ static int shmem_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { struct shmem_inode_info *info = SHMEM_I(inode); const struct xattr *xattr; struct simple_xattr *new_xattr; size_t len; for (xattr = xattr_array; xattr->name != NULL; xattr++) { new_xattr = simple_xattr_alloc(xattr->value, xattr->value_len); if (!new_xattr) return -ENOMEM; len = strlen(xattr->name) + 1; new_xattr->name = kmalloc(XATTR_SECURITY_PREFIX_LEN + len, GFP_KERNEL); if (!new_xattr->name) { kvfree(new_xattr); return -ENOMEM; } memcpy(new_xattr->name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); memcpy(new_xattr->name + XATTR_SECURITY_PREFIX_LEN, xattr->name, len); simple_xattr_list_add(&info->xattrs, new_xattr); } return 0; } static int shmem_xattr_handler_get(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *buffer, size_t size) { struct shmem_inode_info *info = SHMEM_I(inode); name = xattr_full_name(handler, name); return simple_xattr_get(&info->xattrs, name, buffer, size); } static int shmem_xattr_handler_set(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct shmem_inode_info *info = SHMEM_I(inode); name = xattr_full_name(handler, name); return simple_xattr_set(&info->xattrs, name, value, size, flags, NULL); } static const struct xattr_handler shmem_security_xattr_handler = { .prefix = XATTR_SECURITY_PREFIX, .get = shmem_xattr_handler_get, .set = shmem_xattr_handler_set, }; static const struct xattr_handler shmem_trusted_xattr_handler = { .prefix = XATTR_TRUSTED_PREFIX, .get = shmem_xattr_handler_get, .set = shmem_xattr_handler_set, }; static const struct xattr_handler *shmem_xattr_handlers[] = { #ifdef CONFIG_TMPFS_POSIX_ACL &posix_acl_access_xattr_handler, &posix_acl_default_xattr_handler, #endif &shmem_security_xattr_handler, &shmem_trusted_xattr_handler, NULL }; static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size) { struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); return simple_xattr_list(d_inode(dentry), &info->xattrs, buffer, size); } #endif /* CONFIG_TMPFS_XATTR */ static const struct inode_operations shmem_short_symlink_operations = { .get_link = simple_get_link, #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, #endif }; static const struct inode_operations shmem_symlink_inode_operations = { .get_link = shmem_get_link, #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, #endif }; static struct dentry *shmem_get_parent(struct dentry *child) { return ERR_PTR(-ESTALE); } static int shmem_match(struct inode *ino, void *vfh) { __u32 *fh = vfh; __u64 inum = fh[2]; inum = (inum << 32) | fh[1]; return ino->i_ino == inum && fh[0] == ino->i_generation; } /* Find any alias of inode, but prefer a hashed alias */ static struct dentry *shmem_find_alias(struct inode *inode) { struct dentry *alias = d_find_alias(inode); return alias ?: d_find_any_alias(inode); } static struct dentry *shmem_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { struct inode *inode; struct dentry *dentry = NULL; u64 inum; if (fh_len < 3) return NULL; inum = fid->raw[2]; inum = (inum << 32) | fid->raw[1]; inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]), shmem_match, fid->raw); if (inode) { dentry = shmem_find_alias(inode); iput(inode); } return dentry; } static int shmem_encode_fh(struct inode *inode, __u32 *fh, int *len, struct inode *parent) { if (*len < 3) { *len = 3; return FILEID_INVALID; } if (inode_unhashed(inode)) { /* Unfortunately insert_inode_hash is not idempotent, * so as we hash inodes here rather than at creation * time, we need a lock to ensure we only try * to do it once */ static DEFINE_SPINLOCK(lock); spin_lock(&lock); if (inode_unhashed(inode)) __insert_inode_hash(inode, inode->i_ino + inode->i_generation); spin_unlock(&lock); } fh[0] = inode->i_generation; fh[1] = inode->i_ino; fh[2] = ((__u64)inode->i_ino) >> 32; *len = 3; return 1; } static const struct export_operations shmem_export_ops = { .get_parent = shmem_get_parent, .encode_fh = shmem_encode_fh, .fh_to_dentry = shmem_fh_to_dentry, }; enum shmem_param { Opt_gid, Opt_huge, Opt_mode, Opt_mpol, Opt_nr_blocks, Opt_nr_inodes, Opt_size, Opt_uid, Opt_inode32, Opt_inode64, }; static const struct constant_table shmem_param_enums_huge[] = { {"never", SHMEM_HUGE_NEVER }, {"always", SHMEM_HUGE_ALWAYS }, {"within_size", SHMEM_HUGE_WITHIN_SIZE }, {"advise", SHMEM_HUGE_ADVISE }, {} }; const struct fs_parameter_spec shmem_fs_parameters[] = { fsparam_u32 ("gid", Opt_gid), fsparam_enum ("huge", Opt_huge, shmem_param_enums_huge), fsparam_u32oct("mode", Opt_mode), fsparam_string("mpol", Opt_mpol), fsparam_string("nr_blocks", Opt_nr_blocks), fsparam_string("nr_inodes", Opt_nr_inodes), fsparam_string("size", Opt_size), fsparam_u32 ("uid", Opt_uid), fsparam_flag ("inode32", Opt_inode32), fsparam_flag ("inode64", Opt_inode64), {} }; static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param) { struct shmem_options *ctx = fc->fs_private; struct fs_parse_result result; unsigned long long size; char *rest; int opt; kuid_t kuid; kgid_t kgid; opt = fs_parse(fc, shmem_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_size: size = memparse(param->string, &rest); if (*rest == '%') { size <<= PAGE_SHIFT; size *= totalram_pages(); do_div(size, 100); rest++; } if (*rest) goto bad_value; ctx->blocks = DIV_ROUND_UP(size, PAGE_SIZE); ctx->seen |= SHMEM_SEEN_BLOCKS; break; case Opt_nr_blocks: ctx->blocks = memparse(param->string, &rest); if (*rest) goto bad_value; ctx->seen |= SHMEM_SEEN_BLOCKS; break; case Opt_nr_inodes: ctx->inodes = memparse(param->string, &rest); if (*rest) goto bad_value; ctx->seen |= SHMEM_SEEN_INODES; break; case Opt_mode: ctx->mode = result.uint_32 & 07777; break; case Opt_uid: kuid = make_kuid(current_user_ns(), result.uint_32); if (!uid_valid(kuid)) goto bad_value; /* * The requested uid must be representable in the * filesystem's idmapping. */ if (!kuid_has_mapping(fc->user_ns, kuid)) goto bad_value; ctx->uid = kuid; break; case Opt_gid: kgid = make_kgid(current_user_ns(), result.uint_32); if (!gid_valid(kgid)) goto bad_value; /* * The requested gid must be representable in the * filesystem's idmapping. */ if (!kgid_has_mapping(fc->user_ns, kgid)) goto bad_value; ctx->gid = kgid; break; case Opt_huge: ctx->huge = result.uint_32; if (ctx->huge != SHMEM_HUGE_NEVER && !(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && has_transparent_hugepage())) goto unsupported_parameter; ctx->seen |= SHMEM_SEEN_HUGE; break; case Opt_mpol: if (IS_ENABLED(CONFIG_NUMA)) { mpol_put(ctx->mpol); ctx->mpol = NULL; if (mpol_parse_str(param->string, &ctx->mpol)) goto bad_value; break; } goto unsupported_parameter; case Opt_inode32: ctx->full_inums = false; ctx->seen |= SHMEM_SEEN_INUMS; break; case Opt_inode64: if (sizeof(ino_t) < 8) { return invalfc(fc, "Cannot use inode64 with <64bit inums in kernel\n"); } ctx->full_inums = true; ctx->seen |= SHMEM_SEEN_INUMS; break; } return 0; unsupported_parameter: return invalfc(fc, "Unsupported parameter '%s'", param->key); bad_value: return invalfc(fc, "Bad value for '%s'", param->key); } static int shmem_parse_options(struct fs_context *fc, void *data) { char *options = data; if (options) { int err = security_sb_eat_lsm_opts(options, &fc->security); if (err) return err; } while (options != NULL) { char *this_char = options; for (;;) { /* * NUL-terminate this option: unfortunately, * mount options form a comma-separated list, * but mpol's nodelist may also contain commas. */ options = strchr(options, ','); if (options == NULL) break; options++; if (!isdigit(*options)) { options[-1] = '\0'; break; } } if (*this_char) { char *value = strchr(this_char,'='); size_t len = 0; int err; if (value) { *value++ = '\0'; len = strlen(value); } err = vfs_parse_fs_string(fc, this_char, value, len); if (err < 0) return err; } } return 0; } /* * Reconfigure a shmem filesystem. * * Note that we disallow change from limited->unlimited blocks/inodes while any * are in use; but we must separately disallow unlimited->limited, because in * that case we have no record of how much is already in use. */ static int shmem_reconfigure(struct fs_context *fc) { struct shmem_options *ctx = fc->fs_private; struct shmem_sb_info *sbinfo = SHMEM_SB(fc->root->d_sb); unsigned long inodes; const char *err; spin_lock(&sbinfo->stat_lock); inodes = sbinfo->max_inodes - sbinfo->free_inodes; if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) { if (!sbinfo->max_blocks) { err = "Cannot retroactively limit size"; goto out; } if (percpu_counter_compare(&sbinfo->used_blocks, ctx->blocks) > 0) { err = "Too small a size for current use"; goto out; } } if ((ctx->seen & SHMEM_SEEN_INODES) && ctx->inodes) { if (!sbinfo->max_inodes) { err = "Cannot retroactively limit inodes"; goto out; } if (ctx->inodes < inodes) { err = "Too few inodes for current use"; goto out; } } if ((ctx->seen & SHMEM_SEEN_INUMS) && !ctx->full_inums && sbinfo->next_ino > UINT_MAX) { err = "Current inum too high to switch to 32-bit inums"; goto out; } if (ctx->seen & SHMEM_SEEN_HUGE) sbinfo->huge = ctx->huge; if (ctx->seen & SHMEM_SEEN_INUMS) sbinfo->full_inums = ctx->full_inums; if (ctx->seen & SHMEM_SEEN_BLOCKS) sbinfo->max_blocks = ctx->blocks; if (ctx->seen & SHMEM_SEEN_INODES) { sbinfo->max_inodes = ctx->inodes; sbinfo->free_inodes = ctx->inodes - inodes; } /* * Preserve previous mempolicy unless mpol remount option was specified. */ if (ctx->mpol) { mpol_put(sbinfo->mpol); sbinfo->mpol = ctx->mpol; /* transfers initial ref */ ctx->mpol = NULL; } spin_unlock(&sbinfo->stat_lock); return 0; out: spin_unlock(&sbinfo->stat_lock); return invalfc(fc, "%s", err); } static int shmem_show_options(struct seq_file *seq, struct dentry *root) { struct shmem_sb_info *sbinfo = SHMEM_SB(root->d_sb); if (sbinfo->max_blocks != shmem_default_max_blocks()) seq_printf(seq, ",size=%luk", sbinfo->max_blocks << (PAGE_SHIFT - 10)); if (sbinfo->max_inodes != shmem_default_max_inodes()) seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes); if (sbinfo->mode != (0777 | S_ISVTX)) seq_printf(seq, ",mode=%03ho", sbinfo->mode); if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, sbinfo->uid)); if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, sbinfo->gid)); /* * Showing inode{64,32} might be useful even if it's the system default, * since then people don't have to resort to checking both here and * /proc/config.gz to confirm 64-bit inums were successfully applied * (which may not even exist if IKCONFIG_PROC isn't enabled). * * We hide it when inode64 isn't the default and we are using 32-bit * inodes, since that probably just means the feature isn't even under * consideration. * * As such: * * +-----------------+-----------------+ * | TMPFS_INODE64=y | TMPFS_INODE64=n | * +------------------+-----------------+-----------------+ * | full_inums=true | show | show | * | full_inums=false | show | hide | * +------------------+-----------------+-----------------+ * */ if (IS_ENABLED(CONFIG_TMPFS_INODE64) || sbinfo->full_inums) seq_printf(seq, ",inode%d", (sbinfo->full_inums ? 64 : 32)); #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Rightly or wrongly, show huge mount option unmasked by shmem_huge */ if (sbinfo->huge) seq_printf(seq, ",huge=%s", shmem_format_huge(sbinfo->huge)); #endif shmem_show_mpol(seq, sbinfo->mpol); return 0; } #endif /* CONFIG_TMPFS */ static void shmem_put_super(struct super_block *sb) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); free_percpu(sbinfo->ino_batch); percpu_counter_destroy(&sbinfo->used_blocks); mpol_put(sbinfo->mpol); kfree(sbinfo); sb->s_fs_info = NULL; } static int shmem_fill_super(struct super_block *sb, struct fs_context *fc) { struct shmem_options *ctx = fc->fs_private; struct inode *inode; struct shmem_sb_info *sbinfo; int err = -ENOMEM; /* Round up to L1_CACHE_BYTES to resist false sharing */ sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info), L1_CACHE_BYTES), GFP_KERNEL); if (!sbinfo) return -ENOMEM; sb->s_fs_info = sbinfo; #ifdef CONFIG_TMPFS /* * Per default we only allow half of the physical ram per * tmpfs instance, limiting inodes to one per page of lowmem; * but the internal instance is left unlimited. */ if (!(sb->s_flags & SB_KERNMOUNT)) { if (!(ctx->seen & SHMEM_SEEN_BLOCKS)) ctx->blocks = shmem_default_max_blocks(); if (!(ctx->seen & SHMEM_SEEN_INODES)) ctx->inodes = shmem_default_max_inodes(); if (!(ctx->seen & SHMEM_SEEN_INUMS)) ctx->full_inums = IS_ENABLED(CONFIG_TMPFS_INODE64); } else { sb->s_flags |= SB_NOUSER; } sb->s_export_op = &shmem_export_ops; sb->s_flags |= SB_NOSEC; #else sb->s_flags |= SB_NOUSER; #endif sbinfo->max_blocks = ctx->blocks; sbinfo->free_inodes = sbinfo->max_inodes = ctx->inodes; if (sb->s_flags & SB_KERNMOUNT) { sbinfo->ino_batch = alloc_percpu(ino_t); if (!sbinfo->ino_batch) goto failed; } sbinfo->uid = ctx->uid; sbinfo->gid = ctx->gid; sbinfo->full_inums = ctx->full_inums; sbinfo->mode = ctx->mode; sbinfo->huge = ctx->huge; sbinfo->mpol = ctx->mpol; ctx->mpol = NULL; spin_lock_init(&sbinfo->stat_lock); if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL)) goto failed; spin_lock_init(&sbinfo->shrinklist_lock); INIT_LIST_HEAD(&sbinfo->shrinklist); sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = TMPFS_MAGIC; sb->s_op = &shmem_ops; sb->s_time_gran = 1; #ifdef CONFIG_TMPFS_XATTR sb->s_xattr = shmem_xattr_handlers; #endif #ifdef CONFIG_TMPFS_POSIX_ACL sb->s_flags |= SB_POSIXACL; #endif uuid_gen(&sb->s_uuid); inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); if (!inode) goto failed; inode->i_uid = sbinfo->uid; inode->i_gid = sbinfo->gid; sb->s_root = d_make_root(inode); if (!sb->s_root) goto failed; return 0; failed: shmem_put_super(sb); return err; } static int shmem_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, shmem_fill_super); } static void shmem_free_fc(struct fs_context *fc) { struct shmem_options *ctx = fc->fs_private; if (ctx) { mpol_put(ctx->mpol); kfree(ctx); } } static const struct fs_context_operations shmem_fs_context_ops = { .free = shmem_free_fc, .get_tree = shmem_get_tree, #ifdef CONFIG_TMPFS .parse_monolithic = shmem_parse_options, .parse_param = shmem_parse_one, .reconfigure = shmem_reconfigure, #endif }; static struct kmem_cache *shmem_inode_cachep; static struct inode *shmem_alloc_inode(struct super_block *sb) { struct shmem_inode_info *info; info = kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL); if (!info) return NULL; return &info->vfs_inode; } static void shmem_free_in_core_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); } static void shmem_destroy_inode(struct inode *inode) { if (S_ISREG(inode->i_mode)) mpol_free_shared_policy(&SHMEM_I(inode)->policy); } static void shmem_init_inode(void *foo) { struct shmem_inode_info *info = foo; inode_init_once(&info->vfs_inode); } static void shmem_init_inodecache(void) { shmem_inode_cachep = kmem_cache_create("shmem_inode_cache", sizeof(struct shmem_inode_info), 0, SLAB_PANIC|SLAB_ACCOUNT, shmem_init_inode); } static void shmem_destroy_inodecache(void) { kmem_cache_destroy(shmem_inode_cachep); } static const struct address_space_operations shmem_aops = { .writepage = shmem_writepage, .set_page_dirty = __set_page_dirty_no_writeback, #ifdef CONFIG_TMPFS .write_begin = shmem_write_begin, .write_end = shmem_write_end, #endif #ifdef CONFIG_MIGRATION .migratepage = migrate_page, #endif .error_remove_page = generic_error_remove_page, }; static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, .get_unmapped_area = shmem_get_unmapped_area, #ifdef CONFIG_TMPFS .llseek = shmem_file_llseek, .read_iter = shmem_file_read_iter, .write_iter = generic_file_write_iter, .fsync = noop_fsync, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = shmem_fallocate, #endif }; static const struct inode_operations shmem_inode_operations = { .getattr = shmem_getattr, .setattr = shmem_setattr, #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, .set_acl = simple_set_acl, #endif }; static const struct inode_operations shmem_dir_inode_operations = { #ifdef CONFIG_TMPFS .create = shmem_create, .lookup = simple_lookup, .link = shmem_link, .unlink = shmem_unlink, .symlink = shmem_symlink, .mkdir = shmem_mkdir, .rmdir = shmem_rmdir, .mknod = shmem_mknod, .rename = shmem_rename2, .tmpfile = shmem_tmpfile, #endif #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, .set_acl = simple_set_acl, #endif }; static const struct inode_operations shmem_special_inode_operations = { #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, .set_acl = simple_set_acl, #endif }; static const struct super_operations shmem_ops = { .alloc_inode = shmem_alloc_inode, .free_inode = shmem_free_in_core_inode, .destroy_inode = shmem_destroy_inode, #ifdef CONFIG_TMPFS .statfs = shmem_statfs, .show_options = shmem_show_options, #endif .evict_inode = shmem_evict_inode, .drop_inode = generic_delete_inode, .put_super = shmem_put_super, #ifdef CONFIG_TRANSPARENT_HUGEPAGE .nr_cached_objects = shmem_unused_huge_count, .free_cached_objects = shmem_unused_huge_scan, #endif }; static const struct vm_operations_struct shmem_vm_ops = { .fault = shmem_fault, .map_pages = filemap_map_pages, #ifdef CONFIG_NUMA .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, #endif }; int shmem_init_fs_context(struct fs_context *fc) { struct shmem_options *ctx; ctx = kzalloc(sizeof(struct shmem_options), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->mode = 0777 | S_ISVTX; ctx->uid = current_fsuid(); ctx->gid = current_fsgid(); fc->fs_private = ctx; fc->ops = &shmem_fs_context_ops; return 0; } static struct file_system_type shmem_fs_type = { .owner = THIS_MODULE, .name = "tmpfs", .init_fs_context = shmem_init_fs_context, #ifdef CONFIG_TMPFS .parameters = shmem_fs_parameters, #endif .kill_sb = kill_litter_super, .fs_flags = FS_USERNS_MOUNT | FS_THP_SUPPORT, }; int __init shmem_init(void) { int error; shmem_init_inodecache(); error = register_filesystem(&shmem_fs_type); if (error) { pr_err("Could not register tmpfs\n"); goto out2; } shm_mnt = kern_mount(&shmem_fs_type); if (IS_ERR(shm_mnt)) { error = PTR_ERR(shm_mnt); pr_err("Could not kern_mount tmpfs\n"); goto out1; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (has_transparent_hugepage() && shmem_huge > SHMEM_HUGE_DENY) SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; else shmem_huge = 0; /* just in case it was patched */ #endif return 0; out1: unregister_filesystem(&shmem_fs_type); out2: shmem_destroy_inodecache(); shm_mnt = ERR_PTR(error); return error; } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS) static ssize_t shmem_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { static const int values[] = { SHMEM_HUGE_ALWAYS, SHMEM_HUGE_WITHIN_SIZE, SHMEM_HUGE_ADVISE, SHMEM_HUGE_NEVER, SHMEM_HUGE_DENY, SHMEM_HUGE_FORCE, }; int i, count; for (i = 0, count = 0; i < ARRAY_SIZE(values); i++) { const char *fmt = shmem_huge == values[i] ? "[%s] " : "%s "; count += sprintf(buf + count, fmt, shmem_format_huge(values[i])); } buf[count - 1] = '\n'; return count; } static ssize_t shmem_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { char tmp[16]; int huge; if (count + 1 > sizeof(tmp)) return -EINVAL; memcpy(tmp, buf, count); tmp[count] = '\0'; if (count && tmp[count - 1] == '\n') tmp[count - 1] = '\0'; huge = shmem_parse_huge(tmp); if (huge == -EINVAL) return -EINVAL; if (!has_transparent_hugepage() && huge != SHMEM_HUGE_NEVER && huge != SHMEM_HUGE_DENY) return -EINVAL; shmem_huge = huge; if (shmem_huge > SHMEM_HUGE_DENY) SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; return count; } struct kobj_attribute shmem_enabled_attr = __ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store); #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_SYSFS */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE bool shmem_huge_enabled(struct vm_area_struct *vma) { struct inode *inode = file_inode(vma->vm_file); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); loff_t i_size; pgoff_t off; if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false; if (shmem_huge == SHMEM_HUGE_FORCE) return true; if (shmem_huge == SHMEM_HUGE_DENY) return false; switch (sbinfo->huge) { case SHMEM_HUGE_NEVER: return false; case SHMEM_HUGE_ALWAYS: return true; case SHMEM_HUGE_WITHIN_SIZE: off = round_up(vma->vm_pgoff, HPAGE_PMD_NR); i_size = round_up(i_size_read(inode), PAGE_SIZE); if (i_size >= HPAGE_PMD_SIZE && i_size >> PAGE_SHIFT >= off) return true; fallthrough; case SHMEM_HUGE_ADVISE: /* TODO: implement fadvise() hints */ return (vma->vm_flags & VM_HUGEPAGE); default: VM_BUG_ON(1); return false; } } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #else /* !CONFIG_SHMEM */ /* * tiny-shmem: simple shmemfs and tmpfs using ramfs code * * This is intended for small system where the benefits of the full * shmem code (swap-backed and resource-limited) are outweighed by * their complexity. On systems without swap this code should be * effectively equivalent, but much lighter weight. */ static struct file_system_type shmem_fs_type = { .name = "tmpfs", .init_fs_context = ramfs_init_fs_context, .parameters = ramfs_fs_parameters, .kill_sb = ramfs_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; int __init shmem_init(void) { BUG_ON(register_filesystem(&shmem_fs_type) != 0); shm_mnt = kern_mount(&shmem_fs_type); BUG_ON(IS_ERR(shm_mnt)); return 0; } int shmem_unuse(unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { return 0; } int shmem_lock(struct file *file, int lock, struct user_struct *user) { return 0; } void shmem_unlock_mapping(struct address_space *mapping) { } #ifdef CONFIG_MMU unsigned long shmem_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); } #endif void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { truncate_inode_pages_range(inode->i_mapping, lstart, lend); } EXPORT_SYMBOL_GPL(shmem_truncate_range); #define shmem_vm_ops generic_file_vm_ops #define shmem_file_operations ramfs_file_operations #define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev) #define shmem_acct_size(flags, size) 0 #define shmem_unacct_size(flags, size) do {} while (0) #endif /* CONFIG_SHMEM */ /* common code */ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, loff_t size, unsigned long flags, unsigned int i_flags) { struct inode *inode; struct file *res; if (IS_ERR(mnt)) return ERR_CAST(mnt); if (size < 0 || size > MAX_LFS_FILESIZE) return ERR_PTR(-EINVAL); if (shmem_acct_size(flags, size)) return ERR_PTR(-ENOMEM); inode = shmem_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0, flags); if (unlikely(!inode)) { shmem_unacct_size(flags, size); return ERR_PTR(-ENOSPC); } inode->i_flags |= i_flags; inode->i_size = size; clear_nlink(inode); /* It is unlinked */ res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size)); if (!IS_ERR(res)) res = alloc_file_pseudo(inode, mnt, name, O_RDWR, &shmem_file_operations); if (IS_ERR(res)) iput(inode); return res; } /** * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be * kernel internal. There will be NO LSM permission checks against the * underlying inode. So users of this interface must do LSM checks at a * higher layer. The users are the big_key and shm implementations. LSM * checks are provided at the key or shm level rather than the inode. * @name: name for dentry (to be seen in /proc/<pid>/maps * @size: size to be set for the file * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags) { return __shmem_file_setup(shm_mnt, name, size, flags, S_PRIVATE); } /** * shmem_file_setup - get an unlinked file living in tmpfs * @name: name for dentry (to be seen in /proc/<pid>/maps * @size: size to be set for the file * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags) { return __shmem_file_setup(shm_mnt, name, size, flags, 0); } EXPORT_SYMBOL_GPL(shmem_file_setup); /** * shmem_file_setup_with_mnt - get an unlinked file living in tmpfs * @mnt: the tmpfs mount where the file will be created * @name: name for dentry (to be seen in /proc/<pid>/maps * @size: size to be set for the file * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt, const char *name, loff_t size, unsigned long flags) { return __shmem_file_setup(mnt, name, size, flags, 0); } EXPORT_SYMBOL_GPL(shmem_file_setup_with_mnt); /** * shmem_zero_setup - setup a shared anonymous mapping * @vma: the vma to be mmapped is prepared by do_mmap */ int shmem_zero_setup(struct vm_area_struct *vma) { struct file *file; loff_t size = vma->vm_end - vma->vm_start; /* * Cloning a new file under mmap_lock leads to a lock ordering conflict * between XFS directory reading and selinux: since this file is only * accessible to the user through its mapping, use S_PRIVATE flag to * bypass file security, in the same way as shmem_kernel_file_setup(). */ file = shmem_kernel_file_setup("dev/zero", size, vma->vm_flags); if (IS_ERR(file)) return PTR_ERR(file); if (vma->vm_file) fput(vma->vm_file); vma->vm_file = file; vma->vm_ops = &shmem_vm_ops; if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < (vma->vm_end & HPAGE_PMD_MASK)) { khugepaged_enter(vma, vma->vm_flags); } return 0; } /** * shmem_read_mapping_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)", * with any new page allocations done using the specified allocation flags. * But read_cache_page_gfp() uses the ->readpage() method: which does not * suit tmpfs, since it may have pages in swapcache, and needs to find those * for itself; although drivers/gpu/drm i915 and ttm rely upon this support. * * i915_gem_object_get_pages_gtt() mixes __GFP_NORETRY | __GFP_NOWARN in * with the mapping_gfp_mask(), to avoid OOMing the machine unnecessarily. */ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { #ifdef CONFIG_SHMEM struct inode *inode = mapping->host; struct page *page; int error; BUG_ON(mapping->a_ops != &shmem_aops); error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE, gfp, NULL, NULL, NULL); if (error) page = ERR_PTR(error); else unlock_page(page); return page; #else /* * The tiny !SHMEM case uses ramfs without swap */ return read_cache_page_gfp(mapping, index, gfp); #endif } EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * * Support four policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * * interleave Allocate memory interleaved over a set of nodes, * with normal fallback if it fails. * For VMA based allocations this interleaves based on the * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. * * The process policy is applied for most non interrupt memory allocations * in that process' context. Interrupts ignore the policies and always * try to allocate on the local CPU. The VMA policy is only applied for memory * allocations for a VMA in the VM. * * Currently there are a few corner cases in swapping where the policy * is not applied, but the majority should be handled. When process policy * is used it is not remembered over swap outs/swap ins. * * Only the highest zone in the zone hierarchy gets policied. Allocations * requesting a lower zone just use default policy. This implies that * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * * For shmfs/tmpfs/hugetlbfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ /* Notebook: fix mmap readahead to honour policy and enable policy for any page cache object statistics for bigpages global policy for page cache? currently it uses process policy. Requires first item above. handle mremap for shared memory (currently ignored for the policy) grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/ptrace.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/migrate.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/printk.h> #include <linux/swapops.h> #include <asm/tlbflush.h> #include <linux/uaccess.h> #include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_PREFERRED, .flags = MPOL_F_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; /** * numa_map_to_online_node - Find closest online node * @node: Node id to start the search * * Lookup the next closest node by distance if @nid is not online. */ int numa_map_to_online_node(int node) { int min_dist = INT_MAX, dist, n, min_node; if (node == NUMA_NO_NODE || node_online(node)) return node; min_node = node; for_each_online_node(n) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(numa_map_to_online_node); struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; int node; if (pol) return pol; node = numa_node_id(); if (node != NUMA_NO_NODE) { pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ if (pol->mode) return pol; } return &default_policy; } static const struct mempolicy_operations { int (*create)(struct mempolicy *pol, const nodemask_t *nodes); void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); } mpol_ops[MPOL_MAX]; static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_MODE_FLAGS; } static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, const nodemask_t *rel) { nodemask_t tmp; nodes_fold(tmp, *orig, nodes_weight(*rel)); nodes_onto(*ret, tmp, *rel); } static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->v.nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { if (!nodes) pol->flags |= MPOL_F_LOCAL; /* local allocation */ else if (nodes_empty(*nodes)) return -EINVAL; /* no allowed nodes */ else pol->v.preferred_node = first_node(*nodes); return 0; } static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->v.nodes = *nodes; return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes * parameter with respect to the policy mode and flags. But, we need to * handle an empty nodemask with MPOL_PREFERRED here. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. */ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes, struct nodemask_scratch *nsc) { int ret; /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ if (pol == NULL) return 0; /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) nodes = NULL; /* explicit local allocation */ else { if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; } if (nodes) ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); else ret = mpol_ops[pol->mode].create(pol, NULL); return ret; } /* * This function just creates a new policy, does some check and simple * initialization. You must invoke mpol_set_nodemask() to set nodes. */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; pr_debug("setting mode %d flags %d nodes[0] %lx\n", mode, flags, nodes ? nodes_addr(*nodes)[0] : NUMA_NO_NODE); if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); return NULL; } VM_BUG_ON(!nodes); /* * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). * All other modes require a valid pointer to a non-empty nodemask. */ if (mode == MPOL_PREFERRED) { if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); mode = MPOL_PREFERRED; } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; return policy; } /* Slow path of a mpol destructor. */ void __mpol_put(struct mempolicy *p) { if (!atomic_dec_and_test(&p->refcnt)) return; kmem_cache_free(policy_cache, p); } static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) { } static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) nodes_and(tmp, pol->w.user_nodemask, *nodes); else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { nodes_remap(tmp, pol->v.nodes,pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) tmp = *nodes; pol->v.nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) { int node = first_node(pol->w.user_nodemask); if (node_isset(node, *nodes)) { pol->v.preferred_node = node; pol->flags &= ~MPOL_F_LOCAL; } else pol->flags |= MPOL_F_LOCAL; } else if (pol->flags & MPOL_F_RELATIVE_NODES) { mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); pol->v.preferred_node = first_node(tmp); } else if (!(pol->flags & MPOL_F_LOCAL)) { pol->v.preferred_node = node_remap(pol->v.preferred_node, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } } /* * mpol_rebind_policy - Migrate a policy to a different set of nodes * * Per-vma policies are protected by mmap_lock. Allocations using per-task * policies are protected by task->mems_allowed_seq to prevent a premature * OOM/allocation failure due to parallel nodemask modification. */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && !(pol->flags & MPOL_F_LOCAL) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; mpol_ops[pol->mode].rebind(pol, newmask); } /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. * * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); } /* * Rebind each vma in mm to new nodemask. * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; mmap_write_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) mpol_rebind_policy(vma->vm_policy, new); mmap_write_unlock(mm); } static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { [MPOL_DEFAULT] = { .rebind = mpol_rebind_default, }, [MPOL_INTERLEAVE] = { .create = mpol_new_interleave, .rebind = mpol_rebind_nodemask, }, [MPOL_PREFERRED] = { .create = mpol_new_preferred, .rebind = mpol_rebind_preferred, }, [MPOL_BIND] = { .create = mpol_new_bind, .rebind = mpol_rebind_nodemask, }, }; static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags); struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; unsigned long start; unsigned long end; struct vm_area_struct *first; }; /* * Check if the page's nid is in qp->nmask. * * If MPOL_MF_INVERT is set in qp->flags, check if the nid is * in the invert of qp->nmask. */ static inline bool queue_pages_required(struct page *page, struct queue_pages *qp) { int nid = page_to_nid(page); unsigned long flags = qp->flags; return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } /* * queue_pages_pmd() has four possible return values: * 0 - pages are placed on the right node or queued successfully. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 2 - THP was split. * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an * existing page was already on a node that does not follow the * policy. */ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, unsigned long end, struct mm_walk *walk) __releases(ptl) { int ret = 0; struct page *page; struct queue_pages *qp = walk->private; unsigned long flags; if (unlikely(is_pmd_migration_entry(*pmd))) { ret = -EIO; goto unlock; } page = pmd_page(*pmd); if (is_huge_zero_page(page)) { spin_unlock(ptl); __split_huge_pmd(walk->vma, pmd, addr, false, NULL); ret = 2; goto out; } if (!queue_pages_required(page, qp)) goto unlock; flags = qp->flags; /* go to thp migration */ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { if (!vma_migratable(walk->vma) || migrate_page_add(page, qp->pagelist, flags)) { ret = 1; goto unlock; } } else ret = -EIO; unlock: spin_unlock(ptl); out: return ret; } /* * Scan through pages checking if pages follow certain conditions, * and move them to the pagelist if they do. * * queue_pages_pte_range() has three possible return values: * 0 - pages are placed on the right node or queued successfully. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * -EIO - only MPOL_MF_STRICT was specified and an existing page was already * on a node that does not follow the policy. */ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct page *page; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; int ret; bool has_unmovable = false; pte_t *pte, *mapped_pte; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { ret = queue_pages_pmd(pmd, ptl, addr, end, walk); if (ret != 2) return ret; } /* THP was split, fall through to pte walk */ if (pmd_trans_unstable(pmd)) return 0; mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { if (!pte_present(*pte)) continue; page = vm_normal_page(vma, addr, *pte); if (!page) continue; /* * vm_normal_page() filters out zero pages, but there might * still be PageReserved pages to skip, perhaps in a VDSO. */ if (PageReserved(page)) continue; if (!queue_pages_required(page, qp)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { /* MPOL_MF_STRICT must be specified if we get here */ if (!vma_migratable(vma)) { has_unmovable = true; break; } /* * Do not abort immediately since there may be * temporary off LRU pages in the range. Still * need migrate other LRU pages. */ if (migrate_page_add(page, qp->pagelist, flags)) has_unmovable = true; } else break; } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); if (has_unmovable) return 1; return addr != end ? -EIO : 0; } static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { int ret = 0; #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; unsigned long flags = (qp->flags & MPOL_MF_VALID); struct page *page; spinlock_t *ptl; pte_t entry; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); entry = huge_ptep_get(pte); if (!pte_present(entry)) goto unlock; page = pte_page(entry); if (!queue_pages_required(page, qp)) goto unlock; if (flags == MPOL_MF_STRICT) { /* * STRICT alone means only detecting misplaced page and no * need to further check other vma. */ ret = -EIO; goto unlock; } if (!vma_migratable(walk->vma)) { /* * Must be STRICT with MOVE*, otherwise .test_walk() have * stopped walking current vma. * Detecting misplaced page but allow migrating pages which * have been queued. */ ret = 1; goto unlock; } /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ if (flags & (MPOL_MF_MOVE_ALL) || (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 && !hugetlb_pmd_shared(pte))) { if (isolate_hugetlb(page, qp->pagelist) && (flags & MPOL_MF_STRICT)) /* * Failed to isolate page but allow migrating pages * which have been queued. */ ret = 1; } unlock: spin_unlock(ptl); #else BUG(); #endif return ret; } #ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these * faults, pages may be migrated for better NUMA placement. * * This is assuming that NUMA faults are handled using PROT_NONE. If * an architecture makes a different choice, it will need further * changes to the core. */ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { int nr_updated; nr_updated = change_protection(vma, addr, end, PAGE_NONE, MM_CP_PROT_NUMA); if (nr_updated) count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); return nr_updated; } #else static unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { return 0; } #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct queue_pages *qp = walk->private; unsigned long endvma = vma->vm_end; unsigned long flags = qp->flags; /* range check first */ VM_BUG_ON_VMA((vma->vm_start > start) || (vma->vm_end < end), vma); if (!qp->first) { qp->first = vma; if (!(flags & MPOL_MF_DISCONTIG_OK) && (qp->start < vma->vm_start)) /* hole at head side of range */ return -EFAULT; } if (!(flags & MPOL_MF_DISCONTIG_OK) && ((vma->vm_end < qp->end) && (!vma->vm_next || vma->vm_end < vma->vm_next->vm_start))) /* hole at middle or tail of range */ return -EFAULT; /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable */ if (!vma_migratable(vma) && !(flags & MPOL_MF_STRICT)) return 1; if (endvma > end) endvma = end; if (flags & MPOL_MF_LAZY) { /* Similar to task_numa_work, skip inaccessible VMAs */ if (!is_vm_hugetlb_page(vma) && vma_is_accessible(vma) && !(vma->vm_flags & VM_MIXEDMAP)) change_prot_numa(vma, start, endvma); return 1; } /* queue pages from current vma */ if (flags & MPOL_MF_VALID) return 0; return 1; } static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_pages_hugetlb, .pmd_entry = queue_pages_pte_range, .test_walk = queue_pages_test_walk, }; /* * Walk through page tables and collect pages to be migrated. * * If pages found in a given range are on a set of nodes (determined by * @nodes and @flags,) it's isolated and queued to the pagelist which is * passed via @private. * * queue_pages_range() has three possible return values: * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 0 - queue pages successfully or no misplaced page. * errno - i.e. misplaced pages with MPOL_MF_STRICT specified (-EIO) or * memory range specified by nodemask and maxnode points outside * your accessible address space (-EFAULT) */ static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, .start = start, .end = end, .first = NULL, }; err = walk_page_range(mm, start, end, &queue_pages_walk_ops, &qp); if (!qp.first) /* whole range in hole */ err = -EFAULT; return err; } /* * Apply policy to a single VMA * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct mempolicy *old; struct mempolicy *new; pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n", vma->vm_start, vma->vm_end, vma->vm_pgoff, vma->vm_ops, vma->vm_file, vma->vm_ops ? vma->vm_ops->set_policy : NULL); new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) goto err_out; } old = vma->vm_policy; vma->vm_policy = new; /* protected by mmap_lock */ mpol_put(old); return 0; err_out: mpol_put(new); return err; } /* Step 2: apply policy to a range and do splits. */ static int mbind_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct mempolicy *new_pol) { struct vm_area_struct *prev; struct vm_area_struct *vma; int err = 0; pgoff_t pgoff; unsigned long vmstart; unsigned long vmend; vma = find_vma(mm, start); VM_BUG_ON(!vma); prev = vma->vm_prev; if (start > vma->vm_start) prev = vma; for (; vma && vma->vm_start < end; prev = vma, vma = vma->vm_next) { vmstart = max(start, vma->vm_start); vmend = min(end, vma->vm_end); if (mpol_equal(vma_policy(vma), new_pol)) continue; pgoff = vma->vm_pgoff + ((vmstart - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, new_pol, vma->vm_userfaultfd_ctx); if (prev) { vma = prev; goto replace; } if (vma->vm_start != vmstart) { err = split_vma(vma->vm_mm, vma, vmstart, 1); if (err) goto out; } if (vma->vm_end != vmend) { err = split_vma(vma->vm_mm, vma, vmend, 0); if (err) goto out; } replace: err = vma_replace_policy(vma, new_pol); if (err) goto out; } out: return err; } /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new, *old; NODEMASK_SCRATCH(scratch); int ret; if (!scratch) return -ENOMEM; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out; } ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { mpol_put(new); goto out; } task_lock(current); old = current->mempolicy; current->mempolicy = new; if (new && new->mode == MPOL_INTERLEAVE) current->il_prev = MAX_NUMNODES-1; task_unlock(current); mpol_put(old); ret = 0; out: NODEMASK_SCRATCH_FREE(scratch); return ret; } /* * Return nodemask for policy for get_mempolicy() query * * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes) { nodes_clear(*nodes); if (p == &default_policy) return; switch (p->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: *nodes = p->v.nodes; break; case MPOL_PREFERRED: if (!(p->flags & MPOL_F_LOCAL)) node_set(p->v.preferred_node, *nodes); /* else return empty node mask for local allocation */ break; default: BUG(); } } static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p = NULL; int err; int locked = 1; err = get_user_pages_locked(addr & PAGE_MASK, 1, 0, &p, &locked); if (err > 0) { err = page_to_nid(p); put_page(p); } if (locked) mmap_read_unlock(mm); return err; } /* Retrieve NUMA policy */ static long do_get_mempolicy(int *policy, nodemask_t *nmask, unsigned long addr, unsigned long flags) { int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; if (flags & MPOL_F_MEMS_ALLOWED) { if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ task_lock(current); *nmask = cpuset_current_mems_allowed; task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); vma = find_vma_intersection(mm, addr, addr+1); if (!vma) { mmap_read_unlock(mm); return -EFAULT; } if (vma->vm_ops && vma->vm_ops->get_policy) pol = vma->vm_ops->get_policy(vma, addr); else pol = vma->vm_policy; } else if (addr) return -EINVAL; if (!pol) pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, lookup_node() * wil drop the mmap_lock, so after calling * lookup_node() only "pol" remains valid, "vma" * is stale. */ pol_refcount = pol; vma = NULL; mpol_get(pol); err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->v.nodes); } else { err = -EINVAL; goto out; } } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; /* * Internal mempolicy flags must be masked off before exposing * the policy to userspace. */ *policy |= (pol->flags & MPOL_MODE_FLAGS); } err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { *nmask = pol->w.user_nodemask; } else { task_lock(current); get_policy_nodemask(pol, nmask); task_unlock(current); } } out: mpol_cond_put(pol); if (vma) mmap_read_unlock(mm); if (pol_refcount) mpol_put(pol_refcount); return err; } #ifdef CONFIG_MIGRATION /* * page migration, thp tail pages can be passed. */ static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags) { struct page *head = compound_head(page); /* * Avoid migrating a page that is shared with others. */ if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(head) == 1) { if (!isolate_lru_page(head)) { list_add_tail(&head->lru, pagelist); mod_node_page_state(page_pgdat(head), NR_ISOLATED_ANON + page_is_file_lru(head), thp_nr_pages(head)); } else if (flags & MPOL_MF_STRICT) { /* * Non-movable page may reach here. And, there may be * temporary off LRU pages or non-LRU movable pages. * Treat them as unmovable pages since they can't be * isolated, so they can't be moved at the moment. It * should return -EIO for this case too. */ return -EIO; } } return 0; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ static int migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) { nodemask_t nmask; LIST_HEAD(pagelist); int err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, }; nodes_clear(nmask); node_set(source, nmask); /* * This does not "check" the range but isolates all pages that * need migration. Between passing in the full user address * space range and MPOL_MF_DISCONTIG_OK, this call can not fail. */ VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); queue_pages_range(mm, mm->mmap->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL); if (err) putback_movable_pages(&pagelist); } return err; } /* * Move pages between the two nodesets so as to preserve the physical * layout as much as possible. * * Returns the number of page that could not be moved. */ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { int busy = 0; int err; nodemask_t tmp; err = migrate_prep(); if (err) return err; mmap_read_lock(mm); /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' * bit in 'tmp', and return that <source, dest> pair for migration. * The pair of nodemasks 'to' and 'from' define the map. * * If no pair of bits is found that way, fallback to picking some * pair of 'source' and 'dest' bits that are not the same. If the * 'source' and 'dest' bits are the same, this represents a node * that will be migrating to itself, so no pages need move. * * If no bits are left in 'tmp', or if all remaining bits left * in 'tmp' correspond to the same bit in 'to', return false * (nothing left to migrate). * * This lets us pick a pair of nodes to migrate between, such that * if possible the dest node is not already occupied by some other * source node, minimizing the risk of overloading the memory on a * node that would happen if we migrated incoming memory to a node * before migrating outgoing memory source that same node. * * A single scan of tmp is sufficient. As we go, we remember the * most recent <s, d> pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. * Otherwise when we finish scanning from_tmp, we at least have the * most recent <s, d> pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. */ tmp = *from; while (!nodes_empty(tmp)) { int s,d; int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { /* * do_migrate_pages() tries to maintain the relative * node relationship of the pages established between * threads and memory areas. * * However if the number of source nodes is not equal to * the number of destination nodes we can not preserve * this node relative relationship. In that case, skip * copying memory from a node that is in the destination * mask. * * Example: [2,3,4] -> [3,4,5] moves everything. * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ if ((nodes_weight(*from) != nodes_weight(*to)) && (node_isset(s, *to))) continue; d = node_remap(s, *from, *to); if (s == d) continue; source = s; /* Node moved. Memorize */ dest = d; /* dest not in remaining from nodes? */ if (!node_isset(dest, tmp)) break; } if (source == NUMA_NO_NODE) break; node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) busy += err; if (err < 0) break; } mmap_read_unlock(mm); if (err < 0) return err; return busy; } /* * Allocate a new page for page migration based on vma policy. * Start by assuming the page is mapped by the same vma as contains @start. * Search forward from there, if not. N.B., this assumes that the * list of pages handed to migrate_pages()--which is how we get here-- * is in virtual address order. */ static struct page *new_page(struct page *page, unsigned long start) { struct vm_area_struct *vma; unsigned long address; vma = find_vma(current->mm, start); while (vma) { address = page_address_in_vma(page, vma); if (address != -EFAULT) break; vma = vma->vm_next; } if (PageHuge(page)) { return alloc_huge_page_vma(page_hstate(compound_head(page)), vma, address); } else if (PageTransHuge(page)) { struct page *thp; thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, HPAGE_PMD_ORDER); if (!thp) return NULL; prep_transhuge_page(thp); return thp; } /* * if !vma, alloc_page_vma() will use task or system default policy */ return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL, vma, address); } #else static int migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags) { return -EIO; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return -ENOSYS; } static struct page *new_page(struct page *page, unsigned long start) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; struct mempolicy *new; unsigned long end; int err; int ret; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; if (start & ~PAGE_MASK) return -EINVAL; if (mode == MPOL_DEFAULT) flags &= ~MPOL_MF_STRICT; len = (len + PAGE_SIZE - 1) & PAGE_MASK; end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); if (flags & MPOL_MF_LAZY) new->flags |= MPOL_F_MOF; /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all */ if (!new) flags |= MPOL_MF_DISCONTIG_OK; pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n", start, start + len, mode, mode_flags, nmask ? nodes_addr(*nmask)[0] : NUMA_NO_NODE); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { err = migrate_prep(); if (err) goto mpol_out; } { NODEMASK_SCRATCH(scratch); if (scratch) { mmap_write_lock(mm); err = mpol_set_nodemask(new, nmask, scratch); if (err) mmap_write_unlock(mm); } else err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } if (err) goto mpol_out; ret = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); if (ret < 0) { err = ret; goto up_out; } err = mbind_range(mm, start, end, new); if (!err) { int nr_failed = 0; if (!list_empty(&pagelist)) { WARN_ON_ONCE(flags & MPOL_MF_LAZY); nr_failed = migrate_pages(&pagelist, new_page, NULL, start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND); if (nr_failed) putback_movable_pages(&pagelist); } if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) err = -EIO; } else { up_out: if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); } mmap_write_unlock(mm); mpol_out: mpol_put(new); return err; } /* * User space interface with variable sized bitmaps for nodelists. */ /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { unsigned long k; unsigned long t; unsigned long nlongs; unsigned long endmask; --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) return 0; if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; nlongs = BITS_TO_LONGS(maxnode); if ((maxnode % BITS_PER_LONG) == 0) endmask = ~0UL; else endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1; /* * When the user specified more nodes than supported just check * if the non supported part is all zero. * * If maxnode have more longs than MAX_NUMNODES, check * the bits in that area first. And then go through to * check the rest bits which equal or bigger than MAX_NUMNODES. * Otherwise, just check bits [MAX_NUMNODES, maxnode). */ if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) { for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) { if (get_user(t, nmask + k)) return -EFAULT; if (k == nlongs - 1) { if (t & endmask) return -EINVAL; } else if (t) return -EINVAL; } nlongs = BITS_TO_LONGS(MAX_NUMNODES); endmask = ~0UL; } if (maxnode > MAX_NUMNODES && MAX_NUMNODES % BITS_PER_LONG != 0) { unsigned long valid_mask = endmask; valid_mask &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); if (get_user(t, nmask + nlongs - 1)) return -EFAULT; if (t & valid_mask) return -EINVAL; } if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long))) return -EFAULT; nodes_addr(*nodes)[nlongs-1] &= endmask; return 0; } /* Copy a kernel node mask to user space */ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); if (copy > nbytes) { if (copy > PAGE_SIZE) return -EINVAL; if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; } return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { nodemask_t nodes; int err; unsigned short mode_flags; start = untagged_addr(start); mode_flags = mode & MPOL_MODE_FLAGS; mode &= ~MPOL_MODE_FLAGS; if (mode >= MPOL_MAX) return -EINVAL; if ((mode_flags & MPOL_F_STATIC_NODES) && (mode_flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_mbind(start, len, mode, mode_flags, &nodes, flags); } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { return kernel_mbind(start, len, mode, nmask, maxnode, flags); } /* Set the process memory policy */ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { int err; nodemask_t nodes; unsigned short flags; flags = mode & MPOL_MODE_FLAGS; mode &= ~MPOL_MODE_FLAGS; if ((unsigned int)mode >= MPOL_MAX) return -EINVAL; if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_set_mempolicy(mode, flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { return kernel_set_mempolicy(mode, nmask, maxnode); } static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { struct mm_struct *mm = NULL; struct task_struct *task; nodemask_t task_nodes; int err; nodemask_t *old; nodemask_t *new; NODEMASK_SCRATCH(scratch); if (!scratch) return -ENOMEM; old = &scratch->mask1; new = &scratch->mask2; err = get_nodes(old, old_nodes, maxnode); if (err) goto out; err = get_nodes(new, new_nodes, maxnode); if (err) goto out; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); err = -ESRCH; goto out; } get_task_struct(task); err = -EINVAL; /* * Check if this process has the right to modify the specified process. * Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out_put; } rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out_put; } task_nodes = cpuset_mems_allowed(current); nodes_and(*new, *new, task_nodes); if (nodes_empty(*new)) goto out_put; err = security_task_movememory(task); if (err) goto out_put; mm = get_task_mm(task); put_task_struct(task); if (!mm) { err = -EINVAL; goto out; } err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); mmput(mm); out: NODEMASK_SCRATCH_FREE(scratch); return err; out_put: put_task_struct(task); goto out; } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, const unsigned long __user *, old_nodes, const unsigned long __user *, new_nodes) { return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; addr = untagged_addr(addr); err = do_get_mempolicy(&pval, &nodes, addr, flags); if (err) return err; if (policy && put_user(pval, policy)) return -EFAULT; if (nmask) err = copy_nodes_to_user(nmask, maxnode, &nodes); return err; } SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode, compat_ulong_t, addr, compat_ulong_t, flags) { long err; unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; DECLARE_BITMAP(bm, MAX_NUMNODES); nr_bits = min_t(unsigned long, maxnode-1, nr_node_ids); alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) nm = compat_alloc_user_space(alloc_size); err = kernel_get_mempolicy(policy, nm, nr_bits+1, addr, flags); if (!err && nmask) { unsigned long copy_size; copy_size = min_t(unsigned long, sizeof(bm), alloc_size); err = copy_from_user(bm, nm, copy_size); /* ensure entire bitmap is zeroed */ err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8); err |= compat_put_bitmap(nmask, bm, nr_bits); } return err; } COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode) { unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; DECLARE_BITMAP(bm, MAX_NUMNODES); nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES); alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { if (compat_get_bitmap(bm, nmask, nr_bits)) return -EFAULT; nm = compat_alloc_user_space(alloc_size); if (copy_to_user(nm, bm, alloc_size)) return -EFAULT; } return kernel_set_mempolicy(mode, nm, nr_bits+1); } COMPAT_SYSCALL_DEFINE6(mbind, compat_ulong_t, start, compat_ulong_t, len, compat_ulong_t, mode, compat_ulong_t __user *, nmask, compat_ulong_t, maxnode, compat_ulong_t, flags) { unsigned long __user *nm = NULL; unsigned long nr_bits, alloc_size; nodemask_t bm; nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES); alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) { if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits)) return -EFAULT; nm = compat_alloc_user_space(alloc_size); if (copy_to_user(nm, nodes_addr(bm), alloc_size)) return -EFAULT; } return kernel_mbind(start, len, mode, nm, nr_bits+1, flags); } COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid, compat_ulong_t, maxnode, const compat_ulong_t __user *, old_nodes, const compat_ulong_t __user *, new_nodes) { unsigned long __user *old = NULL; unsigned long __user *new = NULL; nodemask_t tmp_mask; unsigned long nr_bits; unsigned long size; nr_bits = min_t(unsigned long, maxnode - 1, MAX_NUMNODES); size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (old_nodes) { if (compat_get_bitmap(nodes_addr(tmp_mask), old_nodes, nr_bits)) return -EFAULT; old = compat_alloc_user_space(new_nodes ? size * 2 : size); if (new_nodes) new = old + size / sizeof(unsigned long); if (copy_to_user(old, nodes_addr(tmp_mask), size)) return -EFAULT; } if (new_nodes) { if (compat_get_bitmap(nodes_addr(tmp_mask), new_nodes, nr_bits)) return -EFAULT; if (new == NULL) new = compat_alloc_user_space(size); if (copy_to_user(new, nodes_addr(tmp_mask), size)) return -EFAULT; } return kernel_migrate_pages(pid, nr_bits + 1, old, new); } #endif /* CONFIG_COMPAT */ bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; /* * DAX device mappings require predictable access latency, so avoid * incurring periodic faults. */ if (vma_is_dax(vma)) return false; if (is_vm_hugetlb_page(vma) && !hugepage_migration_supported(hstate_vma(vma))) return false; /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not * possible. */ if (vma->vm_file && gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) < policy_zone) return false; return true; } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = NULL; if (vma) { if (vma->vm_ops && vma->vm_ops->get_policy) { pol = vma->vm_ops->get_policy(vma, addr); } else if (vma->vm_policy) { pol = vma->vm_policy; /* * shmem_alloc_page() passes MPOL_F_SHARED policy with * a pseudo vma whose vma->vm_ops=NULL. Take a reference * count on these policies which will be dropped by * mpol_cond_put() later */ if (mpol_needs_cond_ref(pol)) mpol_get(pol); } } return pol; } /* * get_vma_policy(@vma, @addr) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); if (!pol) pol = get_task_policy(current); return pol; } bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; if (vma->vm_ops && vma->vm_ops->get_policy) { bool ret = false; pol = vma->vm_ops->get_policy(vma, vma->vm_start); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); return ret; } pol = vma->vm_policy; if (!pol) pol = get_task_policy(current); return pol->flags & MPOL_F_MOF; } static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* * if policy->v.nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->v.nodes is intersect with node_states[N_MEMORY]. * so if the following test faile, it implies * policy->v.nodes has movable memory only. */ if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; } /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation */ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) { /* Lower zones don't get a nodemask applied for MPOL_BIND */ if (unlikely(policy->mode == MPOL_BIND) && apply_policy_zone(policy, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&policy->v.nodes)) return &policy->v.nodes; return NULL; } /* Return the node id preferred by the given mempolicy, or the given id */ static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd) { if (policy->mode == MPOL_PREFERRED && !(policy->flags & MPOL_F_LOCAL)) nd = policy->v.preferred_node; else { /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the * requested node and not break the policy. */ WARN_ON_ONCE(policy->mode == MPOL_BIND && (gfp & __GFP_THISNODE)); } return nd; } /* Do dynamic interleaving for a process */ static unsigned interleave_nodes(struct mempolicy *policy) { unsigned next; struct task_struct *me = current; next = next_node_in(me->il_prev, policy->v.nodes); if (next < MAX_NUMNODES) me->il_prev = next; return next; } /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; int node = numa_mem_id(); if (in_interrupt()) return node; policy = current->mempolicy; if (!policy || policy->flags & MPOL_F_LOCAL) return node; switch (policy->mode) { case MPOL_PREFERRED: /* * handled MPOL_F_LOCAL above */ return policy->v.preferred_node; case MPOL_INTERLEAVE: return interleave_nodes(policy); case MPOL_BIND: { struct zoneref *z; /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->v.nodes); return z->zone ? zone_to_nid(z->zone) : node; } default: BUG(); } } /* * Do static interleaving for a VMA with known offset @n. Returns the n'th * node in pol->v.nodes (starting from n=0), wrapping around if n exceeds the * number of present nodes. */ static unsigned offset_il_node(struct mempolicy *pol, unsigned long n) { unsigned nnodes = nodes_weight(pol->v.nodes); unsigned target; int i; int nid; if (!nnodes) return numa_node_id(); target = (unsigned int)n % nnodes; nid = first_node(pol->v.nodes); for (i = 0; i < target; i++) nid = next_node(nid, pol->v.nodes); return nid; } /* Determine a node number for interleave */ static inline unsigned interleave_nid(struct mempolicy *pol, struct vm_area_struct *vma, unsigned long addr, int shift) { if (vma) { unsigned long off; /* * for small pages, there is no difference between * shift and PAGE_SHIFT, so the bit-shift is safe. * for huge pages, since vm_pgoff is in units of small * pages, we need to shift off the always 0 bits to get * a useful offset. */ BUG_ON(shift < PAGE_SHIFT); off = vma->vm_pgoff >> (shift - PAGE_SHIFT); off += (addr - vma->vm_start) >> shift; return offset_il_node(pol, off); } else return interleave_nodes(pol); } #ifdef CONFIG_HUGETLBFS /* * huge_node(@vma, @addr, @gfp_flags, @mpol) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup and interleave policy * @gfp_flags: for requested zone * @mpol: pointer to mempolicy pointer for reference counted mempolicy * @nodemask: pointer to nodemask pointer for MPOL_BIND nodemask * * Returns a nid suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'BIND, returns a pointer to the mempolicy's * @nodemask for filtering the zonelist. * * Must be protected by read_mems_allowed_begin() */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { int nid; *mpol = get_vma_policy(vma, addr); *nodemask = NULL; /* assume !MPOL_BIND */ if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) { nid = interleave_nid(*mpol, vma, addr, huge_page_shift(hstate_vma(vma))); } else { nid = policy_node(gfp_flags, *mpol, numa_node_id()); if ((*mpol)->mode == MPOL_BIND) *nodemask = &(*mpol)->v.nodes; } return nid; } /* * init_nodemask_of_mempolicy * * If the current task's mempolicy is "default" [NULL], return 'false' * to indicate default policy. Otherwise, extract the policy nodemask * for 'bind' or 'interleave' policy into the argument nodemask, or * initialize the argument nodemask to contain the single node for * 'preferred' or 'local' policy and return 'true' to indicate presence * of non-default mempolicy. * * We don't bother with reference counting the mempolicy [mpol_get/put] * because the current task is examining it's own mempolicy and a task's * mempolicy is only ever changed by the task itself. * * N.B., it is the caller's responsibility to free a returned nodemask. */ bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; int nid; if (!(mask && current->mempolicy)) return false; task_lock(current); mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: if (mempolicy->flags & MPOL_F_LOCAL) nid = numa_node_id(); else nid = mempolicy->v.preferred_node; init_nodemask_of_node(mask, nid); break; case MPOL_BIND: case MPOL_INTERLEAVE: *mask = mempolicy->v.nodes; break; default: BUG(); } task_unlock(current); return true; } #endif /* * mempolicy_nodemask_intersects * * If tsk's mempolicy is "default" [NULL], return 'true' to indicate default * policy. Otherwise, check for intersection between mask and the policy * nodemask for 'bind' or 'interleave' policy. For 'perferred' or 'local' * policy, always return true since it may allocate elsewhere on fallback. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ bool mempolicy_nodemask_intersects(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; bool ret = true; if (!mask) return ret; task_lock(tsk); mempolicy = tsk->mempolicy; if (!mempolicy) goto out; switch (mempolicy->mode) { case MPOL_PREFERRED: /* * MPOL_PREFERRED and MPOL_F_LOCAL are only preferred nodes to * allocate from, they may fallback to other nodes when oom. * Thus, it's possible for tsk to have allocated memory from * nodes in mask. */ break; case MPOL_BIND: case MPOL_INTERLEAVE: ret = nodes_intersects(mempolicy->v.nodes, *mask); break; default: BUG(); } out: task_unlock(tsk); return ret; } /* Allocate a page in interleaved policy. Own path because it needs to do special accounting. */ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, unsigned nid) { struct page *page; page = __alloc_pages(gfp, order, nid); /* skip NUMA_INTERLEAVE_HIT counter update if numa stats is disabled */ if (!static_branch_likely(&vm_numa_stat_key)) return page; if (page && page_to_nid(page) == nid) { preempt_disable(); __inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } return page; } /** * alloc_pages_vma - Allocate a page for a VMA. * * @gfp: * %GFP_USER user allocation. * %GFP_KERNEL kernel allocations, * %GFP_HIGHMEM highmem/user allocations, * %GFP_FS allocation should not call back into a file system. * %GFP_ATOMIC don't sleep. * * @order:Order of the GFP allocation. * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @node: Which node to prefer for allocation (modulo policy). * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. * When VMA is not NULL caller must read-lock the mmap_lock of the * mm_struct of the VMA to prevent it from going away. Should be used for * all allocations for pages that will be mapped into user space. Returns * NULL when no page can be allocated. */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, int node, bool hugepage) { struct mempolicy *pol; struct page *page; int preferred_nid; nodemask_t *nmask; pol = get_vma_policy(vma, addr); if (pol->mode == MPOL_INTERLEAVE) { unsigned nid; nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); goto out; } if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { int hpage_node = node; /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred * node) we only try to allocate from the current/preferred * node and don't fall back to other nodes, as the cost of * remote accesses would likely offset THP benefits. * * If the policy is interleave, or does not allow the current * node in its nodemask, we allocate the standard way. */ if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) hpage_node = pol->v.preferred_node; nmask = policy_nodemask(gfp, pol); if (!nmask || node_isset(hpage_node, *nmask)) { mpol_cond_put(pol); /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ page = __alloc_pages_node(hpage_node, gfp | __GFP_THISNODE | __GFP_NORETRY, order); /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ if (!page && (gfp & __GFP_DIRECT_RECLAIM)) page = __alloc_pages_nodemask(gfp, order, hpage_node, nmask); goto out; } } nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); mpol_cond_put(pol); out: return page; } EXPORT_SYMBOL(alloc_pages_vma); /** * alloc_pages_current - Allocate pages. * * @gfp: * %GFP_USER user allocation, * %GFP_KERNEL kernel allocation, * %GFP_HIGHMEM highmem allocation, * %GFP_FS don't call back into a file system. * %GFP_ATOMIC don't sleep. * @order: Power of two of allocation size in pages. 0 is a single page. * * Allocate a page from the kernel page pool. When not in * interrupt context and apply the current process NUMA policy. * Returns NULL when no page can be allocated. */ struct page *alloc_pages_current(gfp_t gfp, unsigned order) { struct mempolicy *pol = &default_policy; struct page *page; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); /* * No reference counting needed for current->mempolicy * nor system default_policy */ if (pol->mode == MPOL_INTERLEAVE) page = alloc_page_interleave(gfp, order, interleave_nodes(pol)); else page = __alloc_pages_nodemask(gfp, order, policy_node(gfp, pol, numa_node_id()), policy_nodemask(gfp, pol)); return page; } EXPORT_SYMBOL(alloc_pages_current); int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(vma_policy(src)); if (IS_ERR(pol)) return PTR_ERR(pol); dst->vm_policy = pol; return 0; } /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). * * current's mempolicy may be rebinded by the other task(the task that changes * cpuset's mems), so we needn't do rebind work for current task. */ /* Slow path of a mempolicy duplicate */ struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* task's mempolicy is protected by alloc_lock */ if (old == current->mempolicy) { task_lock(current); *new = *old; task_unlock(current); } else *new = *old; if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); mpol_rebind_policy(new, &mems); } atomic_set(&new->refcnt, 1); return new; } /* Slow path of a mempolicy comparison */ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) return false; if (a->mode != b->mode) return false; if (a->flags != b->flags) return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: return !!nodes_equal(a->v.nodes, b->v.nodes); case MPOL_PREFERRED: /* a's ->flags is the same as b's */ if (a->flags & MPOL_F_LOCAL) return true; return a->v.preferred_node == b->v.preferred_node; default: BUG(); return false; } } /* * Shared memory backing store policy support. * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ /* * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ static struct sp_node * sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end) { struct rb_node *n = sp->root.rb_node; while (n) { struct sp_node *p = rb_entry(n, struct sp_node, nd); if (start >= p->end) n = n->rb_right; else if (end <= p->start) n = n->rb_left; else break; } if (!n) return NULL; for (;;) { struct sp_node *w = NULL; struct rb_node *prev = rb_prev(n); if (!prev) break; w = rb_entry(prev, struct sp_node, nd); if (w->end <= start) break; n = prev; } return rb_entry(n, struct sp_node, nd); } /* * Insert a new shared policy into the list. Caller holds sp->lock for * writing. */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; struct rb_node *parent = NULL; struct sp_node *nd; while (*p) { parent = *p; nd = rb_entry(parent, struct sp_node, nd); if (new->start < nd->start) p = &(*p)->rb_left; else if (new->end > nd->end) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); pr_debug("inserting %lx-%lx: %d\n", new->start, new->end, new->policy ? new->policy->mode : 0); } /* Find shared policy intersecting idx */ struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx) { struct mempolicy *pol = NULL; struct sp_node *sn; if (!sp->root.rb_node) return NULL; read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } read_unlock(&sp->lock); return pol; } static void sp_free(struct sp_node *n) { mpol_put(n->policy); kmem_cache_free(sn_cache, n); } /** * mpol_misplaced - check whether current page node is valid in policy * * @page: page to be checked * @vma: vm area where page mapped * @addr: virtual address where page mapped * * Lookup current policy node id for vma,addr and "compare to" page's * node id. * * Returns: * -1 - not misplaced, page is in the right node * node - node id where the page should be * * Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. */ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol; struct zoneref *z; int curnid = page_to_nid(page); unsigned long pgoff; int thiscpu = raw_smp_processor_id(); int thisnid = cpu_to_node(thiscpu); int polnid = NUMA_NO_NODE; int ret = -1; pol = get_vma_policy(vma, addr); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: pgoff = vma->vm_pgoff; pgoff += (addr - vma->vm_start) >> PAGE_SHIFT; polnid = offset_il_node(pol, pgoff); break; case MPOL_PREFERRED: if (pol->flags & MPOL_F_LOCAL) polnid = numa_node_id(); else polnid = pol->v.preferred_node; break; case MPOL_BIND: /* * allows binding to multiple nodes. * use current page if in policy nodemask, * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ if (node_isset(curnid, pol->v.nodes)) goto out; z = first_zones_zonelist( node_zonelist(numa_node_id(), GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->v.nodes); polnid = zone_to_nid(z->zone); break; default: BUG(); } /* Migrate the page towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; if (!should_numa_migrate_memory(current, page, curnid, thiscpu)) goto out; } if (curnid != polnid) ret = polnid; out: mpol_cond_put(pol); return ret; } /* * Drop the (possibly final) reference to task->mempolicy. It needs to be * dropped after task->mempolicy is set to NULL so that any allocation done as * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed * policy. */ void mpol_put_task_policy(struct task_struct *task) { struct mempolicy *pol; task_lock(task); pol = task->mempolicy; task->mempolicy = NULL; task_unlock(task); mpol_put(pol); } static void sp_delete(struct shared_policy *sp, struct sp_node *n) { pr_debug("deleting %lx-l%lx\n", n->start, n->end); rb_erase(&n->nd, &sp->root); sp_free(n); } static void sp_node_init(struct sp_node *node, unsigned long start, unsigned long end, struct mempolicy *pol) { node->start = start; node->end = end; node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { struct sp_node *n; struct mempolicy *newpol; n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n); return NULL; } newpol->flags |= MPOL_F_SHARED; sp_node_init(n, start, end, newpol); return n; } /* Replace a policy range. */ static int shared_policy_replace(struct shared_policy *sp, unsigned long start, unsigned long end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; struct mempolicy *mpol_new = NULL; int ret = 0; restart: write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { struct rb_node *next = rb_next(&n->nd); if (n->start >= start) { if (n->end <= end) sp_delete(sp, n); else n->start = end; } else { /* Old policy spanning whole new range. */ if (n->end > end) { if (!n_new) goto alloc_new; *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); sp_node_init(n_new, end, n->end, mpol_new); n->end = start; sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; } else n->end = start; } if (!next) break; n = rb_entry(next, struct sp_node, nd); } if (new) sp_insert(sp, new); write_unlock(&sp->lock); ret = 0; err_out: if (mpol_new) mpol_put(mpol_new); if (n_new) kmem_cache_free(sn_cache, n_new); return ret; alloc_new: write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) goto err_out; mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; atomic_set(&mpol_new->refcnt, 1); goto restart; } /** * mpol_shared_policy_init - initialize shared policy for inode * @sp: pointer to inode shared policy * @mpol: struct mempolicy to install * * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ rwlock_init(&sp->lock); if (mpol) { struct vm_area_struct pvma; struct mempolicy *new; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; /* contextualize the tmpfs mount point mempolicy */ new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(new)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); ret = mpol_set_nodemask(new, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) goto put_new; /* Create pseudo-vma that contains just the policy */ vma_init(&pvma, NULL); pvma.vm_end = TASK_SIZE; /* policy covers entire file */ mpol_set_shared_policy(sp, &pvma, new); /* adds ref */ put_new: mpol_put(new); /* drop initial ref */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } int mpol_set_shared_policy(struct shared_policy *info, struct vm_area_struct *vma, struct mempolicy *npol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n", vma->vm_pgoff, sz, npol ? npol->mode : -1, npol ? npol->flags : -1, npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE); if (npol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); if (!new) return -ENOMEM; } err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new); if (err && new) sp_free(new); return err; } /* Free a backing policy store on inode delete. */ void mpol_free_shared_policy(struct shared_policy *p) { struct sp_node *n; struct rb_node *next; if (!p->root.rb_node) return; write_lock(&p->lock); next = rb_first(&p->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(p, n); } write_unlock(&p->lock); } #ifdef CONFIG_NUMA_BALANCING static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { bool numabalancing_default = false; if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } static int __init setup_numabalancing(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "enable")) { numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { numabalancing_override = -1; ret = 1; } out: if (!ret) pr_warn("Unable to parse numa_balancing=\n"); return ret; } __setup("numa_balancing=", setup_numabalancing); #else static inline void __init check_numabalancing_enable(void) { } #endif /* CONFIG_NUMA_BALANCING */ /* assumes fs == KERNEL_DS */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; unsigned long largest = 0; int nid, prefer = 0; policy_cache = kmem_cache_create("numa_policy", sizeof(struct mempolicy), 0, SLAB_PANIC, NULL); sn_cache = kmem_cache_create("shared_policy_node", sizeof(struct sp_node), 0, SLAB_PANIC, NULL); for_each_node(nid) { preferred_node_policy[nid] = (struct mempolicy) { .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, .v = { .preferred_node = nid, }, }; } /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ if (largest < total_pages) { largest = total_pages; prefer = nid; } /* Interleave this node? */ if ((total_pages << PAGE_SHIFT) >= (16 << 20)) node_set(nid, interleave_nodes); } /* All too small, use the largest */ if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } /* * Parse and format mempolicy from/to strings */ /* * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag. */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", [MPOL_LOCAL] = "local", }; #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. * @str: string containing mempolicy to parse * @mpol: pointer to struct mempolicy pointer, returned on success. * * Format of input: * <mode>[=<flags>][:<nodelist>] * * On success, returns 0, else 1 */ int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); int err = 1, mode; if (flags) *flags++ = '\0'; /* terminate mode string */ if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; switch (mode) { case MPOL_PREFERRED: /* * Insist on a nodelist of one node only, although later * we use first_node(nodes) to grab a single node, so here * nodelist (or nodes) cannot be empty. */ if (nodelist) { char *rest = nodelist; while (isdigit(*rest)) rest++; if (*rest) goto out; if (nodes_empty(nodes)) goto out; } break; case MPOL_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ if (!nodelist) nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* * Don't allow a nodelist; mpol_new() checks flags */ if (nodelist) goto out; mode = MPOL_PREFERRED; break; case MPOL_DEFAULT: /* * Insist on a empty nodelist */ if (!nodelist) err = 0; goto out; case MPOL_BIND: /* * Insist on a nodelist */ if (!nodelist) goto out; } mode_flags = 0; if (flags) { /* * Currently, we only support two mutually exclusive * mode flags. */ if (!strcmp(flags, "static")) mode_flags |= MPOL_F_STATIC_NODES; else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) goto out; /* * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ if (mode != MPOL_PREFERRED) new->v.nodes = nodes; else if (nodelist) new->v.preferred_node = first_node(nodes); else new->flags |= MPOL_F_LOCAL; /* * Save nodes for contextualization: this will be used to "clone" * the mempolicy in a specific context [cpuset] at a later time. */ new->w.user_nodemask = nodes; err = 0; out: /* Restore string for error message */ if (nodelist) *--nodelist = ':'; if (flags) *--flags = '='; if (!err) *mpol = new; return err; } #endif /* CONFIG_TMPFS */ /** * mpol_to_str - format a mempolicy structure for printing * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the * longest flag, "relative", and to display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; nodemask_t nodes = NODE_MASK_NONE; unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) { mode = pol->mode; flags = pol->flags; } switch (mode) { case MPOL_DEFAULT: break; case MPOL_PREFERRED: if (flags & MPOL_F_LOCAL) mode = MPOL_LOCAL; else node_set(pol->v.preferred_node, nodes); break; case MPOL_BIND: case MPOL_INTERLEAVE: nodes = pol->v.nodes; break; default: WARN_ON_ONCE(1); snprintf(p, maxlen, "unknown"); return; } p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { p += snprintf(p, buffer + maxlen - p, "="); /* * Currently, the only defined flags are mutually exclusive */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_RWSEM_H #define _LINUX_PERCPU_RWSEM_H #include <linux/atomic.h> #include <linux/percpu.h> #include <linux/rcuwait.h> #include <linux/wait.h> #include <linux/rcu_sync.h> #include <linux/lockdep.h> struct percpu_rw_semaphore { struct rcu_sync rss; unsigned int __percpu *read_count; struct rcuwait writer; wait_queue_head_t waiters; atomic_t block; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #ifdef CONFIG_DEBUG_LOCK_ALLOC #define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname }, #else #define __PERCPU_RWSEM_DEP_MAP_INIT(lockname) #endif #define __DEFINE_PERCPU_RWSEM(name, is_static) \ static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name); \ is_static struct percpu_rw_semaphore name = { \ .rss = __RCU_SYNC_INITIALIZER(name.rss), \ .read_count = &__percpu_rwsem_rc_##name, \ .writer = __RCUWAIT_INITIALIZER(name.writer), \ .waiters = __WAIT_QUEUE_HEAD_INITIALIZER(name.waiters), \ .block = ATOMIC_INIT(0), \ __PERCPU_RWSEM_DEP_MAP_INIT(name) \ } #define DEFINE_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, /* not static */) #define DEFINE_STATIC_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, static) extern bool __percpu_down_read(struct percpu_rw_semaphore *, bool); static inline void percpu_down_read(struct percpu_rw_semaphore *sem) { might_sleep(); rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_); preempt_disable(); /* * We are in an RCU-sched read-side critical section, so the writer * cannot both change sem->state from readers_fast and start checking * counters while we are here. So if we see !sem->state, we know that * the writer won't be checking until we're past the preempt_enable() * and that once the synchronize_rcu() is done, the writer will see * anything we did within this RCU-sched read-size critical section. */ if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else __percpu_down_read(sem, false); /* Unconditional memory barrier */ /* * The preempt_enable() prevents the compiler from * bleeding the critical section out. */ preempt_enable(); } static inline bool percpu_down_read_trylock(struct percpu_rw_semaphore *sem) { bool ret = true; preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) this_cpu_inc(*sem->read_count); else ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ preempt_enable(); /* * The barrier() from preempt_enable() prevents the compiler from * bleeding the critical section out. */ if (ret) rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_); return ret; } static inline void percpu_up_read(struct percpu_rw_semaphore *sem) { rwsem_release(&sem->dep_map, _RET_IP_); preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) { this_cpu_dec(*sem->read_count); } else { /* * slowpath; reader will only ever wake a single blocked * writer. */ smp_mb(); /* B matches C */ /* * In other words, if they see our decrement (presumably to * aggregate zero, as that is the only time it matters) they * will also see our critical section. */ this_cpu_dec(*sem->read_count); rcuwait_wake_up(&sem->writer); } preempt_enable(); } extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); extern int __percpu_init_rwsem(struct percpu_rw_semaphore *, const char *, struct lock_class_key *); extern void percpu_free_rwsem(struct percpu_rw_semaphore *); #define percpu_init_rwsem(sem) \ ({ \ static struct lock_class_key rwsem_key; \ __percpu_init_rwsem(sem, #sem, &rwsem_key); \ }) #define percpu_rwsem_is_held(sem) lockdep_is_held(sem) #define percpu_rwsem_assert_held(sem) lockdep_assert_held(sem) static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_release(&sem->dep_map, ip); } static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_acquire(&sem->dep_map, 0, 1, read, 1, NULL, ip); } #endif |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_CPUFEATURE_H #define _ASM_X86_CPUFEATURE_H #include <asm/processor.h> #if defined(__KERNEL__) && !defined(__ASSEMBLY__) #include <asm/asm.h> #include <linux/bitops.h> #include <asm/alternative.h> enum cpuid_leafs { CPUID_1_EDX = 0, CPUID_8000_0001_EDX, CPUID_8086_0001_EDX, CPUID_LNX_1, CPUID_1_ECX, CPUID_C000_0001_EDX, CPUID_8000_0001_ECX, CPUID_LNX_2, CPUID_LNX_3, CPUID_7_0_EBX, CPUID_D_1_EAX, CPUID_LNX_4, CPUID_7_1_EAX, CPUID_8000_0008_EBX, CPUID_6_EAX, CPUID_8000_000A_EDX, CPUID_7_ECX, CPUID_8000_0007_EBX, CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, CPUID_LNX_5, CPUID_8000_0021_ECX, NR_CPUID_WORDS, }; #ifdef CONFIG_X86_FEATURE_NAMES extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; #define X86_CAP_FMT "%s" #define x86_cap_flag(flag) x86_cap_flags[flag] #else #define X86_CAP_FMT "%d:%d" #define x86_cap_flag(flag) ((flag) >> 5), ((flag) & 31) #endif /* * In order to save room, we index into this array by doing * X86_BUG_<name> - NCAPINTS*32. */ extern const char * const x86_bug_flags[NBUGINTS*32]; #define test_cpu_cap(c, bit) \ arch_test_bit(bit, (unsigned long *)((c)->x86_capability)) /* * There are 32 bits/features in each mask word. The high bits * (selected with (bit>>5) give us the word number and the low 5 * bits give us the bit/feature number inside the word. * (1UL<<((bit)&31) gives us a mask for the feature_bit so we can * see if it is set in the mask word. */ #define CHECK_BIT_IN_MASK_WORD(maskname, word, bit) \ (((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word )) /* * {REQUIRED,DISABLED}_MASK_CHECK below may seem duplicated with the * following BUILD_BUG_ON_ZERO() check but when NCAPINTS gets changed, all * header macros which use NCAPINTS need to be changed. The duplicated macro * use causes the compiler to issue errors for all headers so that all usage * sites can be corrected. */ #define REQUIRED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 0, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 1, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 2, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 3, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 4, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 5, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 6, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 7, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 8, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 9, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 10, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 11, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 12, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 13, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 14, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \ REQUIRED_MASK_CHECK || \ BUILD_BUG_ON_ZERO(NCAPINTS != 23)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 1, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 2, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 3, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 4, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 5, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 6, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 7, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 8, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 9, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 10, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 11, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 12, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 13, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 14, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \ DISABLED_MASK_CHECK || \ BUILD_BUG_ON_ZERO(NCAPINTS != 23)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ test_cpu_cap(c, bit)) #define this_cpu_has(bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ x86_this_cpu_test_bit(bit, \ (unsigned long __percpu *)&cpu_info.x86_capability)) /* * This macro is for detection of features which need kernel * infrastructure to be used. It may *not* directly test the CPU * itself. Use the cpu_has() family if you want true runtime * testing of CPU features, like in hypervisor code where you are * supporting a possible guest feature where host support for it * is not relevant. */ #define cpu_feature_enabled(bit) \ (__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : static_cpu_has(bit)) #define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) #define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability)) extern void setup_clear_cpu_cap(unsigned int bit); extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); #define setup_force_cpu_cap(bit) do { \ set_cpu_cap(&boot_cpu_data, bit); \ set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) #if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO) /* * Workaround for the sake of BPF compilation which utilizes kernel * headers, but clang does not support ASM GOTO and fails the build. */ #ifndef __BPF_TRACING__ #warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments" #endif #define static_cpu_has(bit) boot_cpu_has(bit) #else /* * Static testing of CPU features. Used the same as boot_cpu_has(). It * statically patches the target code for additional performance. Use * static_cpu_has() only in fast paths, where every cycle counts. Which * means that the boot_cpu_has() variant is already fast enough for the * majority of cases and you should stick to using it as it is generally * only two instructions: a RIP-relative MOV and a TEST. */ static __always_inline bool _static_cpu_has(u16 bit) { asm_volatile_goto( ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]") ".section .altinstr_aux,\"ax\"\n" "6:\n" " testb %[bitnum],%[cap_byte]\n" " jnz %l[t_yes]\n" " jmp %l[t_no]\n" ".previous\n" : : [feature] "i" (bit), [bitnum] "i" (1 << (bit & 7)), [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) : : t_yes, t_no); t_yes: return true; t_no: return false; } #define static_cpu_has(bit) \ ( \ __builtin_constant_p(boot_cpu_has(bit)) ? \ boot_cpu_has(bit) : \ _static_cpu_has(bit) \ ) #endif #define cpu_has_bug(c, bit) cpu_has(c, (bit)) #define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) #define clear_cpu_bug(c, bit) clear_cpu_cap(c, (bit)) #define static_cpu_has_bug(bit) static_cpu_has((bit)) #define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit)) #define boot_cpu_set_bug(bit) set_cpu_cap(&boot_cpu_data, (bit)) #define MAX_CPU_FEATURES (NCAPINTS * 32) #define cpu_have_feature boot_cpu_has #define CPU_FEATURE_TYPEFMT "x86,ven%04Xfam%04Xmod%04X" #define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \ boot_cpu_data.x86_model #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */ #endif /* _ASM_X86_CPUFEATURE_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1995 Linus Torvalds * Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs. * Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar */ #include <linux/sched.h> /* test_thread_flag(), ... */ #include <linux/sched/task_stack.h> /* task_stack_*(), ... */ #include <linux/kdebug.h> /* oops_begin/end, ... */ #include <linux/extable.h> /* search_exception_tables */ #include <linux/memblock.h> /* max_low_pfn */ #include <linux/kprobes.h> /* NOKPROBE_SYMBOL, ... */ #include <linux/mmiotrace.h> /* kmmio_handler, ... */ #include <linux/perf_event.h> /* perf_sw_event */ #include <linux/hugetlb.h> /* hstate_index_to_shift */ #include <linux/prefetch.h> /* prefetchw */ #include <linux/context_tracking.h> /* exception_enter(), ... */ #include <linux/uaccess.h> /* faulthandler_disabled() */ #include <linux/efi.h> /* efi_recover_from_page_fault()*/ #include <linux/mm_types.h> #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/fixmap.h> /* VSYSCALL_ADDR */ #include <asm/vsyscall.h> /* emulate_vsyscall */ #include <asm/vm86.h> /* struct vm86 */ #include <asm/mmu_context.h> /* vma_pkey() */ #include <asm/efi.h> /* efi_recover_from_page_fault()*/ #include <asm/desc.h> /* store_idt(), ... */ #include <asm/cpu_entry_area.h> /* exception stack */ #include <asm/pgtable_areas.h> /* VMALLOC_START, ... */ #include <asm/kvm_para.h> /* kvm_handle_async_pf */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> /* * Returns 0 if mmiotrace is disabled, or if the fault is not * handled by mmiotrace: */ static nokprobe_inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) { if (unlikely(is_kmmio_active())) if (kmmio_handler(regs, addr) == 1) return -1; return 0; } /* * Prefetch quirks: * * 32-bit mode: * * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch. * Check that here and ignore it. This is AMD erratum #91. * * 64-bit mode: * * Sometimes the CPU reports invalid exceptions on prefetch. * Check that here and ignore it. * * Opcode checker based on code by Richard Brunner. */ static inline int check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr, unsigned char opcode, int *prefetch) { unsigned char instr_hi = opcode & 0xf0; unsigned char instr_lo = opcode & 0x0f; switch (instr_hi) { case 0x20: case 0x30: /* * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes. * In X86_64 long mode, the CPU will signal invalid * opcode if some of these prefixes are present so * X86_64 will never get here anyway */ return ((instr_lo & 7) == 0x6); #ifdef CONFIG_X86_64 case 0x40: /* * In 64-bit mode 0x40..0x4F are valid REX prefixes */ return (!user_mode(regs) || user_64bit_mode(regs)); #endif case 0x60: /* 0x64 thru 0x67 are valid prefixes in all modes. */ return (instr_lo & 0xC) == 0x4; case 0xF0: /* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */ return !instr_lo || (instr_lo>>1) == 1; case 0x00: /* Prefetch instruction is 0x0F0D or 0x0F18 */ if (get_kernel_nofault(opcode, instr)) return 0; *prefetch = (instr_lo == 0xF) && (opcode == 0x0D || opcode == 0x18); return 0; default: return 0; } } static int is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) { unsigned char *max_instr; unsigned char *instr; int prefetch = 0; /* * If it was a exec (instruction fetch) fault on NX page, then * do not ignore the fault: */ if (error_code & X86_PF_INSTR) return 0; instr = (void *)convert_ip_to_linear(current, regs); max_instr = instr + 15; /* * This code has historically always bailed out if IP points to a * not-present page (e.g. due to a race). No one has ever * complained about this. */ pagefault_disable(); while (instr < max_instr) { unsigned char opcode; if (user_mode(regs)) { if (get_user(opcode, instr)) break; } else { if (get_kernel_nofault(opcode, instr)) break; } instr++; if (!check_prefetch_opcode(regs, instr, opcode, &prefetch)) break; } pagefault_enable(); return prefetch; } DEFINE_SPINLOCK(pgd_lock); LIST_HEAD(pgd_list); #ifdef CONFIG_X86_32 static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) { unsigned index = pgd_index(address); pgd_t *pgd_k; p4d_t *p4d, *p4d_k; pud_t *pud, *pud_k; pmd_t *pmd, *pmd_k; pgd += index; pgd_k = init_mm.pgd + index; if (!pgd_present(*pgd_k)) return NULL; /* * set_pgd(pgd, *pgd_k); here would be useless on PAE * and redundant with the set_pmd() on non-PAE. As would * set_p4d/set_pud. */ p4d = p4d_offset(pgd, address); p4d_k = p4d_offset(pgd_k, address); if (!p4d_present(*p4d_k)) return NULL; pud = pud_offset(p4d, address); pud_k = pud_offset(p4d_k, address); if (!pud_present(*pud_k)) return NULL; pmd = pmd_offset(pud, address); pmd_k = pmd_offset(pud_k, address); if (pmd_present(*pmd) != pmd_present(*pmd_k)) set_pmd(pmd, *pmd_k); if (!pmd_present(*pmd_k)) return NULL; else BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k)); return pmd_k; } /* * Handle a fault on the vmalloc or module mapping area * * This is needed because there is a race condition between the time * when the vmalloc mapping code updates the PMD to the point in time * where it synchronizes this update with the other page-tables in the * system. * * In this race window another thread/CPU can map an area on the same * PMD, finds it already present and does not synchronize it with the * rest of the system yet. As a result v[mz]alloc might return areas * which are not mapped in every page-table in the system, causing an * unhandled page-fault when they are accessed. */ static noinline int vmalloc_fault(unsigned long address) { unsigned long pgd_paddr; pmd_t *pmd_k; pte_t *pte_k; /* Make sure we are in vmalloc area: */ if (!(address >= VMALLOC_START && address < VMALLOC_END)) return -1; /* * Synchronize this task's top level page-table * with the 'reference' page table. * * Do _not_ use "current" here. We might be inside * an interrupt in the middle of a task switch.. */ pgd_paddr = read_cr3_pa(); pmd_k = vmalloc_sync_one(__va(pgd_paddr), address); if (!pmd_k) return -1; if (pmd_large(*pmd_k)) return 0; pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; return 0; } NOKPROBE_SYMBOL(vmalloc_fault); void arch_sync_kernel_mappings(unsigned long start, unsigned long end) { unsigned long addr; for (addr = start & PMD_MASK; addr >= TASK_SIZE_MAX && addr < VMALLOC_END; addr += PMD_SIZE) { struct page *page; spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { spinlock_t *pgt_lock; /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); vmalloc_sync_one(page_address(page), addr); spin_unlock(pgt_lock); } spin_unlock(&pgd_lock); } } /* * Did it hit the DOS screen memory VA from vm86 mode? */ static inline void check_v8086_mode(struct pt_regs *regs, unsigned long address, struct task_struct *tsk) { #ifdef CONFIG_VM86 unsigned long bit; if (!v8086_mode(regs) || !tsk->thread.vm86) return; bit = (address - 0xA0000) >> PAGE_SHIFT; if (bit < 32) tsk->thread.vm86->screen_bitmap |= 1 << bit; #endif } static bool low_pfn(unsigned long pfn) { return pfn < max_low_pfn; } static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = &base[pgd_index(address)]; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; #ifdef CONFIG_X86_PAE pr_info("*pdpt = %016Lx ", pgd_val(*pgd)); if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd)) goto out; #define pr_pde pr_cont #else #define pr_pde pr_info #endif p4d = p4d_offset(pgd, address); pud = pud_offset(p4d, address); pmd = pmd_offset(pud, address); pr_pde("*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd)); #undef pr_pde /* * We must not directly access the pte in the highpte * case if the page table is located in highmem. * And let's rather not kmap-atomic the pte, just in case * it's allocated already: */ if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_large(*pmd)) goto out; pte = pte_offset_kernel(pmd, address); pr_cont("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte)); out: pr_cont("\n"); } #else /* CONFIG_X86_64: */ #ifdef CONFIG_CPU_SUP_AMD static const char errata93_warning[] = KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n" "******* Working around it, but it may cause SEGVs or burn power.\n" "******* Please consider a BIOS update.\n" "******* Disabling USB legacy in the BIOS may also help.\n"; #endif /* * No vm86 mode in 64-bit mode: */ static inline void check_v8086_mode(struct pt_regs *regs, unsigned long address, struct task_struct *tsk) { } static int bad_address(void *p) { unsigned long dummy; return get_kernel_nofault(dummy, (unsigned long *)p); } static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = base + pgd_index(address); p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; if (bad_address(pgd)) goto bad; pr_info("PGD %lx ", pgd_val(*pgd)); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (bad_address(p4d)) goto bad; pr_cont("P4D %lx ", p4d_val(*p4d)); if (!p4d_present(*p4d) || p4d_large(*p4d)) goto out; pud = pud_offset(p4d, address); if (bad_address(pud)) goto bad; pr_cont("PUD %lx ", pud_val(*pud)); if (!pud_present(*pud) || pud_large(*pud)) goto out; pmd = pmd_offset(pud, address); if (bad_address(pmd)) goto bad; pr_cont("PMD %lx ", pmd_val(*pmd)); if (!pmd_present(*pmd) || pmd_large(*pmd)) goto out; pte = pte_offset_kernel(pmd, address); if (bad_address(pte)) goto bad; pr_cont("PTE %lx", pte_val(*pte)); out: pr_cont("\n"); return; bad: pr_info("BAD\n"); } #endif /* CONFIG_X86_64 */ /* * Workaround for K8 erratum #93 & buggy BIOS. * * BIOS SMM functions are required to use a specific workaround * to avoid corruption of the 64bit RIP register on C stepping K8. * * A lot of BIOS that didn't get tested properly miss this. * * The OS sees this as a page fault with the upper 32bits of RIP cleared. * Try to work around it here. * * Note we only handle faults in kernel here. * Does nothing on 32-bit. */ static int is_errata93(struct pt_regs *regs, unsigned long address) { #if defined(CONFIG_X86_64) && defined(CONFIG_CPU_SUP_AMD) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD || boot_cpu_data.x86 != 0xf) return 0; if (address != regs->ip) return 0; if ((address >> 32) != 0) return 0; address |= 0xffffffffUL << 32; if ((address >= (u64)_stext && address <= (u64)_etext) || (address >= MODULES_VADDR && address <= MODULES_END)) { printk_once(errata93_warning); regs->ip = address; return 1; } #endif return 0; } /* * Work around K8 erratum #100 K8 in compat mode occasionally jumps * to illegal addresses >4GB. * * We catch this in the page fault handler because these addresses * are not reachable. Just detect this case and return. Any code * segment in LDT is compatibility mode. */ static int is_errata100(struct pt_regs *regs, unsigned long address) { #ifdef CONFIG_X86_64 if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && (address >> 32)) return 1; #endif return 0; } /* Pentium F0 0F C7 C8 bug workaround: */ static int is_f00f_bug(struct pt_regs *regs, unsigned long address) { #ifdef CONFIG_X86_F00F_BUG if (boot_cpu_has_bug(X86_BUG_F00F) && idt_is_f00f_address(address)) { handle_invalid_op(regs); return 1; } #endif return 0; } static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index) { u32 offset = (index >> 3) * sizeof(struct desc_struct); unsigned long addr; struct ldttss_desc desc; if (index == 0) { pr_alert("%s: NULL\n", name); return; } if (offset + sizeof(struct ldttss_desc) >= gdt->size) { pr_alert("%s: 0x%hx -- out of bounds\n", name, index); return; } if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset), sizeof(struct ldttss_desc))) { pr_alert("%s: 0x%hx -- GDT entry is not readable\n", name, index); return; } addr = desc.base0 | (desc.base1 << 16) | ((unsigned long)desc.base2 << 24); #ifdef CONFIG_X86_64 addr |= ((u64)desc.base3 << 32); #endif pr_alert("%s: 0x%hx -- base=0x%lx limit=0x%x\n", name, index, addr, (desc.limit0 | (desc.limit1 << 16))); } static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address) { if (!oops_may_print()) return; if (error_code & X86_PF_INSTR) { unsigned int level; pgd_t *pgd; pte_t *pte; pgd = __va(read_cr3_pa()); pgd += pgd_index(address); pte = lookup_address_in_pgd(pgd, address, &level); if (pte && pte_present(*pte) && !pte_exec(*pte)) pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n", from_kuid(&init_user_ns, current_uid())); if (pte && pte_present(*pte) && pte_exec(*pte) && (pgd_flags(*pgd) & _PAGE_USER) && (__read_cr4() & X86_CR4_SMEP)) pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n", from_kuid(&init_user_ns, current_uid())); } if (address < PAGE_SIZE && !user_mode(regs)) pr_alert("BUG: kernel NULL pointer dereference, address: %px\n", (void *)address); else pr_alert("BUG: unable to handle page fault for address: %px\n", (void *)address); pr_alert("#PF: %s %s in %s mode\n", (error_code & X86_PF_USER) ? "user" : "supervisor", (error_code & X86_PF_INSTR) ? "instruction fetch" : (error_code & X86_PF_WRITE) ? "write access" : "read access", user_mode(regs) ? "user" : "kernel"); pr_alert("#PF: error_code(0x%04lx) - %s\n", error_code, !(error_code & X86_PF_PROT) ? "not-present page" : (error_code & X86_PF_RSVD) ? "reserved bit violation" : (error_code & X86_PF_PK) ? "protection keys violation" : "permissions violation"); if (!(error_code & X86_PF_USER) && user_mode(regs)) { struct desc_ptr idt, gdt; u16 ldtr, tr; /* * This can happen for quite a few reasons. The more obvious * ones are faults accessing the GDT, or LDT. Perhaps * surprisingly, if the CPU tries to deliver a benign or * contributory exception from user code and gets a page fault * during delivery, the page fault can be delivered as though * it originated directly from user code. This could happen * due to wrong permissions on the IDT, GDT, LDT, TSS, or * kernel or IST stack. */ store_idt(&idt); /* Usable even on Xen PV -- it's just slow. */ native_store_gdt(&gdt); pr_alert("IDT: 0x%lx (limit=0x%hx) GDT: 0x%lx (limit=0x%hx)\n", idt.address, idt.size, gdt.address, gdt.size); store_ldt(ldtr); show_ldttss(&gdt, "LDTR", ldtr); store_tr(tr); show_ldttss(&gdt, "TR", tr); } dump_pagetable(address); } static noinline void pgtable_bad(struct pt_regs *regs, unsigned long error_code, unsigned long address) { struct task_struct *tsk; unsigned long flags; int sig; flags = oops_begin(); tsk = current; sig = SIGKILL; printk(KERN_ALERT "%s: Corrupted page table at address %lx\n", tsk->comm, address); dump_pagetable(address); if (__die("Bad pagetable", regs, error_code)) sig = 0; oops_end(flags, regs, sig); } static void set_signal_archinfo(unsigned long address, unsigned long error_code) { struct task_struct *tsk = current; /* * To avoid leaking information about the kernel page * table layout, pretend that user-mode accesses to * kernel addresses are always protection faults. * * NB: This means that failed vsyscalls with vsyscall=none * will have the PROT bit. This doesn't leak any * information and does not appear to cause any problems. */ if (address >= TASK_SIZE_MAX) error_code |= X86_PF_PROT; tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code | X86_PF_USER; tsk->thread.cr2 = address; } static noinline void no_context(struct pt_regs *regs, unsigned long error_code, unsigned long address, int signal, int si_code) { struct task_struct *tsk = current; unsigned long flags; int sig; if (user_mode(regs)) { /* * This is an implicit supervisor-mode access from user * mode. Bypass all the kernel-mode recovery code and just * OOPS. */ goto oops; } /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) return; #ifdef CONFIG_VMAP_STACK /* * Stack overflow? During boot, we can fault near the initial * stack in the direct map, but that's not an overflow -- check * that we're in vmalloc space to avoid this. */ if (is_vmalloc_addr((void *)address) && (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) || address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) { unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *); /* * We're likely to be running with very little stack space * left. It's plausible that we'd hit this condition but * double-fault even before we get this far, in which case * we're fine: the double-fault handler will deal with it. * * We don't want to make it all the way into the oops code * and then double-fault, though, because we're likely to * break the console driver and lose most of the stack dump. */ asm volatile ("movq %[stack], %%rsp\n\t" "call handle_stack_overflow\n\t" "1: jmp 1b" : ASM_CALL_CONSTRAINT : "D" ("kernel stack overflow (page fault)"), "S" (regs), "d" (address), [stack] "rm" (stack)); unreachable(); } #endif /* * 32-bit: * * Valid to do another page fault here, because if this fault * had been triggered by is_prefetch fixup_exception would have * handled it. * * 64-bit: * * Hall of shame of CPU/BIOS bugs. */ if (is_prefetch(regs, error_code, address)) return; if (is_errata93(regs, address)) return; /* * Buggy firmware could access regions which might page fault, try to * recover from such faults. */ if (IS_ENABLED(CONFIG_EFI)) efi_recover_from_page_fault(address); oops: /* * Oops. The kernel tried to access some bad page. We'll have to * terminate things with extreme prejudice: */ flags = oops_begin(); show_fault_oops(regs, error_code, address); if (task_stack_end_corrupted(tsk)) printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); sig = SIGKILL; if (__die("Oops", regs, error_code)) sig = 0; /* Executive summary in case the body of the oops scrolled away */ printk(KERN_DEFAULT "CR2: %016lx\n", address); oops_end(flags, regs, sig); } /* * Print out info about fatal segfaults, if the show_unhandled_signals * sysctl is set: */ static inline void show_signal_msg(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct task_struct *tsk) { const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG; if (!unhandled_signal(tsk, SIGSEGV)) return; if (!printk_ratelimit()) return; printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx", loglvl, tsk->comm, task_pid_nr(tsk), address, (void *)regs->ip, (void *)regs->sp, error_code); print_vma_addr(KERN_CONT " in ", regs->ip); printk(KERN_CONT "\n"); show_opcodes(regs, loglvl); } static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) { struct task_struct *tsk = current; /* User mode accesses just cause a SIGSEGV */ if (user_mode(regs) && (error_code & X86_PF_USER)) { /* * It's possible to have interrupts off here: */ local_irq_enable(); /* * Valid to do another page fault here because this one came * from user space: */ if (is_prefetch(regs, error_code, address)) return; if (is_errata100(regs, address)) return; /* * To avoid leaking information about the kernel page table * layout, pretend that user-mode accesses to kernel addresses * are always protection faults. */ if (address >= TASK_SIZE_MAX) error_code |= X86_PF_PROT; if (likely(show_unhandled_signals)) show_signal_msg(regs, error_code, address, tsk); set_signal_archinfo(address, error_code); if (si_code == SEGV_PKUERR) force_sig_pkuerr((void __user *)address, pkey); force_sig_fault(SIGSEGV, si_code, (void __user *)address); local_irq_disable(); return; } if (is_f00f_bug(regs, address)) return; no_context(regs, error_code, address, SIGSEGV, si_code); } static noinline void bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address) { __bad_area_nosemaphore(regs, error_code, address, 0, SEGV_MAPERR); } static void __bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) { struct mm_struct *mm = current->mm; /* * Something tried to access memory that isn't in our memory map.. * Fix it, but check if it's kernel or user first.. */ mmap_read_unlock(mm); __bad_area_nosemaphore(regs, error_code, address, pkey, si_code); } static noinline void bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address) { __bad_area(regs, error_code, address, 0, SEGV_MAPERR); } static inline bool bad_area_access_from_pkeys(unsigned long error_code, struct vm_area_struct *vma) { /* This code is always called on the current mm */ bool foreign = false; if (!boot_cpu_has(X86_FEATURE_OSPKE)) return false; if (error_code & X86_PF_PK) return true; /* this checks permission keys on the VMA: */ if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), (error_code & X86_PF_INSTR), foreign)) return true; return false; } static noinline void bad_area_access_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct vm_area_struct *vma) { /* * This OSPKE check is not strictly necessary at runtime. * But, doing it this way allows compiler optimizations * if pkeys are compiled out. */ if (bad_area_access_from_pkeys(error_code, vma)) { /* * A protection key fault means that the PKRU value did not allow * access to some PTE. Userspace can figure out what PKRU was * from the XSAVE state. This function captures the pkey from * the vma and passes it to userspace so userspace can discover * which protection key was set on the PTE. * * If we get here, we know that the hardware signaled a X86_PF_PK * fault and that there was a VMA once we got in the fault * handler. It does *not* guarantee that the VMA we find here * was the one that we faulted on. * * 1. T1 : mprotect_key(foo, PAGE_SIZE, pkey=4); * 2. T1 : set PKRU to deny access to pkey=4, touches page * 3. T1 : faults... * 4. T2: mprotect_key(foo, PAGE_SIZE, pkey=5); * 5. T1 : enters fault handler, takes mmap_lock, etc... * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ u32 pkey = vma_pkey(vma); __bad_area(regs, error_code, address, pkey, SEGV_PKUERR); } else { __bad_area(regs, error_code, address, 0, SEGV_ACCERR); } } static void do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, vm_fault_t fault) { /* Kernel mode? Handle exceptions or die: */ if (!(error_code & X86_PF_USER)) { no_context(regs, error_code, address, SIGBUS, BUS_ADRERR); return; } /* User-space => ok to do another page fault: */ if (is_prefetch(regs, error_code, address)) return; set_signal_archinfo(address, error_code); #ifdef CONFIG_MEMORY_FAILURE if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) { struct task_struct *tsk = current; unsigned lsb = 0; pr_err( "MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n", tsk->comm, tsk->pid, address); if (fault & VM_FAULT_HWPOISON_LARGE) lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); if (fault & VM_FAULT_HWPOISON) lsb = PAGE_SHIFT; force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb); return; } #endif force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address); } static noinline void mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, vm_fault_t fault) { if (fatal_signal_pending(current) && !(error_code & X86_PF_USER)) { no_context(regs, error_code, address, 0, 0); return; } if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ if (!(error_code & X86_PF_USER)) { no_context(regs, error_code, address, SIGSEGV, SEGV_MAPERR); return; } /* * We ran out of memory, call the OOM killer, and return the * userspace (which will retry the fault, or kill us if we got * oom-killed): */ pagefault_out_of_memory(); } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) do_sigbus(regs, error_code, address, fault); else if (fault & VM_FAULT_SIGSEGV) bad_area_nosemaphore(regs, error_code, address); else BUG(); } } static int spurious_kernel_fault_check(unsigned long error_code, pte_t *pte) { if ((error_code & X86_PF_WRITE) && !pte_write(*pte)) return 0; if ((error_code & X86_PF_INSTR) && !pte_exec(*pte)) return 0; return 1; } /* * Handle a spurious fault caused by a stale TLB entry. * * This allows us to lazily refresh the TLB when increasing the * permissions of a kernel page (RO -> RW or NX -> X). Doing it * eagerly is very expensive since that implies doing a full * cross-processor TLB flush, even if no stale TLB entries exist * on other processors. * * Spurious faults may only occur if the TLB contains an entry with * fewer permission than the page table entry. Non-present (P = 0) * and reserved bit (R = 1) faults are never spurious. * * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. * * Returns non-zero if a spurious fault was handled, zero otherwise. * * See Intel Developer's Manual Vol 3 Section 4.10.4.3, bullet 3 * (Optional Invalidation). */ static noinline int spurious_kernel_fault(unsigned long error_code, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; int ret; /* * Only writes to RO or instruction fetches from NX may cause * spurious faults. * * These could be from user or supervisor accesses but the TLB * is only lazily flushed after a kernel mapping protection * change, so user accesses are not expected to cause spurious * faults. */ if (error_code != (X86_PF_WRITE | X86_PF_PROT) && error_code != (X86_PF_INSTR | X86_PF_PROT)) return 0; pgd = init_mm.pgd + pgd_index(address); if (!pgd_present(*pgd)) return 0; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) return 0; if (p4d_large(*p4d)) return spurious_kernel_fault_check(error_code, (pte_t *) p4d); pud = pud_offset(p4d, address); if (!pud_present(*pud)) return 0; if (pud_large(*pud)) return spurious_kernel_fault_check(error_code, (pte_t *) pud); pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return 0; if (pmd_large(*pmd)) return spurious_kernel_fault_check(error_code, (pte_t *) pmd); pte = pte_offset_kernel(pmd, address); if (!pte_present(*pte)) return 0; ret = spurious_kernel_fault_check(error_code, pte); if (!ret) return 0; /* * Make sure we have permissions in PMD. * If not, then there's a bug in the page tables: */ ret = spurious_kernel_fault_check(error_code, (pte_t *) pmd); WARN_ONCE(!ret, "PMD has incorrect permission bits\n"); return ret; } NOKPROBE_SYMBOL(spurious_kernel_fault); int show_unhandled_signals = 1; static inline int access_error(unsigned long error_code, struct vm_area_struct *vma) { /* This is only called for the current mm, so: */ bool foreign = false; /* * Read or write was blocked by protection keys. This is * always an unconditional error and can never result in * a follow-up action to resolve the fault, like a COW. */ if (error_code & X86_PF_PK) return 1; /* * Make sure to check the VMA so that we do not perform * faults just to hit a X86_PF_PK as soon as we fill in a * page. */ if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), (error_code & X86_PF_INSTR), foreign)) return 1; if (error_code & X86_PF_WRITE) { /* write, present and write, not present: */ if (unlikely(!(vma->vm_flags & VM_WRITE))) return 1; return 0; } /* read, present: */ if (unlikely(error_code & X86_PF_PROT)) return 1; /* read, not present: */ if (unlikely(!vma_is_accessible(vma))) return 1; return 0; } bool fault_in_kernel_space(unsigned long address) { /* * On 64-bit systems, the vsyscall page is at an address above * TASK_SIZE_MAX, but is not considered part of the kernel * address space. */ if (IS_ENABLED(CONFIG_X86_64) && is_vsyscall_vaddr(address)) return false; return address >= TASK_SIZE_MAX; } /* * Called for all faults where 'address' is part of the kernel address * space. Might get called for faults that originate from *code* that * ran in userspace or the kernel. */ static void do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, unsigned long address) { /* * Protection keys exceptions only happen on user pages. We * have no user pages in the kernel portion of the address * space, so do not expect them here. */ WARN_ON_ONCE(hw_error_code & X86_PF_PK); #ifdef CONFIG_X86_32 /* * We can fault-in kernel-space virtual memory on-demand. The * 'reference' page table is init_mm.pgd. * * NOTE! We MUST NOT take any locks for this case. We may * be in an interrupt or a critical region, and should * only copy the information from the master page table, * nothing more. * * Before doing this on-demand faulting, ensure that the * fault is not any of the following: * 1. A fault on a PTE with a reserved bit set. * 2. A fault caused by a user-mode access. (Do not demand- * fault kernel memory due to user-mode accesses). * 3. A fault caused by a page-level protection violation. * (A demand fault would be on a non-present page which * would have X86_PF_PROT==0). * * This is only needed to close a race condition on x86-32 in * the vmalloc mapping/unmapping code. See the comment above * vmalloc_fault() for details. On x86-64 the race does not * exist as the vmalloc mappings don't need to be synchronized * there. */ if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) { if (vmalloc_fault(address) >= 0) return; } #endif /* Was the fault spurious, caused by lazy TLB invalidation? */ if (spurious_kernel_fault(hw_error_code, address)) return; /* kprobes don't want to hook the spurious faults: */ if (kprobe_page_fault(regs, X86_TRAP_PF)) return; /* * Note, despite being a "bad area", there are quite a few * acceptable reasons to get here, such as erratum fixups * and handling kernel code that can fault, like get_user(). * * Don't take the mm semaphore here. If we fixup a prefetch * fault we could otherwise deadlock: */ bad_area_nosemaphore(regs, hw_error_code, address); } NOKPROBE_SYMBOL(do_kern_addr_fault); /* Handle faults in the user portion of the address space */ static inline void do_user_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, unsigned long address) { struct vm_area_struct *vma; struct task_struct *tsk; struct mm_struct *mm; vm_fault_t fault; unsigned int flags = FAULT_FLAG_DEFAULT; tsk = current; mm = tsk->mm; /* kprobes don't want to hook the spurious faults: */ if (unlikely(kprobe_page_fault(regs, X86_TRAP_PF))) return; /* * Reserved bits are never expected to be set on * entries in the user portion of the page tables. */ if (unlikely(hw_error_code & X86_PF_RSVD)) pgtable_bad(regs, hw_error_code, address); /* * If SMAP is on, check for invalid kernel (supervisor) access to user * pages in the user address space. The odd case here is WRUSS, * which, according to the preliminary documentation, does not respect * SMAP and will have the USER bit set so, in all cases, SMAP * enforcement appears to be consistent with the USER bit. */ if (unlikely(cpu_feature_enabled(X86_FEATURE_SMAP) && !(hw_error_code & X86_PF_USER) && !(regs->flags & X86_EFLAGS_AC))) { bad_area_nosemaphore(regs, hw_error_code, address); return; } /* * If we're in an interrupt, have no user context or are running * in a region with pagefaults disabled then we must not take the fault */ if (unlikely(faulthandler_disabled() || !mm)) { bad_area_nosemaphore(regs, hw_error_code, address); return; } /* * It's safe to allow irq's after cr2 has been saved and the * vmalloc fault has been handled. * * User-mode registers count as a user access even for any * potential system fault or CPU buglet: */ if (user_mode(regs)) { local_irq_enable(); flags |= FAULT_FLAG_USER; } else { if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); } perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); if (hw_error_code & X86_PF_WRITE) flags |= FAULT_FLAG_WRITE; if (hw_error_code & X86_PF_INSTR) flags |= FAULT_FLAG_INSTRUCTION; #ifdef CONFIG_X86_64 /* * Faults in the vsyscall page might need emulation. The * vsyscall page is at a high address (>PAGE_OFFSET), but is * considered to be part of the user address space. * * The vsyscall page does not have a "real" VMA, so do this * emulation before we go searching for VMAs. * * PKRU never rejects instruction fetches, so we don't need * to consider the PF_PK bit. */ if (is_vsyscall_vaddr(address)) { if (emulate_vsyscall(hw_error_code, regs, address)) return; } #endif /* * Kernel-mode access to the user address space should only occur * on well-defined single instructions listed in the exception * tables. But, an erroneous kernel fault occurring outside one of * those areas which also holds mmap_lock might deadlock attempting * to validate the fault against the address space. * * Only do the expensive exception table search when we might be at * risk of a deadlock. This happens if we * 1. Failed to acquire mmap_lock, and * 2. The access did not originate in userspace. */ if (unlikely(!mmap_read_trylock(mm))) { if (!user_mode(regs) && !search_exception_tables(regs->ip)) { /* * Fault from code in kernel from * which we do not expect faults. */ bad_area_nosemaphore(regs, hw_error_code, address); return; } retry: mmap_read_lock(mm); } else { /* * The above down_read_trylock() might have succeeded in * which case we'll have missed the might_sleep() from * down_read(): */ might_sleep(); } vma = find_vma(mm, address); if (unlikely(!vma)) { bad_area(regs, hw_error_code, address); return; } if (likely(vma->vm_start <= address)) goto good_area; if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { bad_area(regs, hw_error_code, address); return; } if (unlikely(expand_stack(vma, address))) { bad_area(regs, hw_error_code, address); return; } /* * Ok, we have a good vm_area for this memory access, so * we can handle it.. */ good_area: if (unlikely(access_error(hw_error_code, vma))) { bad_area_access_error(regs, hw_error_code, address, vma); return; } /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if * we get VM_FAULT_RETRY back, the mmap_lock has been unlocked. * * Note that handle_userfault() may also release and reacquire mmap_lock * (and not return with VM_FAULT_RETRY), when returning to userland to * repeat the page fault later with a VM_FAULT_NOPAGE retval * (potentially after handling any pending signal during the return to * userland). The return to userland is identified whenever * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags. */ fault = handle_mm_fault(vma, address, flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) no_context(regs, hw_error_code, address, SIGBUS, BUS_ADRERR); return; } /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee * that we made any progress. Handle this case first. */ if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { flags |= FAULT_FLAG_TRIED; goto retry; } mmap_read_unlock(mm); if (unlikely(fault & VM_FAULT_ERROR)) { mm_fault_error(regs, hw_error_code, address, fault); return; } check_v8086_mode(regs, address, tsk); } NOKPROBE_SYMBOL(do_user_addr_fault); static __always_inline void trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code, unsigned long address) { if (!trace_pagefault_enabled()) return; if (user_mode(regs)) trace_page_fault_user(address, regs, error_code); else trace_page_fault_kernel(address, regs, error_code); } static __always_inline void handle_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { trace_page_fault_entries(regs, error_code, address); if (unlikely(kmmio_fault(regs, address))) return; /* Was the fault on kernel-controlled part of the address space? */ if (unlikely(fault_in_kernel_space(address))) { do_kern_addr_fault(regs, error_code, address); } else { do_user_addr_fault(regs, error_code, address); /* * User address page fault handling might have reenabled * interrupts. Fixing up all potential exit points of * do_user_addr_fault() and its leaf functions is just not * doable w/o creating an unholy mess or turning the code * upside down. */ local_irq_disable(); } } DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) { unsigned long address = read_cr2(); irqentry_state_t state; prefetchw(¤t->mm->mmap_lock); /* * KVM uses #PF vector to deliver 'page not present' events to guests * (asynchronous page fault mechanism). The event happens when a * userspace task is trying to access some valid (from guest's point of * view) memory which is not currently mapped by the host (e.g. the * memory is swapped out). Note, the corresponding "page ready" event * which is injected when the memory becomes available, is delived via * an interrupt mechanism and not a #PF exception * (see arch/x86/kernel/kvm.c: sysvec_kvm_asyncpf_interrupt()). * * We are relying on the interrupted context being sane (valid RSP, * relevant locks not held, etc.), which is fine as long as the * interrupted context had IF=1. We are also relying on the KVM * async pf type field and CR2 being read consistently instead of * getting values from real and async page faults mixed up. * * Fingers crossed. * * The async #PF handling code takes care of idtentry handling * itself. */ if (kvm_handle_async_pf(regs, (u32)address)) return; /* * Entry handling for valid #PF from kernel mode is slightly * different: RCU is already watching and rcu_irq_enter() must not * be invoked because a kernel fault on a user space address might * sleep. * * In case the fault hit a RCU idle region the conditional entry * code reenabled RCU to avoid subsequent wreckage which helps * debugability. */ state = irqentry_enter(regs); instrumentation_begin(); handle_page_fault(regs, error_code, address); instrumentation_end(); irqentry_exit(regs, state); } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HIGHMEM_H #define _LINUX_HIGHMEM_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/bug.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include <asm/cacheflush.h> #ifndef ARCH_HAS_FLUSH_ANON_PAGE static inline void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) { } #endif #ifndef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE static inline void flush_kernel_dcache_page(struct page *page) { } static inline void flush_kernel_vmap_range(void *vaddr, int size) { } static inline void invalidate_kernel_vmap_range(void *vaddr, int size) { } #endif #include <asm/kmap_types.h> #ifdef CONFIG_HIGHMEM extern void *kmap_atomic_high_prot(struct page *page, pgprot_t prot); extern void kunmap_atomic_high(void *kvaddr); #include <asm/highmem.h> #ifndef ARCH_HAS_KMAP_FLUSH_TLB static inline void kmap_flush_tlb(unsigned long addr) { } #endif #ifndef kmap_prot #define kmap_prot PAGE_KERNEL #endif void *kmap_high(struct page *page); static inline void *kmap(struct page *page) { void *addr; might_sleep(); if (!PageHighMem(page)) addr = page_address(page); else addr = kmap_high(page); kmap_flush_tlb((unsigned long)addr); return addr; } void kunmap_high(struct page *page); static inline void kunmap(struct page *page) { might_sleep(); if (!PageHighMem(page)) return; kunmap_high(page); } /* * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because * no global lock is needed and because the kmap code must perform a global TLB * invalidation when the kmap pool wraps. * * However when holding an atomic kmap it is not legal to sleep, so atomic * kmaps are appropriate for short, tight code paths only. * * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap * gives a more generic (and caching) interface. But kmap_atomic can * be used in IRQ contexts, so in some (very limited) cases we need * it. */ static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot) { preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); return kmap_atomic_high_prot(page, prot); } #define kmap_atomic(page) kmap_atomic_prot(page, kmap_prot) /* declarations for linux/mm/highmem.c */ unsigned int nr_free_highpages(void); extern atomic_long_t _totalhigh_pages; static inline unsigned long totalhigh_pages(void) { return (unsigned long)atomic_long_read(&_totalhigh_pages); } static inline void totalhigh_pages_inc(void) { atomic_long_inc(&_totalhigh_pages); } static inline void totalhigh_pages_dec(void) { atomic_long_dec(&_totalhigh_pages); } static inline void totalhigh_pages_add(long count) { atomic_long_add(count, &_totalhigh_pages); } static inline void totalhigh_pages_set(long val) { atomic_long_set(&_totalhigh_pages, val); } void kmap_flush_unused(void); struct page *kmap_to_page(void *addr); #else /* CONFIG_HIGHMEM */ static inline unsigned int nr_free_highpages(void) { return 0; } static inline struct page *kmap_to_page(void *addr) { return virt_to_page(addr); } static inline unsigned long totalhigh_pages(void) { return 0UL; } static inline void *kmap(struct page *page) { might_sleep(); return page_address(page); } static inline void kunmap_high(struct page *page) { } static inline void kunmap(struct page *page) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(page_address(page)); #endif } static inline void *kmap_atomic(struct page *page) { preempt_disable(); pagefault_disable(); return page_address(page); } #define kmap_atomic_prot(page, prot) kmap_atomic(page) static inline void kunmap_atomic_high(void *addr) { /* * Mostly nothing to do in the CONFIG_HIGHMEM=n case as kunmap_atomic() * handles re-enabling faults + preemption */ #ifdef ARCH_HAS_FLUSH_ON_KUNMAP kunmap_flush_on_unmap(addr); #endif } #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) #define kmap_flush_unused() do {} while(0) #endif /* CONFIG_HIGHMEM */ #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) DECLARE_PER_CPU(int, __kmap_atomic_idx); static inline int kmap_atomic_idx_push(void) { int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1; #ifdef CONFIG_DEBUG_HIGHMEM WARN_ON_ONCE(in_irq() && !irqs_disabled()); BUG_ON(idx >= KM_TYPE_NR); #endif return idx; } static inline int kmap_atomic_idx(void) { return __this_cpu_read(__kmap_atomic_idx) - 1; } static inline void kmap_atomic_idx_pop(void) { #ifdef CONFIG_DEBUG_HIGHMEM int idx = __this_cpu_dec_return(__kmap_atomic_idx); BUG_ON(idx < 0); #else __this_cpu_dec(__kmap_atomic_idx); #endif } #endif /* * Prevent people trying to call kunmap_atomic() as if it were kunmap() * kunmap_atomic() should get the return value of kmap_atomic, not the page. */ #define kunmap_atomic(addr) \ do { \ BUILD_BUG_ON(__same_type((addr), struct page *)); \ kunmap_atomic_high(addr); \ pagefault_enable(); \ preempt_enable(); \ } while (0) /* when CONFIG_HIGHMEM is not set these will be plain clear/copy_page */ #ifndef clear_user_highpage static inline void clear_user_highpage(struct page *page, unsigned long vaddr) { void *addr = kmap_atomic(page); clear_user_page(addr, vaddr, page); kunmap_atomic(addr); } #endif #ifndef __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE /** * __alloc_zeroed_user_highpage - Allocate a zeroed HIGHMEM page for a VMA with caller-specified movable GFP flags * @movableflags: The GFP flags related to the pages future ability to move like __GFP_MOVABLE * @vma: The VMA the page is to be allocated for * @vaddr: The virtual address the page will be inserted into * * This function will allocate a page for a VMA but the caller is expected * to specify via movableflags whether the page will be movable in the * future or not * * An architecture may override this function by defining * __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE and providing their own * implementation. */ static inline struct page * __alloc_zeroed_user_highpage(gfp_t movableflags, struct vm_area_struct *vma, unsigned long vaddr) { struct page *page = alloc_page_vma(GFP_HIGHUSER | movableflags, vma, vaddr); if (page) clear_user_highpage(page, vaddr); return page; } #endif /** * alloc_zeroed_user_highpage_movable - Allocate a zeroed HIGHMEM page for a VMA that the caller knows can move * @vma: The VMA the page is to be allocated for * @vaddr: The virtual address the page will be inserted into * * This function will allocate a page for a VMA that the caller knows will * be able to migrate in the future using move_pages() or reclaimed */ static inline struct page * alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, unsigned long vaddr) { return __alloc_zeroed_user_highpage(__GFP_MOVABLE, vma, vaddr); } static inline void clear_highpage(struct page *page) { void *kaddr = kmap_atomic(page); clear_page(kaddr); kunmap_atomic(kaddr); } static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { void *kaddr = kmap_atomic(page); BUG_ON(end1 > PAGE_SIZE || end2 > PAGE_SIZE); if (end1 > start1) memset(kaddr + start1, 0, end1 - start1); if (end2 > start2) memset(kaddr + start2, 0, end2 - start2); kunmap_atomic(kaddr); flush_dcache_page(page); } static inline void zero_user_segment(struct page *page, unsigned start, unsigned end) { zero_user_segments(page, start, end, 0, 0); } static inline void zero_user(struct page *page, unsigned start, unsigned size) { zero_user_segments(page, start, start + size, 0, 0); } #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE static inline void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { char *vfrom, *vto; vfrom = kmap_atomic(from); vto = kmap_atomic(to); copy_user_page(vto, vfrom, vaddr, to); kunmap_atomic(vto); kunmap_atomic(vfrom); } #endif #ifndef __HAVE_ARCH_COPY_HIGHPAGE static inline void copy_highpage(struct page *to, struct page *from) { char *vfrom, *vto; vfrom = kmap_atomic(from); vto = kmap_atomic(to); copy_page(vto, vfrom); kunmap_atomic(vto); kunmap_atomic(vfrom); } #endif static inline void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { char *from = kmap_atomic(page); memcpy(to, from + offset, len); kunmap_atomic(from); } static inline void memcpy_to_page(struct page *page, size_t offset, const char *from, size_t len) { char *to = kmap_atomic(page); memcpy(to + offset, from, len); kunmap_atomic(to); } #endif /* _LINUX_HIGHMEM_H */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/sched/cputime.h> static DEFINE_SPINLOCK(cgroup_rstat_lock); static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock); static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu); static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) { return per_cpu_ptr(cgrp->rstat_cpu, cpu); } /** * cgroup_rstat_updated - keep track of updated rstat_cpu * @cgrp: target cgroup * @cpu: cpu on which rstat_cpu was updated * * @cgrp's rstat_cpu on @cpu was updated. Put it on the parent's matching * rstat_cpu->updated_children list. See the comment on top of * cgroup_rstat_cpu definition for details. */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup *parent; unsigned long flags; /* nothing to do for root */ if (!cgroup_parent(cgrp)) return; /* * Speculative already-on-list test. This may race leading to * temporary inaccuracies, which is fine. * * Because @parent's updated_children is terminated with @parent * instead of NULL, we can tell whether @cgrp is on the list by * testing the next pointer for NULL. */ if (cgroup_rstat_cpu(cgrp, cpu)->updated_next) return; raw_spin_lock_irqsave(cpu_lock, flags); /* put @cgrp and all ancestors on the corresponding updated lists */ for (parent = cgroup_parent(cgrp); parent; cgrp = parent, parent = cgroup_parent(cgrp)) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu); /* * Both additions and removals are bottom-up. If a cgroup * is already in the tree, all ancestors are. */ if (rstatc->updated_next) break; rstatc->updated_next = prstatc->updated_children; prstatc->updated_children = cgrp; } raw_spin_unlock_irqrestore(cpu_lock, flags); } /** * cgroup_rstat_cpu_pop_updated - iterate and dismantle rstat_cpu updated tree * @pos: current position * @root: root of the tree to traversal * @cpu: target cpu * * Walks the udpated rstat_cpu tree on @cpu from @root. %NULL @pos starts * the traversal and %NULL return indicates the end. During traversal, * each returned cgroup is unlinked from the tree. Must be called with the * matching cgroup_rstat_cpu_lock held. * * The only ordering guarantee is that, for a parent and a child pair * covered by a given traversal, if a child is visited, its parent is * guaranteed to be visited afterwards. */ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos, struct cgroup *root, int cpu) { struct cgroup_rstat_cpu *rstatc; if (pos == root) return NULL; /* * We're gonna walk down to the first leaf and visit/remove it. We * can pick whatever unvisited node as the starting point. */ if (!pos) pos = root; else pos = cgroup_parent(pos); /* walk down to the first leaf */ while (true) { rstatc = cgroup_rstat_cpu(pos, cpu); if (rstatc->updated_children == pos) break; pos = rstatc->updated_children; } /* * Unlink @pos from the tree. As the updated_children list is * singly linked, we have to walk it to find the removal point. * However, due to the way we traverse, @pos will be the first * child in most cases. The only exception is @root. */ if (rstatc->updated_next) { struct cgroup *parent = cgroup_parent(pos); struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu); struct cgroup_rstat_cpu *nrstatc; struct cgroup **nextp; nextp = &prstatc->updated_children; while (true) { nrstatc = cgroup_rstat_cpu(*nextp, cpu); if (*nextp == pos) break; WARN_ON_ONCE(*nextp == parent); nextp = &nrstatc->updated_next; } *nextp = rstatc->updated_next; rstatc->updated_next = NULL; return pos; } /* only happens for @root */ return NULL; } /* see cgroup_rstat_flush() */ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) __releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock) { int cpu; lockdep_assert_held(&cgroup_rstat_lock); for_each_possible_cpu(cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); struct cgroup *pos = NULL; raw_spin_lock(cpu_lock); while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { struct cgroup_subsys_state *css; cgroup_base_stat_flush(pos, cpu); rcu_read_lock(); list_for_each_entry_rcu(css, &pos->rstat_css_list, rstat_css_node) css->ss->css_rstat_flush(css, cpu); rcu_read_unlock(); } raw_spin_unlock(cpu_lock); /* if @may_sleep, play nice and yield if necessary */ if (may_sleep && (need_resched() || spin_needbreak(&cgroup_rstat_lock))) { spin_unlock_irq(&cgroup_rstat_lock); if (!cond_resched()) cpu_relax(); spin_lock_irq(&cgroup_rstat_lock); } } } /** * cgroup_rstat_flush - flush stats in @cgrp's subtree * @cgrp: target cgroup * * Collect all per-cpu stats in @cgrp's subtree into the global counters * and propagate them upwards. After this function returns, all cgroups in * the subtree have up-to-date ->stat. * * This also gets all cgroups in the subtree including @cgrp off the * ->updated_children lists. * * This function may block. */ void cgroup_rstat_flush(struct cgroup *cgrp) { might_sleep(); spin_lock_irq(&cgroup_rstat_lock); cgroup_rstat_flush_locked(cgrp, true); spin_unlock_irq(&cgroup_rstat_lock); } /** * cgroup_rstat_flush_irqsafe - irqsafe version of cgroup_rstat_flush() * @cgrp: target cgroup * * This function can be called from any context. */ void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp) { unsigned long flags; spin_lock_irqsave(&cgroup_rstat_lock, flags); cgroup_rstat_flush_locked(cgrp, false); spin_unlock_irqrestore(&cgroup_rstat_lock, flags); } /** * cgroup_rstat_flush_begin - flush stats in @cgrp's subtree and hold * @cgrp: target cgroup * * Flush stats in @cgrp's subtree and prevent further flushes. Must be * paired with cgroup_rstat_flush_release(). * * This function may block. */ void cgroup_rstat_flush_hold(struct cgroup *cgrp) __acquires(&cgroup_rstat_lock) { might_sleep(); spin_lock_irq(&cgroup_rstat_lock); cgroup_rstat_flush_locked(cgrp, true); } /** * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold() */ void cgroup_rstat_flush_release(void) __releases(&cgroup_rstat_lock) { spin_unlock_irq(&cgroup_rstat_lock); } int cgroup_rstat_init(struct cgroup *cgrp) { int cpu; /* the root cgrp has rstat_cpu preallocated */ if (!cgrp->rstat_cpu) { cgrp->rstat_cpu = alloc_percpu(struct cgroup_rstat_cpu); if (!cgrp->rstat_cpu) return -ENOMEM; } /* ->updated_children list is self terminated */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); rstatc->updated_children = cgrp; u64_stats_init(&rstatc->bsync); } return 0; } void cgroup_rstat_exit(struct cgroup *cgrp) { int cpu; cgroup_rstat_flush(cgrp); /* sanity check */ for_each_possible_cpu(cpu) { struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); if (WARN_ON_ONCE(rstatc->updated_children != cgrp) || WARN_ON_ONCE(rstatc->updated_next)) return; } free_percpu(cgrp->rstat_cpu); cgrp->rstat_cpu = NULL; } void __init cgroup_rstat_boot(void) { int cpu; for_each_possible_cpu(cpu) raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu)); BUG_ON(cgroup_rstat_init(&cgrp_dfl_root.cgrp)); } /* * Functions for cgroup basic resource statistics implemented on top of * rstat. */ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, struct cgroup_base_stat *src_bstat) { dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_rstat_cpu *rstatc = cgroup_rstat_cpu(cgrp, cpu); struct cgroup_base_stat cur, delta; unsigned seq; /* fetch the current per-cpu values */ do { seq = __u64_stats_fetch_begin(&rstatc->bsync); cur.cputime = rstatc->bstat.cputime; } while (__u64_stats_fetch_retry(&rstatc->bsync, seq)); /* propagate percpu delta to global */ delta = cur; cgroup_base_stat_sub(&delta, &rstatc->last_bstat); cgroup_base_stat_add(&cgrp->bstat, &delta); cgroup_base_stat_add(&rstatc->last_bstat, &delta); /* propagate global delta to parent */ if (parent) { delta = cgrp->bstat; cgroup_base_stat_sub(&delta, &cgrp->last_bstat); cgroup_base_stat_add(&parent->bstat, &delta); cgroup_base_stat_add(&cgrp->last_bstat, &delta); } } static struct cgroup_rstat_cpu * cgroup_base_stat_cputime_account_begin(struct cgroup *cgrp) { struct cgroup_rstat_cpu *rstatc; rstatc = get_cpu_ptr(cgrp->rstat_cpu); u64_stats_update_begin(&rstatc->bsync); return rstatc; } static void cgroup_base_stat_cputime_account_end(struct cgroup *cgrp, struct cgroup_rstat_cpu *rstatc) { u64_stats_update_end(&rstatc->bsync); cgroup_rstat_updated(cgrp, smp_processor_id()); put_cpu_ptr(rstatc); } void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; rstatc = cgroup_base_stat_cputime_account_begin(cgrp); rstatc->bstat.cputime.sum_exec_runtime += delta_exec; cgroup_base_stat_cputime_account_end(cgrp, rstatc); } void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup_rstat_cpu *rstatc; rstatc = cgroup_base_stat_cputime_account_begin(cgrp); switch (index) { case CPUTIME_USER: case CPUTIME_NICE: rstatc->bstat.cputime.utime += delta_exec; break; case CPUTIME_SYSTEM: case CPUTIME_IRQ: case CPUTIME_SOFTIRQ: rstatc->bstat.cputime.stime += delta_exec; break; default: break; } cgroup_base_stat_cputime_account_end(cgrp, rstatc); } /* * compute the cputime for the root cgroup by getting the per cpu data * at a global level, then categorizing the fields in a manner consistent * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ static void root_cgroup_cputime(struct task_cputime *cputime) { int i; cputime->stime = 0; cputime->utime = 0; cputime->sum_exec_runtime = 0; for_each_possible_cpu(i) { struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u64 user = 0; u64 sys = 0; kcpustat_cpu_fetch(&kcpustat, i); user += cpustat[CPUTIME_USER]; user += cpustat[CPUTIME_NICE]; cputime->utime += user; sys += cpustat[CPUTIME_SYSTEM]; sys += cpustat[CPUTIME_IRQ]; sys += cpustat[CPUTIME_SOFTIRQ]; cputime->stime += sys; cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; } } void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime; struct task_cputime cputime; if (cgroup_parent(cgrp)) { cgroup_rstat_flush_hold(cgrp); usage = cgrp->bstat.cputime.sum_exec_runtime; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime); cgroup_rstat_flush_release(); } else { root_cgroup_cputime(&cputime); usage = cputime.sum_exec_runtime; utime = cputime.utime; stime = cputime.stime; } do_div(usage, NSEC_PER_USEC); do_div(utime, NSEC_PER_USEC); do_div(stime, NSEC_PER_USEC); seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n", usage, utime, stime); } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 | // SPDX-License-Identifier: GPL-2.0-only /* * NSA Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux hook function implementations. * * Authors: Stephen Smalley, <sds@tycho.nsa.gov> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003-2008 Red Hat, Inc., James Morris <jmorris@redhat.com> * Eric Paris <eparis@redhat.com> * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. * <dgoeddel@trustedcs.com> * Copyright (C) 2006, 2007, 2009 Hewlett-Packard Development Company, L.P. * Paul Moore <paul@paul-moore.com> * Copyright (C) 2007 Hitachi Software Engineering Co., Ltd. * Yuichi Nakamura <ynakam@hitachisoft.jp> * Copyright (C) 2016 Mellanox Technologies */ #include <linux/init.h> #include <linux/kd.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/tracehook.h> #include <linux/errno.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/lsm_hooks.h> #include <linux/xattr.h> #include <linux/capability.h> #include <linux/unistd.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/swap.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/dcache.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/tty.h> #include <net/icmp.h> #include <net/ip.h> /* for local_port_range[] */ #include <net/tcp.h> /* struct or_callable used in sock_rcv_skb */ #include <net/inet_connection_sock.h> #include <net/net_namespace.h> #include <net/netlabel.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/interrupt.h> #include <linux/netdevice.h> /* for network interface checks */ #include <net/netlink.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <net/sctp/structs.h> #include <linux/quota.h> #include <linux/un.h> /* for Unix socket types */ #include <net/af_unix.h> /* for Unix socket types */ #include <linux/parser.h> #include <linux/nfs_mount.h> #include <net/ipv6.h> #include <linux/hugetlb.h> #include <linux/personality.h> #include <linux/audit.h> #include <linux/string.h> #include <linux/mutex.h> #include <linux/posix-timers.h> #include <linux/syslog.h> #include <linux/user_namespace.h> #include <linux/export.h> #include <linux/msg.h> #include <linux/shm.h> #include <linux/bpf.h> #include <linux/kernfs.h> #include <linux/stringhash.h> /* for hashlen_string() */ #include <uapi/linux/mount.h> #include <linux/fsnotify.h> #include <linux/fanotify.h> #include "avc.h" #include "objsec.h" #include "netif.h" #include "netnode.h" #include "netport.h" #include "ibpkey.h" #include "xfrm.h" #include "netlabel.h" #include "audit.h" #include "avc_ss.h" struct selinux_state selinux_state; /* SECMARK reference count */ static atomic_t selinux_secmark_refcount = ATOMIC_INIT(0); #ifdef CONFIG_SECURITY_SELINUX_DEVELOP static int selinux_enforcing_boot __initdata; static int __init enforcing_setup(char *str) { unsigned long enforcing; if (!kstrtoul(str, 0, &enforcing)) selinux_enforcing_boot = enforcing ? 1 : 0; return 1; } __setup("enforcing=", enforcing_setup); #else #define selinux_enforcing_boot 1 #endif int selinux_enabled_boot __initdata = 1; #ifdef CONFIG_SECURITY_SELINUX_BOOTPARAM static int __init selinux_enabled_setup(char *str) { unsigned long enabled; if (!kstrtoul(str, 0, &enabled)) selinux_enabled_boot = enabled ? 1 : 0; return 1; } __setup("selinux=", selinux_enabled_setup); #endif static unsigned int selinux_checkreqprot_boot = CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE; static int __init checkreqprot_setup(char *str) { unsigned long checkreqprot; if (!kstrtoul(str, 0, &checkreqprot)) { selinux_checkreqprot_boot = checkreqprot ? 1 : 0; if (checkreqprot) pr_warn("SELinux: checkreqprot set to 1 via kernel parameter. This is deprecated and will be rejected in a future kernel release.\n"); } return 1; } __setup("checkreqprot=", checkreqprot_setup); /** * selinux_secmark_enabled - Check to see if SECMARK is currently enabled * * Description: * This function checks the SECMARK reference counter to see if any SECMARK * targets are currently configured, if the reference counter is greater than * zero SECMARK is considered to be enabled. Returns true (1) if SECMARK is * enabled, false (0) if SECMARK is disabled. If the always_check_network * policy capability is enabled, SECMARK is always considered enabled. * */ static int selinux_secmark_enabled(void) { return (selinux_policycap_alwaysnetwork() || atomic_read(&selinux_secmark_refcount)); } /** * selinux_peerlbl_enabled - Check to see if peer labeling is currently enabled * * Description: * This function checks if NetLabel or labeled IPSEC is enabled. Returns true * (1) if any are enabled or false (0) if neither are enabled. If the * always_check_network policy capability is enabled, peer labeling * is always considered enabled. * */ static int selinux_peerlbl_enabled(void) { return (selinux_policycap_alwaysnetwork() || netlbl_enabled() || selinux_xfrm_enabled()); } static int selinux_netcache_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) { sel_netif_flush(); sel_netnode_flush(); sel_netport_flush(); synchronize_net(); } return 0; } static int selinux_lsm_notifier_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) { sel_ib_pkey_flush(); call_blocking_lsm_notifier(LSM_POLICY_CHANGE, NULL); } return 0; } /* * initialise the security for the init task */ static void cred_init_security(void) { struct cred *cred = (struct cred *) current->real_cred; struct task_security_struct *tsec; tsec = selinux_cred(cred); tsec->osid = tsec->sid = SECINITSID_KERNEL; } /* * get the security ID of a set of credentials */ static inline u32 cred_sid(const struct cred *cred) { const struct task_security_struct *tsec; tsec = selinux_cred(cred); return tsec->sid; } /* * get the objective security ID of a task */ static inline u32 task_sid(const struct task_struct *task) { u32 sid; rcu_read_lock(); sid = cred_sid(__task_cred(task)); rcu_read_unlock(); return sid; } static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry); /* * Try reloading inode security labels that have been marked as invalid. The * @may_sleep parameter indicates when sleeping and thus reloading labels is * allowed; when set to false, returns -ECHILD when the label is * invalid. The @dentry parameter should be set to a dentry of the inode. */ static int __inode_security_revalidate(struct inode *inode, struct dentry *dentry, bool may_sleep) { struct inode_security_struct *isec = selinux_inode(inode); might_sleep_if(may_sleep); if (selinux_initialized(&selinux_state) && isec->initialized != LABEL_INITIALIZED) { if (!may_sleep) return -ECHILD; /* * Try reloading the inode security label. This will fail if * @opt_dentry is NULL and no dentry for this inode can be * found; in that case, continue using the old label. */ inode_doinit_with_dentry(inode, dentry); } return 0; } static struct inode_security_struct *inode_security_novalidate(struct inode *inode) { return selinux_inode(inode); } static struct inode_security_struct *inode_security_rcu(struct inode *inode, bool rcu) { int error; error = __inode_security_revalidate(inode, NULL, !rcu); if (error) return ERR_PTR(error); return selinux_inode(inode); } /* * Get the security label of an inode. */ static struct inode_security_struct *inode_security(struct inode *inode) { __inode_security_revalidate(inode, NULL, true); return selinux_inode(inode); } static struct inode_security_struct *backing_inode_security_novalidate(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); return selinux_inode(inode); } /* * Get the security label of a dentry's backing inode. */ static struct inode_security_struct *backing_inode_security(struct dentry *dentry) { struct inode *inode = d_backing_inode(dentry); __inode_security_revalidate(inode, dentry, true); return selinux_inode(inode); } static void inode_free_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); struct superblock_security_struct *sbsec; if (!isec) return; sbsec = inode->i_sb->s_security; /* * As not all inode security structures are in a list, we check for * empty list outside of the lock to make sure that we won't waste * time taking a lock doing nothing. * * The list_del_init() function can be safely called more than once. * It should not be possible for this function to be called with * concurrent list_add(), but for better safety against future changes * in the code, we use list_empty_careful() here. */ if (!list_empty_careful(&isec->list)) { spin_lock(&sbsec->isec_lock); list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); } } static void superblock_free_security(struct super_block *sb) { struct superblock_security_struct *sbsec = sb->s_security; sb->s_security = NULL; kfree(sbsec); } struct selinux_mnt_opts { const char *fscontext, *context, *rootcontext, *defcontext; }; static void selinux_free_mnt_opts(void *mnt_opts) { struct selinux_mnt_opts *opts = mnt_opts; kfree(opts->fscontext); kfree(opts->context); kfree(opts->rootcontext); kfree(opts->defcontext); kfree(opts); } enum { Opt_error = -1, Opt_context = 0, Opt_defcontext = 1, Opt_fscontext = 2, Opt_rootcontext = 3, Opt_seclabel = 4, }; #define A(s, has_arg) {#s, sizeof(#s) - 1, Opt_##s, has_arg} static struct { const char *name; int len; int opt; bool has_arg; } tokens[] = { A(context, true), A(fscontext, true), A(defcontext, true), A(rootcontext, true), A(seclabel, false), }; #undef A static int match_opt_prefix(char *s, int l, char **arg) { int i; for (i = 0; i < ARRAY_SIZE(tokens); i++) { size_t len = tokens[i].len; if (len > l || memcmp(s, tokens[i].name, len)) continue; if (tokens[i].has_arg) { if (len == l || s[len] != '=') continue; *arg = s + len + 1; } else if (len != l) continue; return tokens[i].opt; } return Opt_error; } #define SEL_MOUNT_FAIL_MSG "SELinux: duplicate or incompatible mount options\n" static int may_context_mount_sb_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { const struct task_security_struct *tsec = selinux_cred(cred); int rc; rc = avc_has_perm(&selinux_state, tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; rc = avc_has_perm(&selinux_state, tsec->sid, sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELTO, NULL); return rc; } static int may_context_mount_inode_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { const struct task_security_struct *tsec = selinux_cred(cred); int rc; rc = avc_has_perm(&selinux_state, tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; rc = avc_has_perm(&selinux_state, sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, NULL); return rc; } static int selinux_is_genfs_special_handling(struct super_block *sb) { /* Special handling. Genfs but also in-core setxattr handler */ return !strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "pstore") || !strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "rootfs") || (selinux_policycap_cgroupseclabel() && (!strcmp(sb->s_type->name, "cgroup") || !strcmp(sb->s_type->name, "cgroup2"))); } static int selinux_is_sblabel_mnt(struct super_block *sb) { struct superblock_security_struct *sbsec = sb->s_security; /* * IMPORTANT: Double-check logic in this function when adding a new * SECURITY_FS_USE_* definition! */ BUILD_BUG_ON(SECURITY_FS_USE_MAX != 7); switch (sbsec->behavior) { case SECURITY_FS_USE_XATTR: case SECURITY_FS_USE_TRANS: case SECURITY_FS_USE_TASK: case SECURITY_FS_USE_NATIVE: return 1; case SECURITY_FS_USE_GENFS: return selinux_is_genfs_special_handling(sb); /* Never allow relabeling on context mounts */ case SECURITY_FS_USE_MNTPOINT: case SECURITY_FS_USE_NONE: default: return 0; } } static int sb_finish_set_opts(struct super_block *sb) { struct superblock_security_struct *sbsec = sb->s_security; struct dentry *root = sb->s_root; struct inode *root_inode = d_backing_inode(root); int rc = 0; if (sbsec->behavior == SECURITY_FS_USE_XATTR) { /* Make sure that the xattr handler exists and that no error other than -ENODATA is returned by getxattr on the root directory. -ENODATA is ok, as this may be the first boot of the SELinux kernel before we have assigned xattr values to the filesystem. */ if (!(root_inode->i_opflags & IOP_XATTR)) { pr_warn("SELinux: (dev %s, type %s) has no " "xattr support\n", sb->s_id, sb->s_type->name); rc = -EOPNOTSUPP; goto out; } rc = __vfs_getxattr(root, root_inode, XATTR_NAME_SELINUX, NULL, 0); if (rc < 0 && rc != -ENODATA) { if (rc == -EOPNOTSUPP) pr_warn("SELinux: (dev %s, type " "%s) has no security xattr handler\n", sb->s_id, sb->s_type->name); else pr_warn("SELinux: (dev %s, type " "%s) getxattr errno %d\n", sb->s_id, sb->s_type->name, -rc); goto out; } } sbsec->flags |= SE_SBINITIALIZED; /* * Explicitly set or clear SBLABEL_MNT. It's not sufficient to simply * leave the flag untouched because sb_clone_mnt_opts might be handing * us a superblock that needs the flag to be cleared. */ if (selinux_is_sblabel_mnt(sb)) sbsec->flags |= SBLABEL_MNT; else sbsec->flags &= ~SBLABEL_MNT; /* Initialize the root inode. */ rc = inode_doinit_with_dentry(root_inode, root); /* Initialize any other inodes associated with the superblock, e.g. inodes created prior to initial policy load or inodes created during get_sb by a pseudo filesystem that directly populates itself. */ spin_lock(&sbsec->isec_lock); while (!list_empty(&sbsec->isec_head)) { struct inode_security_struct *isec = list_first_entry(&sbsec->isec_head, struct inode_security_struct, list); struct inode *inode = isec->inode; list_del_init(&isec->list); spin_unlock(&sbsec->isec_lock); inode = igrab(inode); if (inode) { if (!IS_PRIVATE(inode)) inode_doinit_with_dentry(inode, NULL); iput(inode); } spin_lock(&sbsec->isec_lock); } spin_unlock(&sbsec->isec_lock); out: return rc; } static int bad_option(struct superblock_security_struct *sbsec, char flag, u32 old_sid, u32 new_sid) { char mnt_flags = sbsec->flags & SE_MNTMASK; /* check if the old mount command had the same options */ if (sbsec->flags & SE_SBINITIALIZED) if (!(sbsec->flags & flag) || (old_sid != new_sid)) return 1; /* check if we were passed the same options twice, * aka someone passed context=a,context=b */ if (!(sbsec->flags & SE_SBINITIALIZED)) if (mnt_flags & flag) return 1; return 0; } static int parse_sid(struct super_block *sb, const char *s, u32 *sid) { int rc = security_context_str_to_sid(&selinux_state, s, sid, GFP_KERNEL); if (rc) pr_warn("SELinux: security_context_str_to_sid" "(%s) failed for (dev %s, type %s) errno=%d\n", s, sb->s_id, sb->s_type->name, rc); return rc; } /* * Allow filesystems with binary mount data to explicitly set mount point * labeling information. */ static int selinux_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { const struct cred *cred = current_cred(); struct superblock_security_struct *sbsec = sb->s_security; struct dentry *root = sbsec->sb->s_root; struct selinux_mnt_opts *opts = mnt_opts; struct inode_security_struct *root_isec; u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0; u32 defcontext_sid = 0; int rc = 0; mutex_lock(&sbsec->lock); if (!selinux_initialized(&selinux_state)) { if (!opts) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ goto out; } rc = -EINVAL; pr_warn("SELinux: Unable to set superblock options " "before the security server is initialized\n"); goto out; } if (kern_flags && !set_kern_flags) { /* Specifying internal flags without providing a place to * place the results is not allowed */ rc = -EINVAL; goto out; } /* * Binary mount data FS will come through this function twice. Once * from an explicit call and once from the generic calls from the vfs. * Since the generic VFS calls will not contain any security mount data * we need to skip the double mount verification. * * This does open a hole in which we will not notice if the first * mount using this sb set explict options and a second mount using * this sb does not set any security options. (The first options * will be used for both mounts) */ if ((sbsec->flags & SE_SBINITIALIZED) && (sb->s_type->fs_flags & FS_BINARY_MOUNTDATA) && !opts) goto out; root_isec = backing_inode_security_novalidate(root); /* * parse the mount options, check if they are valid sids. * also check if someone is trying to mount the same sb more * than once with different security options. */ if (opts) { if (opts->fscontext) { rc = parse_sid(sb, opts->fscontext, &fscontext_sid); if (rc) goto out; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, fscontext_sid)) goto out_double_mount; sbsec->flags |= FSCONTEXT_MNT; } if (opts->context) { rc = parse_sid(sb, opts->context, &context_sid); if (rc) goto out; if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, context_sid)) goto out_double_mount; sbsec->flags |= CONTEXT_MNT; } if (opts->rootcontext) { rc = parse_sid(sb, opts->rootcontext, &rootcontext_sid); if (rc) goto out; if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, rootcontext_sid)) goto out_double_mount; sbsec->flags |= ROOTCONTEXT_MNT; } if (opts->defcontext) { rc = parse_sid(sb, opts->defcontext, &defcontext_sid); if (rc) goto out; if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, defcontext_sid)) goto out_double_mount; sbsec->flags |= DEFCONTEXT_MNT; } } if (sbsec->flags & SE_SBINITIALIZED) { /* previously mounted with options, but not on this attempt? */ if ((sbsec->flags & SE_MNTMASK) && !opts) goto out_double_mount; rc = 0; goto out; } if (strcmp(sb->s_type->name, "proc") == 0) sbsec->flags |= SE_SBPROC | SE_SBGENFS; if (!strcmp(sb->s_type->name, "debugfs") || !strcmp(sb->s_type->name, "tracefs") || !strcmp(sb->s_type->name, "binder") || !strcmp(sb->s_type->name, "bpf") || !strcmp(sb->s_type->name, "pstore")) sbsec->flags |= SE_SBGENFS; if (!strcmp(sb->s_type->name, "sysfs") || !strcmp(sb->s_type->name, "cgroup") || !strcmp(sb->s_type->name, "cgroup2")) sbsec->flags |= SE_SBGENFS | SE_SBGENFS_XATTR; if (!sbsec->behavior) { /* * Determine the labeling behavior to use for this * filesystem type. */ rc = security_fs_use(&selinux_state, sb); if (rc) { pr_warn("%s: security_fs_use(%s) returned %d\n", __func__, sb->s_type->name, rc); goto out; } } /* * If this is a user namespace mount and the filesystem type is not * explicitly whitelisted, then no contexts are allowed on the command * line and security labels must be ignored. */ if (sb->s_user_ns != &init_user_ns && strcmp(sb->s_type->name, "tmpfs") && strcmp(sb->s_type->name, "ramfs") && strcmp(sb->s_type->name, "devpts")) { if (context_sid || fscontext_sid || rootcontext_sid || defcontext_sid) { rc = -EACCES; goto out; } if (sbsec->behavior == SECURITY_FS_USE_XATTR) { sbsec->behavior = SECURITY_FS_USE_MNTPOINT; rc = security_transition_sid(&selinux_state, current_sid(), current_sid(), SECCLASS_FILE, NULL, &sbsec->mntpoint_sid); if (rc) goto out; } goto out_set_opts; } /* sets the context of the superblock for the fs being mounted. */ if (fscontext_sid) { rc = may_context_mount_sb_relabel(fscontext_sid, sbsec, cred); if (rc) goto out; sbsec->sid = fscontext_sid; } /* * Switch to using mount point labeling behavior. * sets the label used on all file below the mountpoint, and will set * the superblock context if not already set. */ if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !context_sid) { sbsec->behavior = SECURITY_FS_USE_NATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } if (context_sid) { if (!fscontext_sid) { rc = may_context_mount_sb_relabel(context_sid, sbsec, cred); if (rc) goto out; sbsec->sid = context_sid; } else { rc = may_context_mount_inode_relabel(context_sid, sbsec, cred); if (rc) goto out; } if (!rootcontext_sid) rootcontext_sid = context_sid; sbsec->mntpoint_sid = context_sid; sbsec->behavior = SECURITY_FS_USE_MNTPOINT; } if (rootcontext_sid) { rc = may_context_mount_inode_relabel(rootcontext_sid, sbsec, cred); if (rc) goto out; root_isec->sid = rootcontext_sid; root_isec->initialized = LABEL_INITIALIZED; } if (defcontext_sid) { if (sbsec->behavior != SECURITY_FS_USE_XATTR && sbsec->behavior != SECURITY_FS_USE_NATIVE) { rc = -EINVAL; pr_warn("SELinux: defcontext option is " "invalid for this filesystem type\n"); goto out; } if (defcontext_sid != sbsec->def_sid) { rc = may_context_mount_inode_relabel(defcontext_sid, sbsec, cred); if (rc) goto out; } sbsec->def_sid = defcontext_sid; } out_set_opts: rc = sb_finish_set_opts(sb); out: mutex_unlock(&sbsec->lock); return rc; out_double_mount: rc = -EINVAL; pr_warn("SELinux: mount invalid. Same superblock, different " "security settings for (dev %s, type %s)\n", sb->s_id, sb->s_type->name); goto out; } static int selinux_cmp_sb_context(const struct super_block *oldsb, const struct super_block *newsb) { struct superblock_security_struct *old = oldsb->s_security; struct superblock_security_struct *new = newsb->s_security; char oldflags = old->flags & SE_MNTMASK; char newflags = new->flags & SE_MNTMASK; if (oldflags != newflags) goto mismatch; if ((oldflags & FSCONTEXT_MNT) && old->sid != new->sid) goto mismatch; if ((oldflags & CONTEXT_MNT) && old->mntpoint_sid != new->mntpoint_sid) goto mismatch; if ((oldflags & DEFCONTEXT_MNT) && old->def_sid != new->def_sid) goto mismatch; if (oldflags & ROOTCONTEXT_MNT) { struct inode_security_struct *oldroot = backing_inode_security(oldsb->s_root); struct inode_security_struct *newroot = backing_inode_security(newsb->s_root); if (oldroot->sid != newroot->sid) goto mismatch; } return 0; mismatch: pr_warn("SELinux: mount invalid. Same superblock, " "different security settings for (dev %s, " "type %s)\n", newsb->s_id, newsb->s_type->name); return -EBUSY; } static int selinux_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { int rc = 0; const struct superblock_security_struct *oldsbsec = oldsb->s_security; struct superblock_security_struct *newsbsec = newsb->s_security; int set_fscontext = (oldsbsec->flags & FSCONTEXT_MNT); int set_context = (oldsbsec->flags & CONTEXT_MNT); int set_rootcontext = (oldsbsec->flags & ROOTCONTEXT_MNT); /* * if the parent was able to be mounted it clearly had no special lsm * mount options. thus we can safely deal with this superblock later */ if (!selinux_initialized(&selinux_state)) return 0; /* * Specifying internal flags without providing a place to * place the results is not allowed. */ if (kern_flags && !set_kern_flags) return -EINVAL; /* how can we clone if the old one wasn't set up?? */ BUG_ON(!(oldsbsec->flags & SE_SBINITIALIZED)); /* if fs is reusing a sb, make sure that the contexts match */ if (newsbsec->flags & SE_SBINITIALIZED) { if ((kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; return selinux_cmp_sb_context(oldsb, newsb); } mutex_lock(&newsbsec->lock); newsbsec->flags = oldsbsec->flags; newsbsec->sid = oldsbsec->sid; newsbsec->def_sid = oldsbsec->def_sid; newsbsec->behavior = oldsbsec->behavior; if (newsbsec->behavior == SECURITY_FS_USE_NATIVE && !(kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) { rc = security_fs_use(&selinux_state, newsb); if (rc) goto out; } if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !set_context) { newsbsec->behavior = SECURITY_FS_USE_NATIVE; *set_kern_flags |= SECURITY_LSM_NATIVE_LABELS; } if (set_context) { u32 sid = oldsbsec->mntpoint_sid; if (!set_fscontext) newsbsec->sid = sid; if (!set_rootcontext) { struct inode_security_struct *newisec = backing_inode_security(newsb->s_root); newisec->sid = sid; } newsbsec->mntpoint_sid = sid; } if (set_rootcontext) { const struct inode_security_struct *oldisec = backing_inode_security(oldsb->s_root); struct inode_security_struct *newisec = backing_inode_security(newsb->s_root); newisec->sid = oldisec->sid; } sb_finish_set_opts(newsb); out: mutex_unlock(&newsbsec->lock); return rc; } static int selinux_add_opt(int token, const char *s, void **mnt_opts) { struct selinux_mnt_opts *opts = *mnt_opts; bool is_alloc_opts = false; if (token == Opt_seclabel) /* eaten and completely ignored */ return 0; if (!s) return -ENOMEM; if (!opts) { opts = kzalloc(sizeof(struct selinux_mnt_opts), GFP_KERNEL); if (!opts) return -ENOMEM; *mnt_opts = opts; is_alloc_opts = true; } switch (token) { case Opt_context: if (opts->context || opts->defcontext) goto Einval; opts->context = s; break; case Opt_fscontext: if (opts->fscontext) goto Einval; opts->fscontext = s; break; case Opt_rootcontext: if (opts->rootcontext) goto Einval; opts->rootcontext = s; break; case Opt_defcontext: if (opts->context || opts->defcontext) goto Einval; opts->defcontext = s; break; } return 0; Einval: if (is_alloc_opts) { kfree(opts); *mnt_opts = NULL; } pr_warn(SEL_MOUNT_FAIL_MSG); return -EINVAL; } static int selinux_add_mnt_opt(const char *option, const char *val, int len, void **mnt_opts) { int token = Opt_error; int rc, i; for (i = 0; i < ARRAY_SIZE(tokens); i++) { if (strcmp(option, tokens[i].name) == 0) { token = tokens[i].opt; break; } } if (token == Opt_error) return -EINVAL; if (token != Opt_seclabel) { val = kmemdup_nul(val, len, GFP_KERNEL); if (!val) { rc = -ENOMEM; goto free_opt; } } rc = selinux_add_opt(token, val, mnt_opts); if (unlikely(rc)) { kfree(val); goto free_opt; } return rc; free_opt: if (*mnt_opts) { selinux_free_mnt_opts(*mnt_opts); *mnt_opts = NULL; } return rc; } static int show_sid(struct seq_file *m, u32 sid) { char *context = NULL; u32 len; int rc; rc = security_sid_to_context(&selinux_state, sid, &context, &len); if (!rc) { bool has_comma = context && strchr(context, ','); seq_putc(m, '='); if (has_comma) seq_putc(m, '\"'); seq_escape(m, context, "\"\n\\"); if (has_comma) seq_putc(m, '\"'); } kfree(context); return rc; } static int selinux_sb_show_options(struct seq_file *m, struct super_block *sb) { struct superblock_security_struct *sbsec = sb->s_security; int rc; if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; if (!selinux_initialized(&selinux_state)) return 0; if (sbsec->flags & FSCONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, FSCONTEXT_STR); rc = show_sid(m, sbsec->sid); if (rc) return rc; } if (sbsec->flags & CONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, CONTEXT_STR); rc = show_sid(m, sbsec->mntpoint_sid); if (rc) return rc; } if (sbsec->flags & DEFCONTEXT_MNT) { seq_putc(m, ','); seq_puts(m, DEFCONTEXT_STR); rc = show_sid(m, sbsec->def_sid); if (rc) return rc; } if (sbsec->flags & ROOTCONTEXT_MNT) { struct dentry *root = sbsec->sb->s_root; struct inode_security_struct *isec = backing_inode_security(root); seq_putc(m, ','); seq_puts(m, ROOTCONTEXT_STR); rc = show_sid(m, isec->sid); if (rc) return rc; } if (sbsec->flags & SBLABEL_MNT) { seq_putc(m, ','); seq_puts(m, SECLABEL_STR); } return 0; } static inline u16 inode_mode_to_security_class(umode_t mode) { switch (mode & S_IFMT) { case S_IFSOCK: return SECCLASS_SOCK_FILE; case S_IFLNK: return SECCLASS_LNK_FILE; case S_IFREG: return SECCLASS_FILE; case S_IFBLK: return SECCLASS_BLK_FILE; case S_IFDIR: return SECCLASS_DIR; case S_IFCHR: return SECCLASS_CHR_FILE; case S_IFIFO: return SECCLASS_FIFO_FILE; } return SECCLASS_FILE; } static inline int default_protocol_stream(int protocol) { return (protocol == IPPROTO_IP || protocol == IPPROTO_TCP); } static inline int default_protocol_dgram(int protocol) { return (protocol == IPPROTO_IP || protocol == IPPROTO_UDP); } static inline u16 socket_type_to_security_class(int family, int type, int protocol) { int extsockclass = selinux_policycap_extsockclass(); switch (family) { case PF_UNIX: switch (type) { case SOCK_STREAM: case SOCK_SEQPACKET: return SECCLASS_UNIX_STREAM_SOCKET; case SOCK_DGRAM: case SOCK_RAW: return SECCLASS_UNIX_DGRAM_SOCKET; } break; case PF_INET: case PF_INET6: switch (type) { case SOCK_STREAM: case SOCK_SEQPACKET: if (default_protocol_stream(protocol)) return SECCLASS_TCP_SOCKET; else if (extsockclass && protocol == IPPROTO_SCTP) return SECCLASS_SCTP_SOCKET; else return SECCLASS_RAWIP_SOCKET; case SOCK_DGRAM: if (default_protocol_dgram(protocol)) return SECCLASS_UDP_SOCKET; else if (extsockclass && (protocol == IPPROTO_ICMP || protocol == IPPROTO_ICMPV6)) return SECCLASS_ICMP_SOCKET; else return SECCLASS_RAWIP_SOCKET; case SOCK_DCCP: return SECCLASS_DCCP_SOCKET; default: return SECCLASS_RAWIP_SOCKET; } break; case PF_NETLINK: switch (protocol) { case NETLINK_ROUTE: return SECCLASS_NETLINK_ROUTE_SOCKET; case NETLINK_SOCK_DIAG: return SECCLASS_NETLINK_TCPDIAG_SOCKET; case NETLINK_NFLOG: return SECCLASS_NETLINK_NFLOG_SOCKET; case NETLINK_XFRM: return SECCLASS_NETLINK_XFRM_SOCKET; case NETLINK_SELINUX: return SECCLASS_NETLINK_SELINUX_SOCKET; case NETLINK_ISCSI: return SECCLASS_NETLINK_ISCSI_SOCKET; case NETLINK_AUDIT: return SECCLASS_NETLINK_AUDIT_SOCKET; case NETLINK_FIB_LOOKUP: return SECCLASS_NETLINK_FIB_LOOKUP_SOCKET; case NETLINK_CONNECTOR: return SECCLASS_NETLINK_CONNECTOR_SOCKET; case NETLINK_NETFILTER: return SECCLASS_NETLINK_NETFILTER_SOCKET; case NETLINK_DNRTMSG: return SECCLASS_NETLINK_DNRT_SOCKET; case NETLINK_KOBJECT_UEVENT: return SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET; case NETLINK_GENERIC: return SECCLASS_NETLINK_GENERIC_SOCKET; case NETLINK_SCSITRANSPORT: return SECCLASS_NETLINK_SCSITRANSPORT_SOCKET; case NETLINK_RDMA: return SECCLASS_NETLINK_RDMA_SOCKET; case NETLINK_CRYPTO: return SECCLASS_NETLINK_CRYPTO_SOCKET; default: return SECCLASS_NETLINK_SOCKET; } case PF_PACKET: return SECCLASS_PACKET_SOCKET; case PF_KEY: return SECCLASS_KEY_SOCKET; case PF_APPLETALK: return SECCLASS_APPLETALK_SOCKET; } if (extsockclass) { switch (family) { case PF_AX25: return SECCLASS_AX25_SOCKET; case PF_IPX: return SECCLASS_IPX_SOCKET; case PF_NETROM: return SECCLASS_NETROM_SOCKET; case PF_ATMPVC: return SECCLASS_ATMPVC_SOCKET; case PF_X25: return SECCLASS_X25_SOCKET; case PF_ROSE: return SECCLASS_ROSE_SOCKET; case PF_DECnet: return SECCLASS_DECNET_SOCKET; case PF_ATMSVC: return SECCLASS_ATMSVC_SOCKET; case PF_RDS: return SECCLASS_RDS_SOCKET; case PF_IRDA: return SECCLASS_IRDA_SOCKET; case PF_PPPOX: return SECCLASS_PPPOX_SOCKET; case PF_LLC: return SECCLASS_LLC_SOCKET; case PF_CAN: return SECCLASS_CAN_SOCKET; case PF_TIPC: return SECCLASS_TIPC_SOCKET; case PF_BLUETOOTH: return SECCLASS_BLUETOOTH_SOCKET; case PF_IUCV: return SECCLASS_IUCV_SOCKET; case PF_RXRPC: return SECCLASS_RXRPC_SOCKET; case PF_ISDN: return SECCLASS_ISDN_SOCKET; case PF_PHONET: return SECCLASS_PHONET_SOCKET; case PF_IEEE802154: return SECCLASS_IEEE802154_SOCKET; case PF_CAIF: return SECCLASS_CAIF_SOCKET; case PF_ALG: return SECCLASS_ALG_SOCKET; case PF_NFC: return SECCLASS_NFC_SOCKET; case PF_VSOCK: return SECCLASS_VSOCK_SOCKET; case PF_KCM: return SECCLASS_KCM_SOCKET; case PF_QIPCRTR: return SECCLASS_QIPCRTR_SOCKET; case PF_SMC: return SECCLASS_SMC_SOCKET; case PF_XDP: return SECCLASS_XDP_SOCKET; #if PF_MAX > 45 #error New address family defined, please update this function. #endif } } return SECCLASS_SOCKET; } static int selinux_genfs_get_sid(struct dentry *dentry, u16 tclass, u16 flags, u32 *sid) { int rc; struct super_block *sb = dentry->d_sb; char *buffer, *path; buffer = (char *)__get_free_page(GFP_KERNEL); if (!buffer) return -ENOMEM; path = dentry_path_raw(dentry, buffer, PAGE_SIZE); if (IS_ERR(path)) rc = PTR_ERR(path); else { if (flags & SE_SBPROC) { /* each process gets a /proc/PID/ entry. Strip off the * PID part to get a valid selinux labeling. * e.g. /proc/1/net/rpc/nfs -> /net/rpc/nfs */ while (path[1] >= '0' && path[1] <= '9') { path[1] = '/'; path++; } } rc = security_genfs_sid(&selinux_state, sb->s_type->name, path, tclass, sid); if (rc == -ENOENT) { /* No match in policy, mark as unlabeled. */ *sid = SECINITSID_UNLABELED; rc = 0; } } free_page((unsigned long)buffer); return rc; } static int inode_doinit_use_xattr(struct inode *inode, struct dentry *dentry, u32 def_sid, u32 *sid) { #define INITCONTEXTLEN 255 char *context; unsigned int len; int rc; len = INITCONTEXTLEN; context = kmalloc(len + 1, GFP_NOFS); if (!context) return -ENOMEM; context[len] = '\0'; rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len); if (rc == -ERANGE) { kfree(context); /* Need a larger buffer. Query for the right size. */ rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, NULL, 0); if (rc < 0) return rc; len = rc; context = kmalloc(len + 1, GFP_NOFS); if (!context) return -ENOMEM; context[len] = '\0'; rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len); } if (rc < 0) { kfree(context); if (rc != -ENODATA) { pr_warn("SELinux: %s: getxattr returned %d for dev=%s ino=%ld\n", __func__, -rc, inode->i_sb->s_id, inode->i_ino); return rc; } *sid = def_sid; return 0; } rc = security_context_to_sid_default(&selinux_state, context, rc, sid, def_sid, GFP_NOFS); if (rc) { char *dev = inode->i_sb->s_id; unsigned long ino = inode->i_ino; if (rc == -EINVAL) { pr_notice_ratelimited("SELinux: inode=%lu on dev=%s was found to have an invalid context=%s. This indicates you may need to relabel the inode or the filesystem in question.\n", ino, dev, context); } else { pr_warn("SELinux: %s: context_to_sid(%s) returned %d for dev=%s ino=%ld\n", __func__, context, -rc, dev, ino); } } kfree(context); return 0; } /* The inode's security attributes must be initialized before first use. */ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry) { struct superblock_security_struct *sbsec = NULL; struct inode_security_struct *isec = selinux_inode(inode); u32 task_sid, sid = 0; u16 sclass; struct dentry *dentry; int rc = 0; if (isec->initialized == LABEL_INITIALIZED) return 0; spin_lock(&isec->lock); if (isec->initialized == LABEL_INITIALIZED) goto out_unlock; if (isec->sclass == SECCLASS_FILE) isec->sclass = inode_mode_to_security_class(inode->i_mode); sbsec = inode->i_sb->s_security; if (!(sbsec->flags & SE_SBINITIALIZED)) { /* Defer initialization until selinux_complete_init, after the initial policy is loaded and the security server is ready to handle calls. */ spin_lock(&sbsec->isec_lock); if (list_empty(&isec->list)) list_add(&isec->list, &sbsec->isec_head); spin_unlock(&sbsec->isec_lock); goto out_unlock; } sclass = isec->sclass; task_sid = isec->task_sid; sid = isec->sid; isec->initialized = LABEL_PENDING; spin_unlock(&isec->lock); switch (sbsec->behavior) { case SECURITY_FS_USE_NATIVE: break; case SECURITY_FS_USE_XATTR: if (!(inode->i_opflags & IOP_XATTR)) { sid = sbsec->def_sid; break; } /* Need a dentry, since the xattr API requires one. Life would be simpler if we could just pass the inode. */ if (opt_dentry) { /* Called from d_instantiate or d_splice_alias. */ dentry = dget(opt_dentry); } else { /* * Called from selinux_complete_init, try to find a dentry. * Some filesystems really want a connected one, so try * that first. We could split SECURITY_FS_USE_XATTR in * two, depending upon that... */ dentry = d_find_alias(inode); if (!dentry) dentry = d_find_any_alias(inode); } if (!dentry) { /* * this is can be hit on boot when a file is accessed * before the policy is loaded. When we load policy we * may find inodes that have no dentry on the * sbsec->isec_head list. No reason to complain as these * will get fixed up the next time we go through * inode_doinit with a dentry, before these inodes could * be used again by userspace. */ goto out_invalid; } rc = inode_doinit_use_xattr(inode, dentry, sbsec->def_sid, &sid); dput(dentry); if (rc) goto out; break; case SECURITY_FS_USE_TASK: sid = task_sid; break; case SECURITY_FS_USE_TRANS: /* Default to the fs SID. */ sid = sbsec->sid; /* Try to obtain a transition SID. */ rc = security_transition_sid(&selinux_state, task_sid, sid, sclass, NULL, &sid); if (rc) goto out; break; case SECURITY_FS_USE_MNTPOINT: sid = sbsec->mntpoint_sid; break; default: /* Default to the fs superblock SID. */ sid = sbsec->sid; if ((sbsec->flags & SE_SBGENFS) && (!S_ISLNK(inode->i_mode) || selinux_policycap_genfs_seclabel_symlinks())) { /* We must have a dentry to determine the label on * procfs inodes */ if (opt_dentry) { /* Called from d_instantiate or * d_splice_alias. */ dentry = dget(opt_dentry); } else { /* Called from selinux_complete_init, try to * find a dentry. Some filesystems really want * a connected one, so try that first. */ dentry = d_find_alias(inode); if (!dentry) dentry = d_find_any_alias(inode); } /* * This can be hit on boot when a file is accessed * before the policy is loaded. When we load policy we * may find inodes that have no dentry on the * sbsec->isec_head list. No reason to complain as * these will get fixed up the next time we go through * inode_doinit() with a dentry, before these inodes * could be used again by userspace. */ if (!dentry) goto out_invalid; rc = selinux_genfs_get_sid(dentry, sclass, sbsec->flags, &sid); if (rc) { dput(dentry); goto out; } if ((sbsec->flags & SE_SBGENFS_XATTR) && (inode->i_opflags & IOP_XATTR)) { rc = inode_doinit_use_xattr(inode, dentry, sid, &sid); if (rc) { dput(dentry); goto out; } } dput(dentry); } break; } out: spin_lock(&isec->lock); if (isec->initialized == LABEL_PENDING) { if (rc) { isec->initialized = LABEL_INVALID; goto out_unlock; } isec->initialized = LABEL_INITIALIZED; isec->sid = sid; } out_unlock: spin_unlock(&isec->lock); return rc; out_invalid: spin_lock(&isec->lock); if (isec->initialized == LABEL_PENDING) { isec->initialized = LABEL_INVALID; isec->sid = sid; } spin_unlock(&isec->lock); return 0; } /* Convert a Linux signal to an access vector. */ static inline u32 signal_to_av(int sig) { u32 perm = 0; switch (sig) { case SIGCHLD: /* Commonly granted from child to parent. */ perm = PROCESS__SIGCHLD; break; case SIGKILL: /* Cannot be caught or ignored */ perm = PROCESS__SIGKILL; break; case SIGSTOP: /* Cannot be caught or ignored */ perm = PROCESS__SIGSTOP; break; default: /* All other signals. */ perm = PROCESS__SIGNAL; break; } return perm; } #if CAP_LAST_CAP > 63 #error Fix SELinux to handle capabilities > 63. #endif /* Check whether a task is allowed to use a capability. */ static int cred_has_capability(const struct cred *cred, int cap, unsigned int opts, bool initns) { struct common_audit_data ad; struct av_decision avd; u16 sclass; u32 sid = cred_sid(cred); u32 av = CAP_TO_MASK(cap); int rc; ad.type = LSM_AUDIT_DATA_CAP; ad.u.cap = cap; switch (CAP_TO_INDEX(cap)) { case 0: sclass = initns ? SECCLASS_CAPABILITY : SECCLASS_CAP_USERNS; break; case 1: sclass = initns ? SECCLASS_CAPABILITY2 : SECCLASS_CAP2_USERNS; break; default: pr_err("SELinux: out of range capability %d\n", cap); BUG(); return -EINVAL; } rc = avc_has_perm_noaudit(&selinux_state, sid, sid, sclass, av, 0, &avd); if (!(opts & CAP_OPT_NOAUDIT)) { int rc2 = avc_audit(&selinux_state, sid, sid, sclass, av, &avd, rc, &ad, 0); if (rc2) return rc2; } return rc; } /* Check whether a task has a particular permission to an inode. The 'adp' parameter is optional and allows other audit data to be passed (e.g. the dentry). */ static int inode_has_perm(const struct cred *cred, struct inode *inode, u32 perms, struct common_audit_data *adp) { struct inode_security_struct *isec; u32 sid; validate_creds(cred); if (unlikely(IS_PRIVATE(inode))) return 0; sid = cred_sid(cred); isec = selinux_inode(inode); return avc_has_perm(&selinux_state, sid, isec->sid, isec->sclass, perms, adp); } /* Same as inode_has_perm, but pass explicit audit data containing the dentry to help the auditing code to more easily generate the pathname if needed. */ static inline int dentry_has_perm(const struct cred *cred, struct dentry *dentry, u32 av) { struct inode *inode = d_backing_inode(dentry); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; __inode_security_revalidate(inode, dentry, true); return inode_has_perm(cred, inode, av, &ad); } /* Same as inode_has_perm, but pass explicit audit data containing the path to help the auditing code to more easily generate the pathname if needed. */ static inline int path_has_perm(const struct cred *cred, const struct path *path, u32 av) { struct inode *inode = d_backing_inode(path->dentry); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; __inode_security_revalidate(inode, path->dentry, true); return inode_has_perm(cred, inode, av, &ad); } /* Same as path_has_perm, but uses the inode from the file struct. */ static inline int file_path_has_perm(const struct cred *cred, struct file *file, u32 av) { struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; return inode_has_perm(cred, file_inode(file), av, &ad); } #ifdef CONFIG_BPF_SYSCALL static int bpf_fd_pass(struct file *file, u32 sid); #endif /* Check whether a task can use an open file descriptor to access an inode in a given way. Check access to the descriptor itself, and then use dentry_has_perm to check a particular permission to the file. Access to the descriptor is implicitly granted if it has the same SID as the process. If av is zero, then access to the file is not checked, e.g. for cases where only the descriptor is affected like seek. */ static int file_has_perm(const struct cred *cred, struct file *file, u32 av) { struct file_security_struct *fsec = selinux_file(file); struct inode *inode = file_inode(file); struct common_audit_data ad; u32 sid = cred_sid(cred); int rc; ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; if (sid != fsec->sid) { rc = avc_has_perm(&selinux_state, sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) goto out; } #ifdef CONFIG_BPF_SYSCALL rc = bpf_fd_pass(file, cred_sid(cred)); if (rc) return rc; #endif /* av is zero if only checking access to the descriptor. */ rc = 0; if (av) rc = inode_has_perm(cred, inode, av, &ad); out: return rc; } /* * Determine the label for an inode that might be unioned. */ static int selinux_determine_inode_label(const struct task_security_struct *tsec, struct inode *dir, const struct qstr *name, u16 tclass, u32 *_new_isid) { const struct superblock_security_struct *sbsec = dir->i_sb->s_security; if ((sbsec->flags & SE_SBINITIALIZED) && (sbsec->behavior == SECURITY_FS_USE_MNTPOINT)) { *_new_isid = sbsec->mntpoint_sid; } else if ((sbsec->flags & SBLABEL_MNT) && tsec->create_sid) { *_new_isid = tsec->create_sid; } else { const struct inode_security_struct *dsec = inode_security(dir); return security_transition_sid(&selinux_state, tsec->sid, dsec->sid, tclass, name, _new_isid); } return 0; } /* Check whether a task can create a file. */ static int may_create(struct inode *dir, struct dentry *dentry, u16 tclass) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct inode_security_struct *dsec; struct superblock_security_struct *sbsec; u32 sid, newsid; struct common_audit_data ad; int rc; dsec = inode_security(dir); sbsec = dir->i_sb->s_security; sid = tsec->sid; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; rc = avc_has_perm(&selinux_state, sid, dsec->sid, SECCLASS_DIR, DIR__ADD_NAME | DIR__SEARCH, &ad); if (rc) return rc; rc = selinux_determine_inode_label(tsec, dir, &dentry->d_name, tclass, &newsid); if (rc) return rc; rc = avc_has_perm(&selinux_state, sid, newsid, tclass, FILE__CREATE, &ad); if (rc) return rc; return avc_has_perm(&selinux_state, newsid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, &ad); } #define MAY_LINK 0 #define MAY_UNLINK 1 #define MAY_RMDIR 2 /* Check whether a task can link, unlink, or rmdir a file/directory. */ static int may_link(struct inode *dir, struct dentry *dentry, int kind) { struct inode_security_struct *dsec, *isec; struct common_audit_data ad; u32 sid = current_sid(); u32 av; int rc; dsec = inode_security(dir); isec = backing_inode_security(dentry); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; av = DIR__SEARCH; av |= (kind ? DIR__REMOVE_NAME : DIR__ADD_NAME); rc = avc_has_perm(&selinux_state, sid, dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; switch (kind) { case MAY_LINK: av = FILE__LINK; break; case MAY_UNLINK: av = FILE__UNLINK; break; case MAY_RMDIR: av = DIR__RMDIR; break; default: pr_warn("SELinux: %s: unrecognized kind %d\n", __func__, kind); return 0; } rc = avc_has_perm(&selinux_state, sid, isec->sid, isec->sclass, av, &ad); return rc; } static inline int may_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct inode_security_struct *old_dsec, *new_dsec, *old_isec, *new_isec; struct common_audit_data ad; u32 sid = current_sid(); u32 av; int old_is_dir, new_is_dir; int rc; old_dsec = inode_security(old_dir); old_isec = backing_inode_security(old_dentry); old_is_dir = d_is_dir(old_dentry); new_dsec = inode_security(new_dir); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = old_dentry; rc = avc_has_perm(&selinux_state, sid, old_dsec->sid, SECCLASS_DIR, DIR__REMOVE_NAME | DIR__SEARCH, &ad); if (rc) return rc; rc = avc_has_perm(&selinux_state, sid, old_isec->sid, old_isec->sclass, FILE__RENAME, &ad); if (rc) return rc; if (old_is_dir && new_dir != old_dir) { rc = avc_has_perm(&selinux_state, sid, old_isec->sid, old_isec->sclass, DIR__REPARENT, &ad); if (rc) return rc; } ad.u.dentry = new_dentry; av = DIR__ADD_NAME | DIR__SEARCH; if (d_is_positive(new_dentry)) av |= DIR__REMOVE_NAME; rc = avc_has_perm(&selinux_state, sid, new_dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; if (d_is_positive(new_dentry)) { new_isec = backing_inode_security(new_dentry); new_is_dir = d_is_dir(new_dentry); rc = avc_has_perm(&selinux_state, sid, new_isec->sid, new_isec->sclass, (new_is_dir ? DIR__RMDIR : FILE__UNLINK), &ad); if (rc) return rc; } return 0; } /* Check whether a task can perform a filesystem operation. */ static int superblock_has_perm(const struct cred *cred, struct super_block *sb, u32 perms, struct common_audit_data *ad) { struct superblock_security_struct *sbsec; u32 sid = cred_sid(cred); sbsec = sb->s_security; return avc_has_perm(&selinux_state, sid, sbsec->sid, SECCLASS_FILESYSTEM, perms, ad); } /* Convert a Linux mode and permission mask to an access vector. */ static inline u32 file_mask_to_av(int mode, int mask) { u32 av = 0; if (!S_ISDIR(mode)) { if (mask & MAY_EXEC) av |= FILE__EXECUTE; if (mask & MAY_READ) av |= FILE__READ; if (mask & MAY_APPEND) av |= FILE__APPEND; else if (mask & MAY_WRITE) av |= FILE__WRITE; } else { if (mask & MAY_EXEC) av |= DIR__SEARCH; if (mask & MAY_WRITE) av |= DIR__WRITE; if (mask & MAY_READ) av |= DIR__READ; } return av; } /* Convert a Linux file to an access vector. */ static inline u32 file_to_av(struct file *file) { u32 av = 0; if (file->f_mode & FMODE_READ) av |= FILE__READ; if (file->f_mode & FMODE_WRITE) { if (file->f_flags & O_APPEND) av |= FILE__APPEND; else av |= FILE__WRITE; } if (!av) { /* * Special file opened with flags 3 for ioctl-only use. */ av = FILE__IOCTL; } return av; } /* * Convert a file to an access vector and include the correct * open permission. */ static inline u32 open_file_to_av(struct file *file) { u32 av = file_to_av(file); struct inode *inode = file_inode(file); if (selinux_policycap_openperm() && inode->i_sb->s_magic != SOCKFS_MAGIC) av |= FILE__OPEN; return av; } /* Hook functions begin here. */ static int selinux_binder_set_context_mgr(const struct cred *mgr) { return avc_has_perm(&selinux_state, current_sid(), cred_sid(mgr), SECCLASS_BINDER, BINDER__SET_CONTEXT_MGR, NULL); } static int selinux_binder_transaction(const struct cred *from, const struct cred *to) { u32 mysid = current_sid(); u32 fromsid = cred_sid(from); u32 tosid = cred_sid(to); int rc; if (mysid != fromsid) { rc = avc_has_perm(&selinux_state, mysid, fromsid, SECCLASS_BINDER, BINDER__IMPERSONATE, NULL); if (rc) return rc; } return avc_has_perm(&selinux_state, fromsid, tosid, SECCLASS_BINDER, BINDER__CALL, NULL); } static int selinux_binder_transfer_binder(const struct cred *from, const struct cred *to) { return avc_has_perm(&selinux_state, cred_sid(from), cred_sid(to), SECCLASS_BINDER, BINDER__TRANSFER, NULL); } static int selinux_binder_transfer_file(const struct cred *from, const struct cred *to, struct file *file) { u32 sid = cred_sid(to); struct file_security_struct *fsec = selinux_file(file); struct dentry *dentry = file->f_path.dentry; struct inode_security_struct *isec; struct common_audit_data ad; int rc; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = file->f_path; if (sid != fsec->sid) { rc = avc_has_perm(&selinux_state, sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) return rc; } #ifdef CONFIG_BPF_SYSCALL rc = bpf_fd_pass(file, sid); if (rc) return rc; #endif if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; isec = backing_inode_security(dentry); return avc_has_perm(&selinux_state, sid, isec->sid, isec->sclass, file_to_av(file), &ad); } static int selinux_ptrace_access_check(struct task_struct *child, unsigned int mode) { u32 sid = current_sid(); u32 csid = task_sid(child); if (mode & PTRACE_MODE_READ) return avc_has_perm(&selinux_state, sid, csid, SECCLASS_FILE, FILE__READ, NULL); return avc_has_perm(&selinux_state, sid, csid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } static int selinux_ptrace_traceme(struct task_struct *parent) { return avc_has_perm(&selinux_state, task_sid(parent), current_sid(), SECCLASS_PROCESS, PROCESS__PTRACE, NULL); } static int selinux_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return avc_has_perm(&selinux_state, current_sid(), task_sid(target), SECCLASS_PROCESS, PROCESS__GETCAP, NULL); } static int selinux_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return avc_has_perm(&selinux_state, cred_sid(old), cred_sid(new), SECCLASS_PROCESS, PROCESS__SETCAP, NULL); } /* * (This comment used to live with the selinux_task_setuid hook, * which was removed). * * Since setuid only affects the current process, and since the SELinux * controls are not based on the Linux identity attributes, SELinux does not * need to control this operation. However, SELinux does control the use of * the CAP_SETUID and CAP_SETGID capabilities using the capable hook. */ static int selinux_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return cred_has_capability(cred, cap, opts, ns == &init_user_ns); } static int selinux_quotactl(int cmds, int type, int id, struct super_block *sb) { const struct cred *cred = current_cred(); int rc = 0; if (!sb) return 0; switch (cmds) { case Q_SYNC: case Q_QUOTAON: case Q_QUOTAOFF: case Q_SETINFO: case Q_SETQUOTA: case Q_XQUOTAOFF: case Q_XQUOTAON: case Q_XSETQLIM: rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAMOD, NULL); break; case Q_GETFMT: case Q_GETINFO: case Q_GETQUOTA: case Q_XGETQUOTA: case Q_XGETQSTAT: case Q_XGETQSTATV: case Q_XGETNEXTQUOTA: rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAGET, NULL); break; default: rc = 0; /* let the kernel handle invalid cmds */ break; } return rc; } static int selinux_quota_on(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__QUOTAON); } static int selinux_syslog(int type) { switch (type) { case SYSLOG_ACTION_READ_ALL: /* Read last kernel messages */ case SYSLOG_ACTION_SIZE_BUFFER: /* Return size of the log buffer */ return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_READ, NULL); case SYSLOG_ACTION_CONSOLE_OFF: /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: /* Enable logging to console */ /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_CONSOLE, NULL); } /* All other syslog types */ return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__SYSLOG_MOD, NULL); } /* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to * succeed and -ENOMEM implies there is not. * * Do not audit the selinux permission check, as this is applied to all * processes that allocate mappings. */ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages) { int rc, cap_sys_admin = 0; rc = cred_has_capability(current_cred(), CAP_SYS_ADMIN, CAP_OPT_NOAUDIT, true); if (rc == 0) cap_sys_admin = 1; return cap_sys_admin; } /* binprm security operations */ static u32 ptrace_parent_sid(void) { u32 sid = 0; struct task_struct *tracer; rcu_read_lock(); tracer = ptrace_parent(current); if (tracer) sid = task_sid(tracer); rcu_read_unlock(); return sid; } static int check_nnp_nosuid(const struct linux_binprm *bprm, const struct task_security_struct *old_tsec, const struct task_security_struct *new_tsec) { int nnp = (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS); int nosuid = !mnt_may_suid(bprm->file->f_path.mnt); int rc; u32 av; if (!nnp && !nosuid) return 0; /* neither NNP nor nosuid */ if (new_tsec->sid == old_tsec->sid) return 0; /* No change in credentials */ /* * If the policy enables the nnp_nosuid_transition policy capability, * then we permit transitions under NNP or nosuid if the * policy allows the corresponding permission between * the old and new contexts. */ if (selinux_policycap_nnp_nosuid_transition()) { av = 0; if (nnp) av |= PROCESS2__NNP_TRANSITION; if (nosuid) av |= PROCESS2__NOSUID_TRANSITION; rc = avc_has_perm(&selinux_state, old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS2, av, NULL); if (!rc) return 0; } /* * We also permit NNP or nosuid transitions to bounded SIDs, * i.e. SIDs that are guaranteed to only be allowed a subset * of the permissions of the current SID. */ rc = security_bounded_transition(&selinux_state, old_tsec->sid, new_tsec->sid); if (!rc) return 0; /* * On failure, preserve the errno values for NNP vs nosuid. * NNP: Operation not permitted for caller. * nosuid: Permission denied to file. */ if (nnp) return -EPERM; return -EACCES; } static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm) { const struct task_security_struct *old_tsec; struct task_security_struct *new_tsec; struct inode_security_struct *isec; struct common_audit_data ad; struct inode *inode = file_inode(bprm->file); int rc; /* SELinux context only depends on initial program or script and not * the script interpreter */ old_tsec = selinux_cred(current_cred()); new_tsec = selinux_cred(bprm->cred); isec = inode_security(inode); /* Default to the current task SID. */ new_tsec->sid = old_tsec->sid; new_tsec->osid = old_tsec->sid; /* Reset fs, key, and sock SIDs on execve. */ new_tsec->create_sid = 0; new_tsec->keycreate_sid = 0; new_tsec->sockcreate_sid = 0; if (old_tsec->exec_sid) { new_tsec->sid = old_tsec->exec_sid; /* Reset exec SID on execve. */ new_tsec->exec_sid = 0; /* Fail on NNP or nosuid if not an allowed transition. */ rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); if (rc) return rc; } else { /* Check for a default transition on this program. */ rc = security_transition_sid(&selinux_state, old_tsec->sid, isec->sid, SECCLASS_PROCESS, NULL, &new_tsec->sid); if (rc) return rc; /* * Fallback to old SID on NNP or nosuid if not an allowed * transition. */ rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); if (rc) new_tsec->sid = old_tsec->sid; } ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = bprm->file; if (new_tsec->sid == old_tsec->sid) { rc = avc_has_perm(&selinux_state, old_tsec->sid, isec->sid, SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, &ad); if (rc) return rc; } else { /* Check permissions for the transition. */ rc = avc_has_perm(&selinux_state, old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__TRANSITION, &ad); if (rc) return rc; rc = avc_has_perm(&selinux_state, new_tsec->sid, isec->sid, SECCLASS_FILE, FILE__ENTRYPOINT, &ad); if (rc) return rc; /* Check for shared state */ if (bprm->unsafe & LSM_UNSAFE_SHARE) { rc = avc_has_perm(&selinux_state, old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__SHARE, NULL); if (rc) return -EPERM; } /* Make sure that anyone attempting to ptrace over a task that * changes its SID has the appropriate permit */ if (bprm->unsafe & LSM_UNSAFE_PTRACE) { u32 ptsid = ptrace_parent_sid(); if (ptsid != 0) { rc = avc_has_perm(&selinux_state, ptsid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (rc) return -EPERM; } } /* Clear any possibly unsafe personality bits on exec: */ bprm->per_clear |= PER_CLEAR_ON_SETID; /* Enable secure mode for SIDs transitions unless the noatsecure permission is granted between the two SIDs, i.e. ahp returns 0. */ rc = avc_has_perm(&selinux_state, old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__NOATSECURE, NULL); bprm->secureexec |= !!rc; } return 0; } static int match_file(const void *p, struct file *file, unsigned fd) { return file_has_perm(p, file, file_to_av(file)) ? fd + 1 : 0; } /* Derived from fs/exec.c:flush_old_files. */ static inline void flush_unauthorized_files(const struct cred *cred, struct files_struct *files) { struct file *file, *devnull = NULL; struct tty_struct *tty; int drop_tty = 0; unsigned n; tty = get_current_tty(); if (tty) { spin_lock(&tty->files_lock); if (!list_empty(&tty->tty_files)) { struct tty_file_private *file_priv; /* Revalidate access to controlling tty. Use file_path_has_perm on the tty path directly rather than using file_has_perm, as this particular open file may belong to another process and we are only interested in the inode-based check here. */ file_priv = list_first_entry(&tty->tty_files, struct tty_file_private, list); file = file_priv->file; if (file_path_has_perm(cred, file, FILE__READ | FILE__WRITE)) drop_tty = 1; } spin_unlock(&tty->files_lock); tty_kref_put(tty); } /* Reset controlling tty. */ if (drop_tty) no_tty(); /* Revalidate access to inherited open files. */ n = iterate_fd(files, 0, match_file, cred); if (!n) /* none found? */ return; devnull = dentry_open(&selinux_null, O_RDWR, cred); if (IS_ERR(devnull)) devnull = NULL; /* replace all the matching ones with this */ do { replace_fd(n - 1, devnull, 0); } while ((n = iterate_fd(files, n, match_file, cred)) != 0); if (devnull) fput(devnull); } /* * Prepare a process for imminent new credential changes due to exec */ static void selinux_bprm_committing_creds(struct linux_binprm *bprm) { struct task_security_struct *new_tsec; struct rlimit *rlim, *initrlim; int rc, i; new_tsec = selinux_cred(bprm->cred); if (new_tsec->sid == new_tsec->osid) return; /* Close files for which the new task SID is not authorized. */ flush_unauthorized_files(bprm->cred, current->files); /* Always clear parent death signal on SID transitions. */ current->pdeath_signal = 0; /* Check whether the new SID can inherit resource limits from the old * SID. If not, reset all soft limits to the lower of the current * task's hard limit and the init task's soft limit. * * Note that the setting of hard limits (even to lower them) can be * controlled by the setrlimit check. The inclusion of the init task's * soft limit into the computation is to avoid resetting soft limits * higher than the default soft limit for cases where the default is * lower than the hard limit, e.g. RLIMIT_CORE or RLIMIT_STACK. */ rc = avc_has_perm(&selinux_state, new_tsec->osid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__RLIMITINH, NULL); if (rc) { /* protect against do_prlimit() */ task_lock(current); for (i = 0; i < RLIM_NLIMITS; i++) { rlim = current->signal->rlim + i; initrlim = init_task.signal->rlim + i; rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur); } task_unlock(current); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) update_rlimit_cpu(current, rlimit(RLIMIT_CPU)); } } /* * Clean up the process immediately after the installation of new credentials * due to exec */ static void selinux_bprm_committed_creds(struct linux_binprm *bprm) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 osid, sid; int rc; osid = tsec->osid; sid = tsec->sid; if (sid == osid) return; /* Check whether the new SID can inherit signal state from the old SID. * If not, clear itimers to avoid subsequent signal generation and * flush and unblock signals. * * This must occur _after_ the task SID has been updated so that any * kill done after the flush will be checked against the new SID. */ rc = avc_has_perm(&selinux_state, osid, sid, SECCLASS_PROCESS, PROCESS__SIGINH, NULL); if (rc) { clear_itimer(); spin_lock_irq(¤t->sighand->siglock); if (!fatal_signal_pending(current)) { flush_sigqueue(¤t->pending); flush_sigqueue(¤t->signal->shared_pending); flush_signal_handlers(current, 1); sigemptyset(¤t->blocked); recalc_sigpending(); } spin_unlock_irq(¤t->sighand->siglock); } /* Wake up the parent if it is waiting so that it can recheck * wait permission to the new task SID. */ read_lock(&tasklist_lock); __wake_up_parent(current, current->real_parent); read_unlock(&tasklist_lock); } /* superblock security operations */ static int selinux_sb_alloc_security(struct super_block *sb) { struct superblock_security_struct *sbsec; sbsec = kzalloc(sizeof(struct superblock_security_struct), GFP_KERNEL); if (!sbsec) return -ENOMEM; mutex_init(&sbsec->lock); INIT_LIST_HEAD(&sbsec->isec_head); spin_lock_init(&sbsec->isec_lock); sbsec->sb = sb; sbsec->sid = SECINITSID_UNLABELED; sbsec->def_sid = SECINITSID_FILE; sbsec->mntpoint_sid = SECINITSID_UNLABELED; sb->s_security = sbsec; return 0; } static void selinux_sb_free_security(struct super_block *sb) { superblock_free_security(sb); } static inline int opt_len(const char *s) { bool open_quote = false; int len; char c; for (len = 0; (c = s[len]) != '\0'; len++) { if (c == '"') open_quote = !open_quote; if (c == ',' && !open_quote) break; } return len; } static int selinux_sb_eat_lsm_opts(char *options, void **mnt_opts) { char *from = options; char *to = options; bool first = true; int rc; while (1) { int len = opt_len(from); int token; char *arg = NULL; token = match_opt_prefix(from, len, &arg); if (token != Opt_error) { char *p, *q; /* strip quotes */ if (arg) { for (p = q = arg; p < from + len; p++) { char c = *p; if (c != '"') *q++ = c; } arg = kmemdup_nul(arg, q - arg, GFP_KERNEL); if (!arg) { rc = -ENOMEM; goto free_opt; } } rc = selinux_add_opt(token, arg, mnt_opts); if (unlikely(rc)) { kfree(arg); goto free_opt; } } else { if (!first) { // copy with preceding comma from--; len++; } if (to != from) memmove(to, from, len); to += len; first = false; } if (!from[len]) break; from += len + 1; } *to = '\0'; return 0; free_opt: if (*mnt_opts) { selinux_free_mnt_opts(*mnt_opts); *mnt_opts = NULL; } return rc; } static int selinux_sb_remount(struct super_block *sb, void *mnt_opts) { struct selinux_mnt_opts *opts = mnt_opts; struct superblock_security_struct *sbsec = sb->s_security; u32 sid; int rc; if (!(sbsec->flags & SE_SBINITIALIZED)) return 0; if (!opts) return 0; if (opts->fscontext) { rc = parse_sid(sb, opts->fscontext, &sid); if (rc) return rc; if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, sid)) goto out_bad_option; } if (opts->context) { rc = parse_sid(sb, opts->context, &sid); if (rc) return rc; if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, sid)) goto out_bad_option; } if (opts->rootcontext) { struct inode_security_struct *root_isec; root_isec = backing_inode_security(sb->s_root); rc = parse_sid(sb, opts->rootcontext, &sid); if (rc) return rc; if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, sid)) goto out_bad_option; } if (opts->defcontext) { rc = parse_sid(sb, opts->defcontext, &sid); if (rc) return rc; if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, sid)) goto out_bad_option; } return 0; out_bad_option: pr_warn("SELinux: unable to change security options " "during remount (dev %s, type=%s)\n", sb->s_id, sb->s_type->name); return -EINVAL; } static int selinux_sb_kern_mount(struct super_block *sb) { const struct cred *cred = current_cred(); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = sb->s_root; return superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad); } static int selinux_sb_statfs(struct dentry *dentry) { const struct cred *cred = current_cred(); struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry->d_sb->s_root; return superblock_has_perm(cred, dentry->d_sb, FILESYSTEM__GETATTR, &ad); } static int selinux_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { const struct cred *cred = current_cred(); if (flags & MS_REMOUNT) return superblock_has_perm(cred, path->dentry->d_sb, FILESYSTEM__REMOUNT, NULL); else return path_has_perm(cred, path, FILE__MOUNTON); } static int selinux_move_mount(const struct path *from_path, const struct path *to_path) { const struct cred *cred = current_cred(); return path_has_perm(cred, to_path, FILE__MOUNTON); } static int selinux_umount(struct vfsmount *mnt, int flags) { const struct cred *cred = current_cred(); return superblock_has_perm(cred, mnt->mnt_sb, FILESYSTEM__UNMOUNT, NULL); } static int selinux_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { const struct selinux_mnt_opts *src = src_fc->security; struct selinux_mnt_opts *opts; if (!src) return 0; fc->security = kzalloc(sizeof(struct selinux_mnt_opts), GFP_KERNEL); if (!fc->security) return -ENOMEM; opts = fc->security; if (src->fscontext) { opts->fscontext = kstrdup(src->fscontext, GFP_KERNEL); if (!opts->fscontext) return -ENOMEM; } if (src->context) { opts->context = kstrdup(src->context, GFP_KERNEL); if (!opts->context) return -ENOMEM; } if (src->rootcontext) { opts->rootcontext = kstrdup(src->rootcontext, GFP_KERNEL); if (!opts->rootcontext) return -ENOMEM; } if (src->defcontext) { opts->defcontext = kstrdup(src->defcontext, GFP_KERNEL); if (!opts->defcontext) return -ENOMEM; } return 0; } static const struct fs_parameter_spec selinux_fs_parameters[] = { fsparam_string(CONTEXT_STR, Opt_context), fsparam_string(DEFCONTEXT_STR, Opt_defcontext), fsparam_string(FSCONTEXT_STR, Opt_fscontext), fsparam_string(ROOTCONTEXT_STR, Opt_rootcontext), fsparam_flag (SECLABEL_STR, Opt_seclabel), {} }; static int selinux_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct fs_parse_result result; int opt, rc; opt = fs_parse(fc, selinux_fs_parameters, param, &result); if (opt < 0) return opt; rc = selinux_add_opt(opt, param->string, &fc->security); if (!rc) param->string = NULL; return rc; } /* inode security operations */ static int selinux_inode_alloc_security(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); u32 sid = current_sid(); spin_lock_init(&isec->lock); INIT_LIST_HEAD(&isec->list); isec->inode = inode; isec->sid = SECINITSID_UNLABELED; isec->sclass = SECCLASS_FILE; isec->task_sid = sid; isec->initialized = LABEL_INVALID; return 0; } static void selinux_inode_free_security(struct inode *inode) { inode_free_security(inode); } static int selinux_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, void **ctx, u32 *ctxlen) { u32 newsid; int rc; rc = selinux_determine_inode_label(selinux_cred(current_cred()), d_inode(dentry->d_parent), name, inode_mode_to_security_class(mode), &newsid); if (rc) return rc; return security_sid_to_context(&selinux_state, newsid, (char **)ctx, ctxlen); } static int selinux_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) { u32 newsid; int rc; struct task_security_struct *tsec; rc = selinux_determine_inode_label(selinux_cred(old), d_inode(dentry->d_parent), name, inode_mode_to_security_class(mode), &newsid); if (rc) return rc; tsec = selinux_cred(new); tsec->create_sid = newsid; return 0; } static int selinux_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const char **name, void **value, size_t *len) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct superblock_security_struct *sbsec; u32 newsid, clen; int rc; char *context; sbsec = dir->i_sb->s_security; newsid = tsec->create_sid; rc = selinux_determine_inode_label(tsec, dir, qstr, inode_mode_to_security_class(inode->i_mode), &newsid); if (rc) return rc; /* Possibly defer initialization to selinux_complete_init. */ if (sbsec->flags & SE_SBINITIALIZED) { struct inode_security_struct *isec = selinux_inode(inode); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; } if (!selinux_initialized(&selinux_state) || !(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (name) *name = XATTR_SELINUX_SUFFIX; if (value && len) { rc = security_sid_to_context_force(&selinux_state, newsid, &context, &clen); if (rc) return rc; *value = context; *len = clen; } return 0; } static int selinux_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode) { return may_create(dir, dentry, SECCLASS_FILE); } static int selinux_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { return may_link(dir, old_dentry, MAY_LINK); } static int selinux_inode_unlink(struct inode *dir, struct dentry *dentry) { return may_link(dir, dentry, MAY_UNLINK); } static int selinux_inode_symlink(struct inode *dir, struct dentry *dentry, const char *name) { return may_create(dir, dentry, SECCLASS_LNK_FILE); } static int selinux_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mask) { return may_create(dir, dentry, SECCLASS_DIR); } static int selinux_inode_rmdir(struct inode *dir, struct dentry *dentry) { return may_link(dir, dentry, MAY_RMDIR); } static int selinux_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { return may_create(dir, dentry, inode_mode_to_security_class(mode)); } static int selinux_inode_rename(struct inode *old_inode, struct dentry *old_dentry, struct inode *new_inode, struct dentry *new_dentry) { return may_rename(old_inode, old_dentry, new_inode, new_dentry); } static int selinux_inode_readlink(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__READ); } static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode, bool rcu) { const struct cred *cred = current_cred(); struct common_audit_data ad; struct inode_security_struct *isec; u32 sid; validate_creds(cred); ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; sid = cred_sid(cred); isec = inode_security_rcu(inode, rcu); if (IS_ERR(isec)) return PTR_ERR(isec); return avc_has_perm_flags(&selinux_state, sid, isec->sid, isec->sclass, FILE__READ, &ad, rcu ? MAY_NOT_BLOCK : 0); } static noinline int audit_inode_permission(struct inode *inode, u32 perms, u32 audited, u32 denied, int result) { struct common_audit_data ad; struct inode_security_struct *isec = selinux_inode(inode); int rc; ad.type = LSM_AUDIT_DATA_INODE; ad.u.inode = inode; rc = slow_avc_audit(&selinux_state, current_sid(), isec->sid, isec->sclass, perms, audited, denied, result, &ad); if (rc) return rc; return 0; } static int selinux_inode_permission(struct inode *inode, int mask) { const struct cred *cred = current_cred(); u32 perms; bool from_access; bool no_block = mask & MAY_NOT_BLOCK; struct inode_security_struct *isec; u32 sid; struct av_decision avd; int rc, rc2; u32 audited, denied; from_access = mask & MAY_ACCESS; mask &= (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND); /* No permission to check. Existence test. */ if (!mask) return 0; validate_creds(cred); if (unlikely(IS_PRIVATE(inode))) return 0; perms = file_mask_to_av(inode->i_mode, mask); sid = cred_sid(cred); isec = inode_security_rcu(inode, no_block); if (IS_ERR(isec)) return PTR_ERR(isec); rc = avc_has_perm_noaudit(&selinux_state, sid, isec->sid, isec->sclass, perms, no_block ? AVC_NONBLOCKING : 0, &avd); audited = avc_audit_required(perms, &avd, rc, from_access ? FILE__AUDIT_ACCESS : 0, &denied); if (likely(!audited)) return rc; /* fall back to ref-walk if we have to generate audit */ if (no_block) return -ECHILD; rc2 = audit_inode_permission(inode, perms, audited, denied, rc); if (rc2) return rc2; return rc; } static int selinux_inode_setattr(struct dentry *dentry, struct iattr *iattr) { const struct cred *cred = current_cred(); struct inode *inode = d_backing_inode(dentry); unsigned int ia_valid = iattr->ia_valid; __u32 av = FILE__WRITE; /* ATTR_FORCE is just used for ATTR_KILL_S[UG]ID. */ if (ia_valid & ATTR_FORCE) { ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_MODE | ATTR_FORCE); if (!ia_valid) return 0; } if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_TIMES_SET)) return dentry_has_perm(cred, dentry, FILE__SETATTR); if (selinux_policycap_openperm() && inode->i_sb->s_magic != SOCKFS_MAGIC && (ia_valid & ATTR_SIZE) && !(ia_valid & ATTR_FILE)) av |= FILE__OPEN; return dentry_has_perm(cred, dentry, av); } static int selinux_inode_getattr(const struct path *path) { return path_has_perm(current_cred(), path, FILE__GETATTR); } static bool has_cap_mac_admin(bool audit) { const struct cred *cred = current_cred(); unsigned int opts = audit ? CAP_OPT_NONE : CAP_OPT_NOAUDIT; if (cap_capable(cred, &init_user_ns, CAP_MAC_ADMIN, opts)) return false; if (cred_has_capability(cred, CAP_MAC_ADMIN, opts, true)) return false; return true; } static int selinux_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct inode_security_struct *isec; struct superblock_security_struct *sbsec; struct common_audit_data ad; u32 newsid, sid = current_sid(); int rc = 0; if (strcmp(name, XATTR_NAME_SELINUX)) { rc = cap_inode_setxattr(dentry, name, value, size, flags); if (rc) return rc; /* Not an attribute we recognize, so just check the ordinary setattr permission. */ return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } if (!selinux_initialized(&selinux_state)) return (inode_owner_or_capable(inode) ? 0 : -EPERM); sbsec = inode->i_sb->s_security; if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (!inode_owner_or_capable(inode)) return -EPERM; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; isec = backing_inode_security(dentry); rc = avc_has_perm(&selinux_state, sid, isec->sid, isec->sclass, FILE__RELABELFROM, &ad); if (rc) return rc; rc = security_context_to_sid(&selinux_state, value, size, &newsid, GFP_KERNEL); if (rc == -EINVAL) { if (!has_cap_mac_admin(true)) { struct audit_buffer *ab; size_t audit_size; /* We strip a nul only if it is at the end, otherwise the * context contains a nul and we should audit that */ if (value) { const char *str = value; if (str[size - 1] == '\0') audit_size = size - 1; else audit_size = size; } else { audit_size = 0; } ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); audit_log_format(ab, "op=setxattr invalid_context="); audit_log_n_untrustedstring(ab, value, audit_size); audit_log_end(ab); return rc; } rc = security_context_to_sid_force(&selinux_state, value, size, &newsid); } if (rc) return rc; rc = avc_has_perm(&selinux_state, sid, newsid, isec->sclass, FILE__RELABELTO, &ad); if (rc) return rc; rc = security_validate_transition(&selinux_state, isec->sid, newsid, sid, isec->sclass); if (rc) return rc; return avc_has_perm(&selinux_state, newsid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__ASSOCIATE, &ad); } static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = d_backing_inode(dentry); struct inode_security_struct *isec; u32 newsid; int rc; if (strcmp(name, XATTR_NAME_SELINUX)) { /* Not an attribute we recognize, so nothing to do. */ return; } if (!selinux_initialized(&selinux_state)) { /* If we haven't even been initialized, then we can't validate * against a policy, so leave the label as invalid. It may * resolve to a valid label on the next revalidation try if * we've since initialized. */ return; } rc = security_context_to_sid_force(&selinux_state, value, size, &newsid); if (rc) { pr_err("SELinux: unable to map context to SID" "for (%s, %lu), rc=%d\n", inode->i_sb->s_id, inode->i_ino, -rc); return; } isec = backing_inode_security(dentry); spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); return; } static int selinux_inode_getxattr(struct dentry *dentry, const char *name) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__GETATTR); } static int selinux_inode_listxattr(struct dentry *dentry) { const struct cred *cred = current_cred(); return dentry_has_perm(cred, dentry, FILE__GETATTR); } static int selinux_inode_removexattr(struct dentry *dentry, const char *name) { if (strcmp(name, XATTR_NAME_SELINUX)) { int rc = cap_inode_removexattr(dentry, name); if (rc) return rc; /* Not an attribute we recognize, so just check the ordinary setattr permission. */ return dentry_has_perm(current_cred(), dentry, FILE__SETATTR); } if (!selinux_initialized(&selinux_state)) return 0; /* No one is allowed to remove a SELinux security label. You can change the label, but all data must be labeled. */ return -EACCES; } static int selinux_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { int ret; u32 perm; struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_PATH; ad.u.path = *path; /* * Set permission needed based on the type of mark being set. * Performs an additional check for sb watches. */ switch (obj_type) { case FSNOTIFY_OBJ_TYPE_VFSMOUNT: perm = FILE__WATCH_MOUNT; break; case FSNOTIFY_OBJ_TYPE_SB: perm = FILE__WATCH_SB; ret = superblock_has_perm(current_cred(), path->dentry->d_sb, FILESYSTEM__WATCH, &ad); if (ret) return ret; break; case FSNOTIFY_OBJ_TYPE_INODE: perm = FILE__WATCH; break; default: return -EINVAL; } /* blocking watches require the file:watch_with_perm permission */ if (mask & (ALL_FSNOTIFY_PERM_EVENTS)) perm |= FILE__WATCH_WITH_PERM; /* watches on read-like events need the file:watch_reads permission */ if (mask & (FS_ACCESS | FS_ACCESS_PERM | FS_CLOSE_NOWRITE)) perm |= FILE__WATCH_READS; return path_has_perm(current_cred(), path, perm); } /* * Copy the inode security context value to the user. * * Permission check is handled by selinux_inode_getxattr hook. */ static int selinux_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc) { u32 size; int error; char *context = NULL; struct inode_security_struct *isec; /* * If we're not initialized yet, then we can't validate contexts, so * just let vfs_getxattr fall back to using the on-disk xattr. */ if (!selinux_initialized(&selinux_state) || strcmp(name, XATTR_SELINUX_SUFFIX)) return -EOPNOTSUPP; /* * If the caller has CAP_MAC_ADMIN, then get the raw context * value even if it is not defined by current policy; otherwise, * use the in-core value under current policy. * Use the non-auditing forms of the permission checks since * getxattr may be called by unprivileged processes commonly * and lack of permission just means that we fall back to the * in-core context value, not a denial. */ isec = inode_security(inode); if (has_cap_mac_admin(false)) error = security_sid_to_context_force(&selinux_state, isec->sid, &context, &size); else error = security_sid_to_context(&selinux_state, isec->sid, &context, &size); if (error) return error; error = size; if (alloc) { *buffer = context; goto out_nofree; } kfree(context); out_nofree: return error; } static int selinux_inode_setsecurity(struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct inode_security_struct *isec = inode_security_novalidate(inode); struct superblock_security_struct *sbsec = inode->i_sb->s_security; u32 newsid; int rc; if (strcmp(name, XATTR_SELINUX_SUFFIX)) return -EOPNOTSUPP; if (!(sbsec->flags & SBLABEL_MNT)) return -EOPNOTSUPP; if (!value || !size) return -EACCES; rc = security_context_to_sid(&selinux_state, value, size, &newsid, GFP_KERNEL); if (rc) return rc; spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = newsid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); return 0; } static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size) { const int len = sizeof(XATTR_NAME_SELINUX); if (!selinux_initialized(&selinux_state)) return 0; if (buffer && len <= buffer_size) memcpy(buffer, XATTR_NAME_SELINUX, len); return len; } static void selinux_inode_getsecid(struct inode *inode, u32 *secid) { struct inode_security_struct *isec = inode_security_novalidate(inode); *secid = isec->sid; } static int selinux_inode_copy_up(struct dentry *src, struct cred **new) { u32 sid; struct task_security_struct *tsec; struct cred *new_creds = *new; if (new_creds == NULL) { new_creds = prepare_creds(); if (!new_creds) return -ENOMEM; } tsec = selinux_cred(new_creds); /* Get label from overlay inode and set it in create_sid */ selinux_inode_getsecid(d_inode(src), &sid); tsec->create_sid = sid; *new = new_creds; return 0; } static int selinux_inode_copy_up_xattr(const char *name) { /* The copy_up hook above sets the initial context on an inode, but we * don't then want to overwrite it by blindly copying all the lower * xattrs up. Instead, we have to filter out SELinux-related xattrs. */ if (strcmp(name, XATTR_NAME_SELINUX) == 0) return 1; /* Discard */ /* * Any other attribute apart from SELINUX is not claimed, supported * by selinux. */ return -EOPNOTSUPP; } /* kernfs node operations */ static int selinux_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 parent_sid, newsid, clen; int rc; char *context; rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, NULL, 0); if (rc == -ENODATA) return 0; else if (rc < 0) return rc; clen = (u32)rc; context = kmalloc(clen, GFP_KERNEL); if (!context) return -ENOMEM; rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, context, clen); if (rc < 0) { kfree(context); return rc; } rc = security_context_to_sid(&selinux_state, context, clen, &parent_sid, GFP_KERNEL); kfree(context); if (rc) return rc; if (tsec->create_sid) { newsid = tsec->create_sid; } else { u16 secclass = inode_mode_to_security_class(kn->mode); struct qstr q; q.name = kn->name; q.hash_len = hashlen_string(kn_dir, kn->name); rc = security_transition_sid(&selinux_state, tsec->sid, parent_sid, secclass, &q, &newsid); if (rc) return rc; } rc = security_sid_to_context_force(&selinux_state, newsid, &context, &clen); if (rc) return rc; rc = kernfs_xattr_set(kn, XATTR_NAME_SELINUX, context, clen, XATTR_CREATE); kfree(context); return rc; } /* file security operations */ static int selinux_revalidate_file_permission(struct file *file, int mask) { const struct cred *cred = current_cred(); struct inode *inode = file_inode(file); /* file_mask_to_av won't add FILE__WRITE if MAY_APPEND is set */ if ((file->f_flags & O_APPEND) && (mask & MAY_WRITE)) mask |= MAY_APPEND; return file_has_perm(cred, file, file_mask_to_av(inode->i_mode, mask)); } static int selinux_file_permission(struct file *file, int mask) { struct inode *inode = file_inode(file); struct file_security_struct *fsec = selinux_file(file); struct inode_security_struct *isec; u32 sid = current_sid(); if (!mask) /* No permission to check. Existence test. */ return 0; isec = inode_security(inode); if (sid == fsec->sid && fsec->isid == isec->sid && fsec->pseqno == avc_policy_seqno(&selinux_state)) /* No change since file_open check. */ return 0; return selinux_revalidate_file_permission(file, mask); } static int selinux_file_alloc_security(struct file *file) { struct file_security_struct *fsec = selinux_file(file); u32 sid = current_sid(); fsec->sid = sid; fsec->fown_sid = sid; return 0; } /* * Check whether a task has the ioctl permission and cmd * operation to an inode. */ static int ioctl_has_perm(const struct cred *cred, struct file *file, u32 requested, u16 cmd) { struct common_audit_data ad; struct file_security_struct *fsec = selinux_file(file); struct inode *inode = file_inode(file); struct inode_security_struct *isec; struct lsm_ioctlop_audit ioctl; u32 ssid = cred_sid(cred); int rc; u8 driver = cmd >> 8; u8 xperm = cmd & 0xff; ad.type = LSM_AUDIT_DATA_IOCTL_OP; ad.u.op = &ioctl; ad.u.op->cmd = cmd; ad.u.op->path = file->f_path; if (ssid != fsec->sid) { rc = avc_has_perm(&selinux_state, ssid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) goto out; } if (unlikely(IS_PRIVATE(inode))) return 0; isec = inode_security(inode); rc = avc_has_extended_perms(&selinux_state, ssid, isec->sid, isec->sclass, requested, driver, xperm, &ad); out: return rc; } static int selinux_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { const struct cred *cred = current_cred(); int error = 0; switch (cmd) { case FIONREAD: case FIBMAP: case FIGETBSZ: case FS_IOC_GETFLAGS: case FS_IOC_GETVERSION: error = file_has_perm(cred, file, FILE__GETATTR); break; case FS_IOC_SETFLAGS: case FS_IOC_SETVERSION: error = file_has_perm(cred, file, FILE__SETATTR); break; /* sys_ioctl() checks */ case FIONBIO: case FIOASYNC: error = file_has_perm(cred, file, 0); break; case KDSKBENT: case KDSKBSENT: error = cred_has_capability(cred, CAP_SYS_TTY_CONFIG, CAP_OPT_NONE, true); break; case FIOCLEX: case FIONCLEX: if (!selinux_policycap_ioctl_skip_cloexec()) error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd); break; /* default case assumes that the command will go * to the file's ioctl() function. */ default: error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd); } return error; } static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { /* * If we are in a 64-bit kernel running 32-bit userspace, we need to * make sure we don't compare 32-bit flags to 64-bit flags. */ switch (cmd) { case FS_IOC32_GETFLAGS: cmd = FS_IOC_GETFLAGS; break; case FS_IOC32_SETFLAGS: cmd = FS_IOC_SETFLAGS; break; case FS_IOC32_GETVERSION: cmd = FS_IOC_GETVERSION; break; case FS_IOC32_SETVERSION: cmd = FS_IOC_SETVERSION; break; default: break; } return selinux_file_ioctl(file, cmd, arg); } static int default_noexec __ro_after_init; static int file_map_prot_check(struct file *file, unsigned long prot, int shared) { const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); int rc = 0; if (default_noexec && (prot & PROT_EXEC) && (!file || IS_PRIVATE(file_inode(file)) || (!shared && (prot & PROT_WRITE)))) { /* * We are making executable an anonymous mapping or a * private file mapping that will also be writable. * This has an additional check. */ rc = avc_has_perm(&selinux_state, sid, sid, SECCLASS_PROCESS, PROCESS__EXECMEM, NULL); if (rc) goto error; } if (file) { /* read access is always possible with a mapping */ u32 av = FILE__READ; /* write access only matters if the mapping is shared */ if (shared && (prot & PROT_WRITE)) av |= FILE__WRITE; if (prot & PROT_EXEC) av |= FILE__EXECUTE; return file_has_perm(cred, file, av); } error: return rc; } static int selinux_mmap_addr(unsigned long addr) { int rc = 0; if (addr < CONFIG_LSM_MMAP_MIN_ADDR) { u32 sid = current_sid(); rc = avc_has_perm(&selinux_state, sid, sid, SECCLASS_MEMPROTECT, MEMPROTECT__MMAP_ZERO, NULL); } return rc; } static int selinux_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { struct common_audit_data ad; int rc; if (file) { ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; rc = inode_has_perm(current_cred(), file_inode(file), FILE__MAP, &ad); if (rc) return rc; } if (checkreqprot_get(&selinux_state)) prot = reqprot; return file_map_prot_check(file, prot, (flags & MAP_TYPE) == MAP_SHARED); } static int selinux_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { const struct cred *cred = current_cred(); u32 sid = cred_sid(cred); if (checkreqprot_get(&selinux_state)) prot = reqprot; if (default_noexec && (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) { int rc = 0; if (vma->vm_start >= vma->vm_mm->start_brk && vma->vm_end <= vma->vm_mm->brk) { rc = avc_has_perm(&selinux_state, sid, sid, SECCLASS_PROCESS, PROCESS__EXECHEAP, NULL); } else if (!vma->vm_file && ((vma->vm_start <= vma->vm_mm->start_stack && vma->vm_end >= vma->vm_mm->start_stack) || vma_is_stack_for_current(vma))) { rc = avc_has_perm(&selinux_state, sid, sid, SECCLASS_PROCESS, PROCESS__EXECSTACK, NULL); } else if (vma->vm_file && vma->anon_vma) { /* * We are making executable a file mapping that has * had some COW done. Since pages might have been * written, check ability to execute the possibly * modified content. This typically should only * occur for text relocations. */ rc = file_has_perm(cred, vma->vm_file, FILE__EXECMOD); } if (rc) return rc; } return file_map_prot_check(vma->vm_file, prot, vma->vm_flags&VM_SHARED); } static int selinux_file_lock(struct file *file, unsigned int cmd) { const struct cred *cred = current_cred(); return file_has_perm(cred, file, FILE__LOCK); } static int selinux_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { const struct cred *cred = current_cred(); int err = 0; switch (cmd) { case F_SETFL: if ((file->f_flags & O_APPEND) && !(arg & O_APPEND)) { err = file_has_perm(cred, file, FILE__WRITE); break; } fallthrough; case F_SETOWN: case F_SETSIG: case F_GETFL: case F_GETOWN: case F_GETSIG: case F_GETOWNER_UIDS: /* Just check FD__USE permission */ err = file_has_perm(cred, file, 0); break; case F_GETLK: case F_SETLK: case F_SETLKW: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: #if BITS_PER_LONG == 32 case F_GETLK64: case F_SETLK64: case F_SETLKW64: #endif err = file_has_perm(cred, file, FILE__LOCK); break; } return err; } static void selinux_file_set_fowner(struct file *file) { struct file_security_struct *fsec; fsec = selinux_file(file); fsec->fown_sid = current_sid(); } static int selinux_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int signum) { struct file *file; u32 sid = task_sid(tsk); u32 perm; struct file_security_struct *fsec; /* struct fown_struct is never outside the context of a struct file */ file = container_of(fown, struct file, f_owner); fsec = selinux_file(file); if (!signum) perm = signal_to_av(SIGIO); /* as per send_sigio_to_task */ else perm = signal_to_av(signum); return avc_has_perm(&selinux_state, fsec->fown_sid, sid, SECCLASS_PROCESS, perm, NULL); } static int selinux_file_receive(struct file *file) { const struct cred *cred = current_cred(); return file_has_perm(cred, file, file_to_av(file)); } static int selinux_file_open(struct file *file) { struct file_security_struct *fsec; struct inode_security_struct *isec; fsec = selinux_file(file); isec = inode_security(file_inode(file)); /* * Save inode label and policy sequence number * at open-time so that selinux_file_permission * can determine whether revalidation is necessary. * Task label is already saved in the file security * struct as its SID. */ fsec->isid = isec->sid; fsec->pseqno = avc_policy_seqno(&selinux_state); /* * Since the inode label or policy seqno may have changed * between the selinux_inode_permission check and the saving * of state above, recheck that access is still permitted. * Otherwise, access might never be revalidated against the * new inode label or new policy. * This check is not redundant - do not remove. */ return file_path_has_perm(file->f_cred, file, open_file_to_av(file)); } /* task security operations */ static int selinux_task_alloc(struct task_struct *task, unsigned long clone_flags) { u32 sid = current_sid(); return avc_has_perm(&selinux_state, sid, sid, SECCLASS_PROCESS, PROCESS__FORK, NULL); } /* * prepare a new set of credentials for modification */ static int selinux_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { const struct task_security_struct *old_tsec = selinux_cred(old); struct task_security_struct *tsec = selinux_cred(new); *tsec = *old_tsec; return 0; } /* * transfer the SELinux data to a blank set of creds */ static void selinux_cred_transfer(struct cred *new, const struct cred *old) { const struct task_security_struct *old_tsec = selinux_cred(old); struct task_security_struct *tsec = selinux_cred(new); *tsec = *old_tsec; } static void selinux_cred_getsecid(const struct cred *c, u32 *secid) { *secid = cred_sid(c); } /* * set the security data for a kernel service * - all the creation contexts are set to unlabelled */ static int selinux_kernel_act_as(struct cred *new, u32 secid) { struct task_security_struct *tsec = selinux_cred(new); u32 sid = current_sid(); int ret; ret = avc_has_perm(&selinux_state, sid, secid, SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__USE_AS_OVERRIDE, NULL); if (ret == 0) { tsec->sid = secid; tsec->create_sid = 0; tsec->keycreate_sid = 0; tsec->sockcreate_sid = 0; } return ret; } /* * set the file creation context in a security record to the same as the * objective context of the specified inode */ static int selinux_kernel_create_files_as(struct cred *new, struct inode *inode) { struct inode_security_struct *isec = inode_security(inode); struct task_security_struct *tsec = selinux_cred(new); u32 sid = current_sid(); int ret; ret = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__CREATE_FILES_AS, NULL); if (ret == 0) tsec->create_sid = isec->sid; return ret; } static int selinux_kernel_module_request(char *kmod_name) { struct common_audit_data ad; ad.type = LSM_AUDIT_DATA_KMOD; ad.u.kmod_name = kmod_name; return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__MODULE_REQUEST, &ad); } static int selinux_kernel_module_from_file(struct file *file) { struct common_audit_data ad; struct inode_security_struct *isec; struct file_security_struct *fsec; u32 sid = current_sid(); int rc; /* init_module */ if (file == NULL) return avc_has_perm(&selinux_state, sid, sid, SECCLASS_SYSTEM, SYSTEM__MODULE_LOAD, NULL); /* finit_module */ ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = file; fsec = selinux_file(file); if (sid != fsec->sid) { rc = avc_has_perm(&selinux_state, sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) return rc; } isec = inode_security(file_inode(file)); return avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_SYSTEM, SYSTEM__MODULE_LOAD, &ad); } static int selinux_kernel_read_file(struct file *file, enum kernel_read_file_id id, bool contents) { int rc = 0; switch (id) { case READING_MODULE: rc = selinux_kernel_module_from_file(contents ? file : NULL); break; default: break; } return rc; } static int selinux_kernel_load_data(enum kernel_load_data_id id, bool contents) { int rc = 0; switch (id) { case LOADING_MODULE: rc = selinux_kernel_module_from_file(NULL); default: break; } return rc; } static int selinux_task_setpgid(struct task_struct *p, pid_t pgid) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__SETPGID, NULL); } static int selinux_task_getpgid(struct task_struct *p) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__GETPGID, NULL); } static int selinux_task_getsid(struct task_struct *p) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__GETSESSION, NULL); } static void selinux_task_getsecid(struct task_struct *p, u32 *secid) { *secid = task_sid(p); } static int selinux_task_setnice(struct task_struct *p, int nice) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_setioprio(struct task_struct *p, int ioprio) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_getioprio(struct task_struct *p) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__GETSCHED, NULL); } static int selinux_task_prlimit(const struct cred *cred, const struct cred *tcred, unsigned int flags) { u32 av = 0; if (!flags) return 0; if (flags & LSM_PRLIMIT_WRITE) av |= PROCESS__SETRLIMIT; if (flags & LSM_PRLIMIT_READ) av |= PROCESS__GETRLIMIT; return avc_has_perm(&selinux_state, cred_sid(cred), cred_sid(tcred), SECCLASS_PROCESS, av, NULL); } static int selinux_task_setrlimit(struct task_struct *p, unsigned int resource, struct rlimit *new_rlim) { struct rlimit *old_rlim = p->signal->rlim + resource; /* Control the ability to change the hard limit (whether lowering or raising it), so that the hard limit can later be used as a safe reset point for the soft limit upon context transitions. See selinux_bprm_committing_creds. */ if (old_rlim->rlim_max != new_rlim->rlim_max) return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__SETRLIMIT, NULL); return 0; } static int selinux_task_setscheduler(struct task_struct *p) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_getscheduler(struct task_struct *p) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__GETSCHED, NULL); } static int selinux_task_movememory(struct task_struct *p) { return avc_has_perm(&selinux_state, current_sid(), task_sid(p), SECCLASS_PROCESS, PROCESS__SETSCHED, NULL); } static int selinux_task_kill(struct task_struct *p, struct kernel_siginfo *info, int sig, const struct cred *cred) { u32 secid; u32 perm; if (!sig) perm = PROCESS__SIGNULL; /* null signal; existence test */ else perm = signal_to_av(sig); if (!cred) secid = current_sid(); else secid = cred_sid(cred); return avc_has_perm(&selinux_state, secid, task_sid(p), SECCLASS_PROCESS, perm, NULL); } static void selinux_task_to_inode(struct task_struct *p, struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); u32 sid = task_sid(p); spin_lock(&isec->lock); isec->sclass = inode_mode_to_security_class(inode->i_mode); isec->sid = sid; isec->initialized = LABEL_INITIALIZED; spin_unlock(&isec->lock); } /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv4(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int offset, ihlen, ret = -EINVAL; struct iphdr _iph, *ih; offset = skb_network_offset(skb); ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); if (ih == NULL) goto out; ihlen = ih->ihl * 4; if (ihlen < sizeof(_iph)) goto out; ad->u.net->v4info.saddr = ih->saddr; ad->u.net->v4info.daddr = ih->daddr; ret = 0; if (proto) *proto = ih->protocol; switch (ih->protocol) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } #if IS_ENABLED(CONFIG_IP_SCTP) case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; if (ntohs(ih->frag_off) & IP_OFFSET) break; offset += ihlen; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } #endif default: break; } out: return ret; } #if IS_ENABLED(CONFIG_IPV6) /* Returns error only if unable to parse addresses */ static int selinux_parse_skb_ipv6(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { u8 nexthdr; int ret = -EINVAL, offset; struct ipv6hdr _ipv6h, *ip6; __be16 frag_off; offset = skb_network_offset(skb); ip6 = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (ip6 == NULL) goto out; ad->u.net->v6info.saddr = ip6->saddr; ad->u.net->v6info.daddr = ip6->daddr; ret = 0; nexthdr = ip6->nexthdr; offset += sizeof(_ipv6h); offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset < 0) goto out; if (proto) *proto = nexthdr; switch (nexthdr) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } #if IS_ENABLED(CONFIG_IP_SCTP) case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } #endif /* includes fragments */ default: break; } out: return ret; } #endif /* IPV6 */ static int selinux_parse_skb(struct sk_buff *skb, struct common_audit_data *ad, char **_addrp, int src, u8 *proto) { char *addrp; int ret; switch (ad->u.net->family) { case PF_INET: ret = selinux_parse_skb_ipv4(skb, ad, proto); if (ret) goto parse_error; addrp = (char *)(src ? &ad->u.net->v4info.saddr : &ad->u.net->v4info.daddr); goto okay; #if IS_ENABLED(CONFIG_IPV6) case PF_INET6: ret = selinux_parse_skb_ipv6(skb, ad, proto); if (ret) goto parse_error; addrp = (char *)(src ? &ad->u.net->v6info.saddr : &ad->u.net->v6info.daddr); goto okay; #endif /* IPV6 */ default: addrp = NULL; goto okay; } parse_error: pr_warn( "SELinux: failure in selinux_parse_skb()," " unable to parse packet\n"); return ret; okay: if (_addrp) *_addrp = addrp; return 0; } /** * selinux_skb_peerlbl_sid - Determine the peer label of a packet * @skb: the packet * @family: protocol family * @sid: the packet's peer label SID * * Description: * Check the various different forms of network peer labeling and determine * the peer label/SID for the packet; most of the magic actually occurs in * the security server function security_net_peersid_cmp(). The function * returns zero if the value in @sid is valid (although it may be SECSID_NULL) * or -EACCES if @sid is invalid due to inconsistencies with the different * peer labels. * */ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid) { int err; u32 xfrm_sid; u32 nlbl_sid; u32 nlbl_type; err = selinux_xfrm_skb_sid(skb, &xfrm_sid); if (unlikely(err)) return -EACCES; err = selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid); if (unlikely(err)) return -EACCES; err = security_net_peersid_resolve(&selinux_state, nlbl_sid, nlbl_type, xfrm_sid, sid); if (unlikely(err)) { pr_warn( "SELinux: failure in selinux_skb_peerlbl_sid()," " unable to determine packet's peer label\n"); return -EACCES; } return 0; } /** * selinux_conn_sid - Determine the child socket label for a connection * @sk_sid: the parent socket's SID * @skb_sid: the packet's SID * @conn_sid: the resulting connection SID * * If @skb_sid is valid then the user:role:type information from @sk_sid is * combined with the MLS information from @skb_sid in order to create * @conn_sid. If @skb_sid is not valid then @conn_sid is simply a copy * of @sk_sid. Returns zero on success, negative values on failure. * */ static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid) { int err = 0; if (skb_sid != SECSID_NULL) err = security_sid_mls_copy(&selinux_state, sk_sid, skb_sid, conn_sid); else *conn_sid = sk_sid; return err; } /* socket security operations */ static int socket_sockcreate_sid(const struct task_security_struct *tsec, u16 secclass, u32 *socksid) { if (tsec->sockcreate_sid > SECSID_NULL) { *socksid = tsec->sockcreate_sid; return 0; } return security_transition_sid(&selinux_state, tsec->sid, tsec->sid, secclass, NULL, socksid); } static int sock_has_perm(struct sock *sk, u32 perms) { struct sk_security_struct *sksec = sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net = {0,}; if (sksec->sid == SECINITSID_KERNEL) return 0; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sk = sk; return avc_has_perm(&selinux_state, current_sid(), sksec->sid, sksec->sclass, perms, &ad); } static int selinux_socket_create(int family, int type, int protocol, int kern) { const struct task_security_struct *tsec = selinux_cred(current_cred()); u32 newsid; u16 secclass; int rc; if (kern) return 0; secclass = socket_type_to_security_class(family, type, protocol); rc = socket_sockcreate_sid(tsec, secclass, &newsid); if (rc) return rc; return avc_has_perm(&selinux_state, tsec->sid, newsid, secclass, SOCKET__CREATE, NULL); } static int selinux_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { const struct task_security_struct *tsec = selinux_cred(current_cred()); struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(sock)); struct sk_security_struct *sksec; u16 sclass = socket_type_to_security_class(family, type, protocol); u32 sid = SECINITSID_KERNEL; int err = 0; if (!kern) { err = socket_sockcreate_sid(tsec, sclass, &sid); if (err) return err; } isec->sclass = sclass; isec->sid = sid; isec->initialized = LABEL_INITIALIZED; if (sock->sk) { sksec = sock->sk->sk_security; sksec->sclass = sclass; sksec->sid = sid; /* Allows detection of the first association on this socket */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) sksec->sctp_assoc_state = SCTP_ASSOC_UNSET; err = selinux_netlbl_socket_post_create(sock->sk, family); } return err; } static int selinux_socket_socketpair(struct socket *socka, struct socket *sockb) { struct sk_security_struct *sksec_a = socka->sk->sk_security; struct sk_security_struct *sksec_b = sockb->sk->sk_security; sksec_a->peer_sid = sksec_b->sid; sksec_b->peer_sid = sksec_a->sid; return 0; } /* Range of port numbers used to automatically bind. Need to determine whether we should perform a name_bind permission check between the socket and the port number. */ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; struct sk_security_struct *sksec = sk->sk_security; u16 family; int err; err = sock_has_perm(sk, SOCKET__BIND); if (err) goto out; /* If PF_INET or PF_INET6, check name_bind permission for the port. */ family = sk->sk_family; if (family == PF_INET || family == PF_INET6) { char *addrp; struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; u16 family_sa; unsigned short snum; u32 sid, node_perm; /* * sctp_bindx(3) calls via selinux_sctp_bind_connect() * that validates multiple binding addresses. Because of this * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ if (addrlen < offsetofend(struct sockaddr, sa_family)) return -EINVAL; family_sa = address->sa_family; switch (family_sa) { case AF_UNSPEC: case AF_INET: if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; addr4 = (struct sockaddr_in *)address; if (family_sa == AF_UNSPEC) { if (family == PF_INET6) { /* Length check from inet6_bind_sk() */ if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; /* Family check from __inet6_bind() */ goto err_af; } /* see __inet_bind(), we only want to allow * AF_UNSPEC if the address is INADDR_ANY */ if (addr4->sin_addr.s_addr != htonl(INADDR_ANY)) goto err_af; family_sa = AF_INET; } snum = ntohs(addr4->sin_port); addrp = (char *)&addr4->sin_addr.s_addr; break; case AF_INET6: if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; addr6 = (struct sockaddr_in6 *)address; snum = ntohs(addr6->sin6_port); addrp = (char *)&addr6->sin6_addr.s6_addr; break; default: goto err_af; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sport = htons(snum); ad.u.net->family = family_sa; if (snum) { int low, high; inet_get_local_port_range(sock_net(sk), &low, &high); if (inet_port_requires_bind_service(sock_net(sk), snum) || snum < low || snum > high) { err = sel_netport_sid(sk->sk_protocol, snum, &sid); if (err) goto out; err = avc_has_perm(&selinux_state, sksec->sid, sid, sksec->sclass, SOCKET__NAME_BIND, &ad); if (err) goto out; } } switch (sksec->sclass) { case SECCLASS_TCP_SOCKET: node_perm = TCP_SOCKET__NODE_BIND; break; case SECCLASS_UDP_SOCKET: node_perm = UDP_SOCKET__NODE_BIND; break; case SECCLASS_DCCP_SOCKET: node_perm = DCCP_SOCKET__NODE_BIND; break; case SECCLASS_SCTP_SOCKET: node_perm = SCTP_SOCKET__NODE_BIND; break; default: node_perm = RAWIP_SOCKET__NODE_BIND; break; } err = sel_netnode_sid(addrp, family_sa, &sid); if (err) goto out; if (family_sa == AF_INET) ad.u.net->v4info.saddr = addr4->sin_addr.s_addr; else ad.u.net->v6info.saddr = addr6->sin6_addr; err = avc_has_perm(&selinux_state, sksec->sid, sid, sksec->sclass, node_perm, &ad); if (err) goto out; } out: return err; err_af: /* Note that SCTP services expect -EINVAL, others -EAFNOSUPPORT. */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) return -EINVAL; return -EAFNOSUPPORT; } /* This supports connect(2) and SCTP connect services such as sctp_connectx(3) * and sctp_sendmsg(3) as described in Documentation/security/SCTP.rst */ static int selinux_socket_connect_helper(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; struct sk_security_struct *sksec = sk->sk_security; int err; err = sock_has_perm(sk, SOCKET__CONNECT); if (err) return err; if (addrlen < offsetofend(struct sockaddr, sa_family)) return -EINVAL; /* connect(AF_UNSPEC) has special handling, as it is a documented * way to disconnect the socket */ if (address->sa_family == AF_UNSPEC) return 0; /* * If a TCP, DCCP or SCTP socket, check name_connect permission * for the port. */ if (sksec->sclass == SECCLASS_TCP_SOCKET || sksec->sclass == SECCLASS_DCCP_SOCKET || sksec->sclass == SECCLASS_SCTP_SOCKET) { struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; unsigned short snum; u32 sid, perm; /* sctp_connectx(3) calls via selinux_sctp_bind_connect() * that validates multiple connect addresses. Because of this * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ switch (address->sa_family) { case AF_INET: addr4 = (struct sockaddr_in *)address; if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; snum = ntohs(addr4->sin_port); break; case AF_INET6: addr6 = (struct sockaddr_in6 *)address; if (addrlen < SIN6_LEN_RFC2133) return -EINVAL; snum = ntohs(addr6->sin6_port); break; default: /* Note that SCTP services expect -EINVAL, whereas * others expect -EAFNOSUPPORT. */ if (sksec->sclass == SECCLASS_SCTP_SOCKET) return -EINVAL; else return -EAFNOSUPPORT; } err = sel_netport_sid(sk->sk_protocol, snum, &sid); if (err) return err; switch (sksec->sclass) { case SECCLASS_TCP_SOCKET: perm = TCP_SOCKET__NAME_CONNECT; break; case SECCLASS_DCCP_SOCKET: perm = DCCP_SOCKET__NAME_CONNECT; break; case SECCLASS_SCTP_SOCKET: perm = SCTP_SOCKET__NAME_CONNECT; break; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->dport = htons(snum); ad.u.net->family = address->sa_family; err = avc_has_perm(&selinux_state, sksec->sid, sid, sksec->sclass, perm, &ad); if (err) return err; } return 0; } /* Supports connect(2), see comments in selinux_socket_connect_helper() */ static int selinux_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { int err; struct sock *sk = sock->sk; err = selinux_socket_connect_helper(sock, address, addrlen); if (err) return err; return selinux_netlbl_socket_connect(sk, address); } static int selinux_socket_listen(struct socket *sock, int backlog) { return sock_has_perm(sock->sk, SOCKET__LISTEN); } static int selinux_socket_accept(struct socket *sock, struct socket *newsock) { int err; struct inode_security_struct *isec; struct inode_security_struct *newisec; u16 sclass; u32 sid; err = sock_has_perm(sock->sk, SOCKET__ACCEPT); if (err) return err; isec = inode_security_novalidate(SOCK_INODE(sock)); spin_lock(&isec->lock); sclass = isec->sclass; sid = isec->sid; spin_unlock(&isec->lock); newisec = inode_security_novalidate(SOCK_INODE(newsock)); newisec->sclass = sclass; newisec->sid = sid; newisec->initialized = LABEL_INITIALIZED; return 0; } static int selinux_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size) { return sock_has_perm(sock->sk, SOCKET__WRITE); } static int selinux_socket_recvmsg(struct socket *sock, struct msghdr *msg, int size, int flags) { return sock_has_perm(sock->sk, SOCKET__READ); } static int selinux_socket_getsockname(struct socket *sock) { return sock_has_perm(sock->sk, SOCKET__GETATTR); } static int selinux_socket_getpeername(struct socket *sock) { return sock_has_perm(sock->sk, SOCKET__GETATTR); } static int selinux_socket_setsockopt(struct socket *sock, int level, int optname) { int err; err = sock_has_perm(sock->sk, SOCKET__SETOPT); if (err) return err; return selinux_netlbl_socket_setsockopt(sock, level, optname); } static int selinux_socket_getsockopt(struct socket *sock, int level, int optname) { return sock_has_perm(sock->sk, SOCKET__GETOPT); } static int selinux_socket_shutdown(struct socket *sock, int how) { return sock_has_perm(sock->sk, SOCKET__SHUTDOWN); } static int selinux_socket_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { struct sk_security_struct *sksec_sock = sock->sk_security; struct sk_security_struct *sksec_other = other->sk_security; struct sk_security_struct *sksec_new = newsk->sk_security; struct common_audit_data ad; struct lsm_network_audit net = {0,}; int err; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sk = other; err = avc_has_perm(&selinux_state, sksec_sock->sid, sksec_other->sid, sksec_other->sclass, UNIX_STREAM_SOCKET__CONNECTTO, &ad); if (err) return err; /* server child socket */ sksec_new->peer_sid = sksec_sock->sid; err = security_sid_mls_copy(&selinux_state, sksec_other->sid, sksec_sock->sid, &sksec_new->sid); if (err) return err; /* connecting socket */ sksec_sock->peer_sid = sksec_new->sid; return 0; } static int selinux_socket_unix_may_send(struct socket *sock, struct socket *other) { struct sk_security_struct *ssec = sock->sk->sk_security; struct sk_security_struct *osec = other->sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net = {0,}; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sk = other->sk; return avc_has_perm(&selinux_state, ssec->sid, osec->sid, osec->sclass, SOCKET__SENDTO, &ad); } static int selinux_inet_sys_rcv_skb(struct net *ns, int ifindex, char *addrp, u16 family, u32 peer_sid, struct common_audit_data *ad) { int err; u32 if_sid; u32 node_sid; err = sel_netif_sid(ns, ifindex, &if_sid); if (err) return err; err = avc_has_perm(&selinux_state, peer_sid, if_sid, SECCLASS_NETIF, NETIF__INGRESS, ad); if (err) return err; err = sel_netnode_sid(addrp, family, &node_sid); if (err) return err; return avc_has_perm(&selinux_state, peer_sid, node_sid, SECCLASS_NODE, NODE__RECVFROM, ad); } static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb, u16 family) { int err = 0; struct sk_security_struct *sksec = sk->sk_security; u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net = {0,}; char *addrp; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->netif = skb->skb_iif; ad.u.net->family = family; err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL); if (err) return err; if (selinux_secmark_enabled()) { err = avc_has_perm(&selinux_state, sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) return err; } err = selinux_netlbl_sock_rcv_skb(sksec, skb, family, &ad); if (err) return err; err = selinux_xfrm_sock_rcv_skb(sksec->sid, skb, &ad); return err; } static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err; struct sk_security_struct *sksec = sk->sk_security; u16 family = sk->sk_family; u32 sk_sid = sksec->sid; struct common_audit_data ad; struct lsm_network_audit net = {0,}; char *addrp; u8 secmark_active; u8 peerlbl_active; if (family != PF_INET && family != PF_INET6) return 0; /* Handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; /* If any sort of compatibility mode is enabled then handoff processing * to the selinux_sock_rcv_skb_compat() function to deal with the * special handling. We do this in an attempt to keep this function * as fast and as clean as possible. */ if (!selinux_policycap_netpeer()) return selinux_sock_rcv_skb_compat(sk, skb, family); secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return 0; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->netif = skb->skb_iif; ad.u.net->family = family; err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL); if (err) return err; if (peerlbl_active) { u32 peer_sid; err = selinux_skb_peerlbl_sid(skb, family, &peer_sid); if (err) return err; err = selinux_inet_sys_rcv_skb(sock_net(sk), skb->skb_iif, addrp, family, peer_sid, &ad); if (err) { selinux_netlbl_err(skb, family, err, 0); return err; } err = avc_has_perm(&selinux_state, sk_sid, peer_sid, SECCLASS_PEER, PEER__RECV, &ad); if (err) { selinux_netlbl_err(skb, family, err, 0); return err; } } if (secmark_active) { err = avc_has_perm(&selinux_state, sk_sid, skb->secmark, SECCLASS_PACKET, PACKET__RECV, &ad); if (err) return err; } return err; } static int selinux_socket_getpeersec_stream(struct socket *sock, sockptr_t optval, sockptr_t optlen, unsigned int len) { int err = 0; char *scontext = NULL; u32 scontext_len; struct sk_security_struct *sksec = sock->sk->sk_security; u32 peer_sid = SECSID_NULL; if (sksec->sclass == SECCLASS_UNIX_STREAM_SOCKET || sksec->sclass == SECCLASS_TCP_SOCKET || sksec->sclass == SECCLASS_SCTP_SOCKET) peer_sid = sksec->peer_sid; if (peer_sid == SECSID_NULL) return -ENOPROTOOPT; err = security_sid_to_context(&selinux_state, peer_sid, &scontext, &scontext_len); if (err) return err; if (scontext_len > len) { err = -ERANGE; goto out_len; } if (copy_to_sockptr(optval, scontext, scontext_len)) err = -EFAULT; out_len: if (copy_to_sockptr(optlen, &scontext_len, sizeof(scontext_len))) err = -EFAULT; kfree(scontext); return err; } static int selinux_socket_getpeersec_dgram(struct socket *sock, struct sk_buff *skb, u32 *secid) { u32 peer_secid = SECSID_NULL; u16 family; struct inode_security_struct *isec; if (skb && skb->protocol == htons(ETH_P_IP)) family = PF_INET; else if (skb && skb->protocol == htons(ETH_P_IPV6)) family = PF_INET6; else if (sock) family = sock->sk->sk_family; else goto out; if (sock && family == PF_UNIX) { isec = inode_security_novalidate(SOCK_INODE(sock)); peer_secid = isec->sid; } else if (skb) selinux_skb_peerlbl_sid(skb, family, &peer_secid); out: *secid = peer_secid; if (peer_secid == SECSID_NULL) return -EINVAL; return 0; } static int selinux_sk_alloc_security(struct sock *sk, int family, gfp_t priority) { struct sk_security_struct *sksec; sksec = kzalloc(sizeof(*sksec), priority); if (!sksec) return -ENOMEM; sksec->peer_sid = SECINITSID_UNLABELED; sksec->sid = SECINITSID_UNLABELED; sksec->sclass = SECCLASS_SOCKET; selinux_netlbl_sk_security_reset(sksec); sk->sk_security = sksec; return 0; } static void selinux_sk_free_security(struct sock *sk) { struct sk_security_struct *sksec = sk->sk_security; sk->sk_security = NULL; selinux_netlbl_sk_security_free(sksec); kfree(sksec); } static void selinux_sk_clone_security(const struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = sk->sk_security; struct sk_security_struct *newsksec = newsk->sk_security; newsksec->sid = sksec->sid; newsksec->peer_sid = sksec->peer_sid; newsksec->sclass = sksec->sclass; selinux_netlbl_sk_security_reset(newsksec); } static void selinux_sk_getsecid(struct sock *sk, u32 *secid) { if (!sk) *secid = SECINITSID_ANY_SOCKET; else { struct sk_security_struct *sksec = sk->sk_security; *secid = sksec->sid; } } static void selinux_sock_graft(struct sock *sk, struct socket *parent) { struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(parent)); struct sk_security_struct *sksec = sk->sk_security; if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6 || sk->sk_family == PF_UNIX) isec->sid = sksec->sid; sksec->sclass = isec->sclass; } /* Called whenever SCTP receives an INIT chunk. This happens when an incoming * connect(2), sctp_connectx(3) or sctp_sendmsg(3) (with no association * already present). */ static int selinux_sctp_assoc_request(struct sctp_endpoint *ep, struct sk_buff *skb) { struct sk_security_struct *sksec = ep->base.sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net = {0,}; u8 peerlbl_active; u32 peer_sid = SECINITSID_UNLABELED; u32 conn_sid; int err = 0; if (!selinux_policycap_extsockclass()) return 0; peerlbl_active = selinux_peerlbl_enabled(); if (peerlbl_active) { /* This will return peer_sid = SECSID_NULL if there are * no peer labels, see security_net_peersid_resolve(). */ err = selinux_skb_peerlbl_sid(skb, ep->base.sk->sk_family, &peer_sid); if (err) return err; if (peer_sid == SECSID_NULL) peer_sid = SECINITSID_UNLABELED; } if (sksec->sctp_assoc_state == SCTP_ASSOC_UNSET) { sksec->sctp_assoc_state = SCTP_ASSOC_SET; /* Here as first association on socket. As the peer SID * was allowed by peer recv (and the netif/node checks), * then it is approved by policy and used as the primary * peer SID for getpeercon(3). */ sksec->peer_sid = peer_sid; } else if (sksec->peer_sid != peer_sid) { /* Other association peer SIDs are checked to enforce * consistency among the peer SIDs. */ ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->sk = ep->base.sk; err = avc_has_perm(&selinux_state, sksec->peer_sid, peer_sid, sksec->sclass, SCTP_SOCKET__ASSOCIATION, &ad); if (err) return err; } /* Compute the MLS component for the connection and store * the information in ep. This will be used by SCTP TCP type * sockets and peeled off connections as they cause a new * socket to be generated. selinux_sctp_sk_clone() will then * plug this into the new socket. */ err = selinux_conn_sid(sksec->sid, peer_sid, &conn_sid); if (err) return err; ep->secid = conn_sid; ep->peer_secid = peer_sid; /* Set any NetLabel labels including CIPSO/CALIPSO options. */ return selinux_netlbl_sctp_assoc_request(ep, skb); } /* Check if sctp IPv4/IPv6 addresses are valid for binding or connecting * based on their @optname. */ static int selinux_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen) { int len, err = 0, walk_size = 0; void *addr_buf; struct sockaddr *addr; struct socket *sock; if (!selinux_policycap_extsockclass()) return 0; /* Process one or more addresses that may be IPv4 or IPv6 */ sock = sk->sk_socket; addr_buf = address; while (walk_size < addrlen) { if (walk_size + sizeof(sa_family_t) > addrlen) return -EINVAL; addr = addr_buf; switch (addr->sa_family) { case AF_UNSPEC: case AF_INET: len = sizeof(struct sockaddr_in); break; case AF_INET6: len = sizeof(struct sockaddr_in6); break; default: return -EINVAL; } if (walk_size + len > addrlen) return -EINVAL; err = -EINVAL; switch (optname) { /* Bind checks */ case SCTP_PRIMARY_ADDR: case SCTP_SET_PEER_PRIMARY_ADDR: case SCTP_SOCKOPT_BINDX_ADD: err = selinux_socket_bind(sock, addr, len); break; /* Connect checks */ case SCTP_SOCKOPT_CONNECTX: case SCTP_PARAM_SET_PRIMARY: case SCTP_PARAM_ADD_IP: case SCTP_SENDMSG_CONNECT: err = selinux_socket_connect_helper(sock, addr, len); if (err) return err; /* As selinux_sctp_bind_connect() is called by the * SCTP protocol layer, the socket is already locked, * therefore selinux_netlbl_socket_connect_locked() * is called here. The situations handled are: * sctp_connectx(3), sctp_sendmsg(3), sendmsg(2), * whenever a new IP address is added or when a new * primary address is selected. * Note that an SCTP connect(2) call happens before * the SCTP protocol layer and is handled via * selinux_socket_connect(). */ err = selinux_netlbl_socket_connect_locked(sk, addr); break; } if (err) return err; addr_buf += len; walk_size += len; } return 0; } /* Called whenever a new socket is created by accept(2) or sctp_peeloff(3). */ static void selinux_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = sk->sk_security; struct sk_security_struct *newsksec = newsk->sk_security; /* If policy does not support SECCLASS_SCTP_SOCKET then call * the non-sctp clone version. */ if (!selinux_policycap_extsockclass()) return selinux_sk_clone_security(sk, newsk); newsksec->sid = ep->secid; newsksec->peer_sid = ep->peer_secid; newsksec->sclass = sksec->sclass; selinux_netlbl_sctp_sk_clone(sk, newsk); } static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct sk_security_struct *sksec = sk->sk_security; int err; u16 family = req->rsk_ops->family; u32 connsid; u32 peersid; err = selinux_skb_peerlbl_sid(skb, family, &peersid); if (err) return err; err = selinux_conn_sid(sksec->sid, peersid, &connsid); if (err) return err; req->secid = connsid; req->peer_secid = peersid; return selinux_netlbl_inet_conn_request(req, family); } static void selinux_inet_csk_clone(struct sock *newsk, const struct request_sock *req) { struct sk_security_struct *newsksec = newsk->sk_security; newsksec->sid = req->secid; newsksec->peer_sid = req->peer_secid; /* NOTE: Ideally, we should also get the isec->sid for the new socket in sync, but we don't have the isec available yet. So we will wait until sock_graft to do it, by which time it will have been created and available. */ /* We don't need to take any sort of lock here as we are the only * thread with access to newsksec */ selinux_netlbl_inet_csk_clone(newsk, req->rsk_ops->family); } static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) { u16 family = sk->sk_family; struct sk_security_struct *sksec = sk->sk_security; /* handle mapped IPv4 packets arriving via IPv6 sockets */ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP)) family = PF_INET; selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); } static int selinux_secmark_relabel_packet(u32 sid) { const struct task_security_struct *__tsec; u32 tsid; __tsec = selinux_cred(current_cred()); tsid = __tsec->sid; return avc_has_perm(&selinux_state, tsid, sid, SECCLASS_PACKET, PACKET__RELABELTO, NULL); } static void selinux_secmark_refcount_inc(void) { atomic_inc(&selinux_secmark_refcount); } static void selinux_secmark_refcount_dec(void) { atomic_dec(&selinux_secmark_refcount); } static void selinux_req_classify_flow(const struct request_sock *req, struct flowi_common *flic) { flic->flowic_secid = req->secid; } static int selinux_tun_dev_alloc_security(void **security) { struct tun_security_struct *tunsec; tunsec = kzalloc(sizeof(*tunsec), GFP_KERNEL); if (!tunsec) return -ENOMEM; tunsec->sid = current_sid(); *security = tunsec; return 0; } static void selinux_tun_dev_free_security(void *security) { kfree(security); } static int selinux_tun_dev_create(void) { u32 sid = current_sid(); /* we aren't taking into account the "sockcreate" SID since the socket * that is being created here is not a socket in the traditional sense, * instead it is a private sock, accessible only to the kernel, and * representing a wide range of network traffic spanning multiple * connections unlike traditional sockets - check the TUN driver to * get a better understanding of why this socket is special */ return avc_has_perm(&selinux_state, sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__CREATE, NULL); } static int selinux_tun_dev_attach_queue(void *security) { struct tun_security_struct *tunsec = security; return avc_has_perm(&selinux_state, current_sid(), tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__ATTACH_QUEUE, NULL); } static int selinux_tun_dev_attach(struct sock *sk, void *security) { struct tun_security_struct *tunsec = security; struct sk_security_struct *sksec = sk->sk_security; /* we don't currently perform any NetLabel based labeling here and it * isn't clear that we would want to do so anyway; while we could apply * labeling without the support of the TUN user the resulting labeled * traffic from the other end of the connection would almost certainly * cause confusion to the TUN user that had no idea network labeling * protocols were being used */ sksec->sid = tunsec->sid; sksec->sclass = SECCLASS_TUN_SOCKET; return 0; } static int selinux_tun_dev_open(void *security) { struct tun_security_struct *tunsec = security; u32 sid = current_sid(); int err; err = avc_has_perm(&selinux_state, sid, tunsec->sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELFROM, NULL); if (err) return err; err = avc_has_perm(&selinux_state, sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__RELABELTO, NULL); if (err) return err; tunsec->sid = sid; return 0; } #ifdef CONFIG_NETFILTER static unsigned int selinux_ip_forward(struct sk_buff *skb, const struct net_device *indev, u16 family) { int err; char *addrp; u32 peer_sid; struct common_audit_data ad; struct lsm_network_audit net = {0,}; u8 secmark_active; u8 netlbl_active; u8 peerlbl_active; if (!selinux_policycap_netpeer()) return NF_ACCEPT; secmark_active = selinux_secmark_enabled(); netlbl_active = netlbl_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return NF_ACCEPT; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid) != 0) return NF_DROP; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->netif = indev->ifindex; ad.u.net->family = family; if (selinux_parse_skb(skb, &ad, &addrp, 1, NULL) != 0) return NF_DROP; if (peerlbl_active) { err = selinux_inet_sys_rcv_skb(dev_net(indev), indev->ifindex, addrp, family, peer_sid, &ad); if (err) { selinux_netlbl_err(skb, family, err, 1); return NF_DROP; } } if (secmark_active) if (avc_has_perm(&selinux_state, peer_sid, skb->secmark, SECCLASS_PACKET, PACKET__FORWARD_IN, &ad)) return NF_DROP; if (netlbl_active) /* we do this in the FORWARD path and not the POST_ROUTING * path because we want to make sure we apply the necessary * labeling before IPsec is applied so we can leverage AH * protection */ if (selinux_netlbl_skbuff_setsid(skb, family, peer_sid) != 0) return NF_DROP; return NF_ACCEPT; } static unsigned int selinux_ipv4_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return selinux_ip_forward(skb, state->in, PF_INET); } #if IS_ENABLED(CONFIG_IPV6) static unsigned int selinux_ipv6_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return selinux_ip_forward(skb, state->in, PF_INET6); } #endif /* IPV6 */ static unsigned int selinux_ip_output(struct sk_buff *skb, u16 family) { struct sock *sk; u32 sid; if (!netlbl_enabled()) return NF_ACCEPT; /* we do this in the LOCAL_OUT path and not the POST_ROUTING path * because we want to make sure we apply the necessary labeling * before IPsec is applied so we can leverage AH protection */ sk = skb->sk; if (sk) { struct sk_security_struct *sksec; if (sk_listener(sk)) /* if the socket is the listening state then this * packet is a SYN-ACK packet which means it needs to * be labeled based on the connection/request_sock and * not the parent socket. unfortunately, we can't * lookup the request_sock yet as it isn't queued on * the parent socket until after the SYN-ACK is sent. * the "solution" is to simply pass the packet as-is * as any IP option based labeling should be copied * from the initial connection request (in the IP * layer). it is far from ideal, but until we get a * security label in the packet itself this is the * best we can do. */ return NF_ACCEPT; /* standard practice, label using the parent socket */ sksec = sk->sk_security; sid = sksec->sid; } else sid = SECINITSID_KERNEL; if (selinux_netlbl_skbuff_setsid(skb, family, sid) != 0) return NF_DROP; return NF_ACCEPT; } static unsigned int selinux_ipv4_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return selinux_ip_output(skb, PF_INET); } #if IS_ENABLED(CONFIG_IPV6) static unsigned int selinux_ipv6_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return selinux_ip_output(skb, PF_INET6); } #endif /* IPV6 */ static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb, int ifindex, u16 family) { struct sock *sk = skb_to_full_sk(skb); struct sk_security_struct *sksec; struct common_audit_data ad; struct lsm_network_audit net = {0,}; char *addrp; u8 proto = 0; if (sk == NULL) return NF_ACCEPT; sksec = sk->sk_security; ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->netif = ifindex; ad.u.net->family = family; if (selinux_parse_skb(skb, &ad, &addrp, 0, &proto)) return NF_DROP; if (selinux_secmark_enabled()) if (avc_has_perm(&selinux_state, sksec->sid, skb->secmark, SECCLASS_PACKET, PACKET__SEND, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (selinux_xfrm_postroute_last(sksec->sid, skb, &ad, proto)) return NF_DROP_ERR(-ECONNREFUSED); return NF_ACCEPT; } static unsigned int selinux_ip_postroute(struct sk_buff *skb, const struct net_device *outdev, u16 family) { u32 secmark_perm; u32 peer_sid; int ifindex = outdev->ifindex; struct sock *sk; struct common_audit_data ad; struct lsm_network_audit net = {0,}; char *addrp; u8 secmark_active; u8 peerlbl_active; /* If any sort of compatibility mode is enabled then handoff processing * to the selinux_ip_postroute_compat() function to deal with the * special handling. We do this in an attempt to keep this function * as fast and as clean as possible. */ if (!selinux_policycap_netpeer()) return selinux_ip_postroute_compat(skb, ifindex, family); secmark_active = selinux_secmark_enabled(); peerlbl_active = selinux_peerlbl_enabled(); if (!secmark_active && !peerlbl_active) return NF_ACCEPT; sk = skb_to_full_sk(skb); #ifdef CONFIG_XFRM /* If skb->dst->xfrm is non-NULL then the packet is undergoing an IPsec * packet transformation so allow the packet to pass without any checks * since we'll have another chance to perform access control checks * when the packet is on it's final way out. * NOTE: there appear to be some IPv6 multicast cases where skb->dst * is NULL, in this case go ahead and apply access control. * NOTE: if this is a local socket (skb->sk != NULL) that is in the * TCP listening state we cannot wait until the XFRM processing * is done as we will miss out on the SA label if we do; * unfortunately, this means more work, but it is only once per * connection. */ if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL && !(sk && sk_listener(sk))) return NF_ACCEPT; #endif if (sk == NULL) { /* Without an associated socket the packet is either coming * from the kernel or it is being forwarded; check the packet * to determine which and if the packet is being forwarded * query the packet directly to determine the security label. */ if (skb->skb_iif) { secmark_perm = PACKET__FORWARD_OUT; if (selinux_skb_peerlbl_sid(skb, family, &peer_sid)) return NF_DROP; } else { secmark_perm = PACKET__SEND; peer_sid = SECINITSID_KERNEL; } } else if (sk_listener(sk)) { /* Locally generated packet but the associated socket is in the * listening state which means this is a SYN-ACK packet. In * this particular case the correct security label is assigned * to the connection/request_sock but unfortunately we can't * query the request_sock as it isn't queued on the parent * socket until after the SYN-ACK packet is sent; the only * viable choice is to regenerate the label like we do in * selinux_inet_conn_request(). See also selinux_ip_output() * for similar problems. */ u32 skb_sid; struct sk_security_struct *sksec; sksec = sk->sk_security; if (selinux_skb_peerlbl_sid(skb, family, &skb_sid)) return NF_DROP; /* At this point, if the returned skb peerlbl is SECSID_NULL * and the packet has been through at least one XFRM * transformation then we must be dealing with the "final" * form of labeled IPsec packet; since we've already applied * all of our access controls on this packet we can safely * pass the packet. */ if (skb_sid == SECSID_NULL) { switch (family) { case PF_INET: if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return NF_ACCEPT; break; case PF_INET6: if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return NF_ACCEPT; break; default: return NF_DROP_ERR(-ECONNREFUSED); } } if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid)) return NF_DROP; secmark_perm = PACKET__SEND; } else { /* Locally generated packet, fetch the security label from the * associated socket. */ struct sk_security_struct *sksec = sk->sk_security; peer_sid = sksec->sid; secmark_perm = PACKET__SEND; } ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->netif = ifindex; ad.u.net->family = family; if (selinux_parse_skb(skb, &ad, &addrp, 0, NULL)) return NF_DROP; if (secmark_active) if (avc_has_perm(&selinux_state, peer_sid, skb->secmark, SECCLASS_PACKET, secmark_perm, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (peerlbl_active) { u32 if_sid; u32 node_sid; if (sel_netif_sid(dev_net(outdev), ifindex, &if_sid)) return NF_DROP; if (avc_has_perm(&selinux_state, peer_sid, if_sid, SECCLASS_NETIF, NETIF__EGRESS, &ad)) return NF_DROP_ERR(-ECONNREFUSED); if (sel_netnode_sid(addrp, family, &node_sid)) return NF_DROP; if (avc_has_perm(&selinux_state, peer_sid, node_sid, SECCLASS_NODE, NODE__SENDTO, &ad)) return NF_DROP_ERR(-ECONNREFUSED); } return NF_ACCEPT; } static unsigned int selinux_ipv4_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return selinux_ip_postroute(skb, state->out, PF_INET); } #if IS_ENABLED(CONFIG_IPV6) static unsigned int selinux_ipv6_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return selinux_ip_postroute(skb, state->out, PF_INET6); } #endif /* IPV6 */ #endif /* CONFIG_NETFILTER */ static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) { int rc = 0; unsigned int msg_len; unsigned int data_len = skb->len; unsigned char *data = skb->data; struct nlmsghdr *nlh; struct sk_security_struct *sksec = sk->sk_security; u16 sclass = sksec->sclass; u32 perm; while (data_len >= nlmsg_total_size(0)) { nlh = (struct nlmsghdr *)data; /* NOTE: the nlmsg_len field isn't reliably set by some netlink * users which means we can't reject skb's with bogus * length fields; our solution is to follow what * netlink_rcv_skb() does and simply skip processing at * messages with length fields that are clearly junk */ if (nlh->nlmsg_len < NLMSG_HDRLEN || nlh->nlmsg_len > data_len) return 0; rc = selinux_nlmsg_lookup(sclass, nlh->nlmsg_type, &perm); if (rc == 0) { rc = sock_has_perm(sk, perm); if (rc) return rc; } else if (rc == -EINVAL) { /* -EINVAL is a missing msg/perm mapping */ pr_warn_ratelimited("SELinux: unrecognized netlink" " message: protocol=%hu nlmsg_type=%hu sclass=%s" " pid=%d comm=%s\n", sk->sk_protocol, nlh->nlmsg_type, secclass_map[sclass - 1].name, task_pid_nr(current), current->comm); if (enforcing_enabled(&selinux_state) && !security_get_allow_unknown(&selinux_state)) return rc; rc = 0; } else if (rc == -ENOENT) { /* -ENOENT is a missing socket/class mapping, ignore */ rc = 0; } else { return rc; } /* move to the next message after applying netlink padding */ msg_len = NLMSG_ALIGN(nlh->nlmsg_len); if (msg_len >= data_len) return 0; data_len -= msg_len; data += msg_len; } return rc; } static void ipc_init_security(struct ipc_security_struct *isec, u16 sclass) { isec->sclass = sclass; isec->sid = current_sid(); } static int ipc_has_perm(struct kern_ipc_perm *ipc_perms, u32 perms) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(ipc_perms); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = ipc_perms->key; return avc_has_perm(&selinux_state, sid, isec->sid, isec->sclass, perms, &ad); } static int selinux_msg_msg_alloc_security(struct msg_msg *msg) { struct msg_security_struct *msec; msec = selinux_msg_msg(msg); msec->sid = SECINITSID_UNLABELED; return 0; } /* message queue security operations */ static int selinux_msg_queue_alloc_security(struct kern_ipc_perm *msq) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); int rc; isec = selinux_ipc(msq); ipc_init_security(isec, SECCLASS_MSGQ); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_MSGQ, MSGQ__CREATE, &ad); return rc; } static int selinux_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(msq); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; return avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_MSGQ, MSGQ__ASSOCIATE, &ad); } static int selinux_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd) { int err; int perms; switch (cmd) { case IPC_INFO: case MSG_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case IPC_STAT: case MSG_STAT: case MSG_STAT_ANY: perms = MSGQ__GETATTR | MSGQ__ASSOCIATE; break; case IPC_SET: perms = MSGQ__SETATTR; break; case IPC_RMID: perms = MSGQ__DESTROY; break; default: return 0; } err = ipc_has_perm(msq, perms); return err; } static int selinux_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg) { struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; u32 sid = current_sid(); int rc; isec = selinux_ipc(msq); msec = selinux_msg_msg(msg); /* * First time through, need to assign label to the message */ if (msec->sid == SECINITSID_UNLABELED) { /* * Compute new sid based on current process and * message queue this message will be stored in */ rc = security_transition_sid(&selinux_state, sid, isec->sid, SECCLASS_MSG, NULL, &msec->sid); if (rc) return rc; } ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; /* Can this process write to the queue? */ rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_MSGQ, MSGQ__WRITE, &ad); if (!rc) /* Can this process send the message */ rc = avc_has_perm(&selinux_state, sid, msec->sid, SECCLASS_MSG, MSG__SEND, &ad); if (!rc) /* Can the message be put in the queue? */ rc = avc_has_perm(&selinux_state, msec->sid, isec->sid, SECCLASS_MSGQ, MSGQ__ENQUEUE, &ad); return rc; } static int selinux_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { struct ipc_security_struct *isec; struct msg_security_struct *msec; struct common_audit_data ad; u32 sid = task_sid(target); int rc; isec = selinux_ipc(msq); msec = selinux_msg_msg(msg); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = msq->key; rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_MSGQ, MSGQ__READ, &ad); if (!rc) rc = avc_has_perm(&selinux_state, sid, msec->sid, SECCLASS_MSG, MSG__RECEIVE, &ad); return rc; } /* Shared Memory security operations */ static int selinux_shm_alloc_security(struct kern_ipc_perm *shp) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); int rc; isec = selinux_ipc(shp); ipc_init_security(isec, SECCLASS_SHM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_SHM, SHM__CREATE, &ad); return rc; } static int selinux_shm_associate(struct kern_ipc_perm *shp, int shmflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(shp); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = shp->key; return avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_SHM, SHM__ASSOCIATE, &ad); } /* Note, at this point, shp is locked down */ static int selinux_shm_shmctl(struct kern_ipc_perm *shp, int cmd) { int perms; int err; switch (cmd) { case IPC_INFO: case SHM_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case IPC_STAT: case SHM_STAT: case SHM_STAT_ANY: perms = SHM__GETATTR | SHM__ASSOCIATE; break; case IPC_SET: perms = SHM__SETATTR; break; case SHM_LOCK: case SHM_UNLOCK: perms = SHM__LOCK; break; case IPC_RMID: perms = SHM__DESTROY; break; default: return 0; } err = ipc_has_perm(shp, perms); return err; } static int selinux_shm_shmat(struct kern_ipc_perm *shp, char __user *shmaddr, int shmflg) { u32 perms; if (shmflg & SHM_RDONLY) perms = SHM__READ; else perms = SHM__READ | SHM__WRITE; return ipc_has_perm(shp, perms); } /* Semaphore security operations */ static int selinux_sem_alloc_security(struct kern_ipc_perm *sma) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); int rc; isec = selinux_ipc(sma); ipc_init_security(isec, SECCLASS_SEM); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; rc = avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_SEM, SEM__CREATE, &ad); return rc; } static int selinux_sem_associate(struct kern_ipc_perm *sma, int semflg) { struct ipc_security_struct *isec; struct common_audit_data ad; u32 sid = current_sid(); isec = selinux_ipc(sma); ad.type = LSM_AUDIT_DATA_IPC; ad.u.ipc_id = sma->key; return avc_has_perm(&selinux_state, sid, isec->sid, SECCLASS_SEM, SEM__ASSOCIATE, &ad); } /* Note, at this point, sma is locked down */ static int selinux_sem_semctl(struct kern_ipc_perm *sma, int cmd) { int err; u32 perms; switch (cmd) { case IPC_INFO: case SEM_INFO: /* No specific object, just general system-wide information. */ return avc_has_perm(&selinux_state, current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL); case GETPID: case GETNCNT: case GETZCNT: perms = SEM__GETATTR; break; case GETVAL: case GETALL: perms = SEM__READ; break; case SETVAL: case SETALL: perms = SEM__WRITE; break; case IPC_RMID: perms = SEM__DESTROY; break; case IPC_SET: perms = SEM__SETATTR; break; case IPC_STAT: case SEM_STAT: case SEM_STAT_ANY: perms = SEM__GETATTR | SEM__ASSOCIATE; break; default: return 0; } err = ipc_has_perm(sma, perms); return err; } static int selinux_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops, unsigned nsops, int alter) { u32 perms; if (alter) perms = SEM__READ | SEM__WRITE; else perms = SEM__READ; return ipc_has_perm(sma, perms); } static int selinux_ipc_permission(struct kern_ipc_perm *ipcp, short flag) { u32 av = 0; av = 0; if (flag & S_IRUGO) av |= IPC__UNIX_READ; if (flag & S_IWUGO) av |= IPC__UNIX_WRITE; if (av == 0) return 0; return ipc_has_perm(ipcp, av); } static void selinux_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid) { struct ipc_security_struct *isec = selinux_ipc(ipcp); *secid = isec->sid; } static void selinux_d_instantiate(struct dentry *dentry, struct inode *inode) { if (inode) inode_doinit_with_dentry(inode, dentry); } static int selinux_getprocattr(struct task_struct *p, char *name, char **value) { const struct task_security_struct *__tsec; u32 sid; int error; unsigned len; rcu_read_lock(); __tsec = selinux_cred(__task_cred(p)); if (current != p) { error = avc_has_perm(&selinux_state, current_sid(), __tsec->sid, SECCLASS_PROCESS, PROCESS__GETATTR, NULL); if (error) goto bad; } if (!strcmp(name, "current")) sid = __tsec->sid; else if (!strcmp(name, "prev")) sid = __tsec->osid; else if (!strcmp(name, "exec")) sid = __tsec->exec_sid; else if (!strcmp(name, "fscreate")) sid = __tsec->create_sid; else if (!strcmp(name, "keycreate")) sid = __tsec->keycreate_sid; else if (!strcmp(name, "sockcreate")) sid = __tsec->sockcreate_sid; else { error = -EINVAL; goto bad; } rcu_read_unlock(); if (!sid) return 0; error = security_sid_to_context(&selinux_state, sid, value, &len); if (error) return error; return len; bad: rcu_read_unlock(); return error; } static int selinux_setprocattr(const char *name, void *value, size_t size) { struct task_security_struct *tsec; struct cred *new; u32 mysid = current_sid(), sid = 0, ptsid; int error; char *str = value; /* * Basic control over ability to set these attributes at all. */ if (!strcmp(name, "exec")) error = avc_has_perm(&selinux_state, mysid, mysid, SECCLASS_PROCESS, PROCESS__SETEXEC, NULL); else if (!strcmp(name, "fscreate")) error = avc_has_perm(&selinux_state, mysid, mysid, SECCLASS_PROCESS, PROCESS__SETFSCREATE, NULL); else if (!strcmp(name, "keycreate")) error = avc_has_perm(&selinux_state, mysid, mysid, SECCLASS_PROCESS, PROCESS__SETKEYCREATE, NULL); else if (!strcmp(name, "sockcreate")) error = avc_has_perm(&selinux_state, mysid, mysid, SECCLASS_PROCESS, PROCESS__SETSOCKCREATE, NULL); else if (!strcmp(name, "current")) error = avc_has_perm(&selinux_state, mysid, mysid, SECCLASS_PROCESS, PROCESS__SETCURRENT, NULL); else error = -EINVAL; if (error) return error; /* Obtain a SID for the context, if one was specified. */ if (size && str[0] && str[0] != '\n') { if (str[size-1] == '\n') { str[size-1] = 0; size--; } error = security_context_to_sid(&selinux_state, value, size, &sid, GFP_KERNEL); if (error == -EINVAL && !strcmp(name, "fscreate")) { if (!has_cap_mac_admin(true)) { struct audit_buffer *ab; size_t audit_size; /* We strip a nul only if it is at the end, otherwise the * context contains a nul and we should audit that */ if (str[size - 1] == '\0') audit_size = size - 1; else audit_size = size; ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); audit_log_format(ab, "op=fscreate invalid_context="); audit_log_n_untrustedstring(ab, value, audit_size); audit_log_end(ab); return error; } error = security_context_to_sid_force( &selinux_state, value, size, &sid); } if (error) return error; } new = prepare_creds(); if (!new) return -ENOMEM; /* Permission checking based on the specified context is performed during the actual operation (execve, open/mkdir/...), when we know the full context of the operation. See selinux_bprm_creds_for_exec for the execve checks and may_create for the file creation checks. The operation will then fail if the context is not permitted. */ tsec = selinux_cred(new); if (!strcmp(name, "exec")) { tsec->exec_sid = sid; } else if (!strcmp(name, "fscreate")) { tsec->create_sid = sid; } else if (!strcmp(name, "keycreate")) { if (sid) { error = avc_has_perm(&selinux_state, mysid, sid, SECCLASS_KEY, KEY__CREATE, NULL); if (error) goto abort_change; } tsec->keycreate_sid = sid; } else if (!strcmp(name, "sockcreate")) { tsec->sockcreate_sid = sid; } else if (!strcmp(name, "current")) { error = -EINVAL; if (sid == 0) goto abort_change; /* Only allow single threaded processes to change context */ error = -EPERM; if (!current_is_single_threaded()) { error = security_bounded_transition(&selinux_state, tsec->sid, sid); if (error) goto abort_change; } /* Check permissions for the transition. */ error = avc_has_perm(&selinux_state, tsec->sid, sid, SECCLASS_PROCESS, PROCESS__DYNTRANSITION, NULL); if (error) goto abort_change; /* Check for ptracing, and update the task SID if ok. Otherwise, leave SID unchanged and fail. */ ptsid = ptrace_parent_sid(); if (ptsid != 0) { error = avc_has_perm(&selinux_state, ptsid, sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (error) goto abort_change; } tsec->sid = sid; } else { error = -EINVAL; goto abort_change; } commit_creds(new); return size; abort_change: abort_creds(new); return error; } static int selinux_ismaclabel(const char *name) { return (strcmp(name, XATTR_SELINUX_SUFFIX) == 0); } static int selinux_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) { return security_sid_to_context(&selinux_state, secid, secdata, seclen); } static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid) { return security_context_to_sid(&selinux_state, secdata, seclen, secid, GFP_KERNEL); } static void selinux_release_secctx(char *secdata, u32 seclen) { kfree(secdata); } static void selinux_inode_invalidate_secctx(struct inode *inode) { struct inode_security_struct *isec = selinux_inode(inode); spin_lock(&isec->lock); isec->initialized = LABEL_INVALID; spin_unlock(&isec->lock); } /* * called with inode->i_mutex locked */ static int selinux_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen) { int rc = selinux_inode_setsecurity(inode, XATTR_SELINUX_SUFFIX, ctx, ctxlen, 0); /* Do not return error when suppressing label (SBLABEL_MNT not set). */ return rc == -EOPNOTSUPP ? 0 : rc; } /* * called with inode->i_mutex locked */ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen) { return __vfs_setxattr_locked(dentry, XATTR_NAME_SELINUX, ctx, ctxlen, 0, NULL); } static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen) { int len = 0; len = selinux_inode_getsecurity(inode, XATTR_SELINUX_SUFFIX, ctx, true); if (len < 0) return len; *ctxlen = len; return 0; } #ifdef CONFIG_KEYS static int selinux_key_alloc(struct key *k, const struct cred *cred, unsigned long flags) { const struct task_security_struct *tsec; struct key_security_struct *ksec; ksec = kzalloc(sizeof(struct key_security_struct), GFP_KERNEL); if (!ksec) return -ENOMEM; tsec = selinux_cred(cred); if (tsec->keycreate_sid) ksec->sid = tsec->keycreate_sid; else ksec->sid = tsec->sid; k->security = ksec; return 0; } static void selinux_key_free(struct key *k) { struct key_security_struct *ksec = k->security; k->security = NULL; kfree(ksec); } static int selinux_key_permission(key_ref_t key_ref, const struct cred *cred, enum key_need_perm need_perm) { struct key *key; struct key_security_struct *ksec; u32 perm, sid; switch (need_perm) { case KEY_NEED_VIEW: perm = KEY__VIEW; break; case KEY_NEED_READ: perm = KEY__READ; break; case KEY_NEED_WRITE: perm = KEY__WRITE; break; case KEY_NEED_SEARCH: perm = KEY__SEARCH; break; case KEY_NEED_LINK: perm = KEY__LINK; break; case KEY_NEED_SETATTR: perm = KEY__SETATTR; break; case KEY_NEED_UNLINK: case KEY_SYSADMIN_OVERRIDE: case KEY_AUTHTOKEN_OVERRIDE: case KEY_DEFER_PERM_CHECK: return 0; default: WARN_ON(1); return -EPERM; } sid = cred_sid(cred); key = key_ref_to_ptr(key_ref); ksec = key->security; return avc_has_perm(&selinux_state, sid, ksec->sid, SECCLASS_KEY, perm, NULL); } static int selinux_key_getsecurity(struct key *key, char **_buffer) { struct key_security_struct *ksec = key->security; char *context = NULL; unsigned len; int rc; rc = security_sid_to_context(&selinux_state, ksec->sid, &context, &len); if (!rc) rc = len; *_buffer = context; return rc; } #ifdef CONFIG_KEY_NOTIFICATIONS static int selinux_watch_key(struct key *key) { struct key_security_struct *ksec = key->security; u32 sid = current_sid(); return avc_has_perm(&selinux_state, sid, ksec->sid, SECCLASS_KEY, KEY__VIEW, NULL); } #endif #endif #ifdef CONFIG_SECURITY_INFINIBAND static int selinux_ib_pkey_access(void *ib_sec, u64 subnet_prefix, u16 pkey_val) { struct common_audit_data ad; int err; u32 sid = 0; struct ib_security_struct *sec = ib_sec; struct lsm_ibpkey_audit ibpkey; err = sel_ib_pkey_sid(subnet_prefix, pkey_val, &sid); if (err) return err; ad.type = LSM_AUDIT_DATA_IBPKEY; ibpkey.subnet_prefix = subnet_prefix; ibpkey.pkey = pkey_val; ad.u.ibpkey = &ibpkey; return avc_has_perm(&selinux_state, sec->sid, sid, SECCLASS_INFINIBAND_PKEY, INFINIBAND_PKEY__ACCESS, &ad); } static int selinux_ib_endport_manage_subnet(void *ib_sec, const char *dev_name, u8 port_num) { struct common_audit_data ad; int err; u32 sid = 0; struct ib_security_struct *sec = ib_sec; struct lsm_ibendport_audit ibendport; err = security_ib_endport_sid(&selinux_state, dev_name, port_num, &sid); if (err) return err; ad.type = LSM_AUDIT_DATA_IBENDPORT; strncpy(ibendport.dev_name, dev_name, sizeof(ibendport.dev_name)); ibendport.port = port_num; ad.u.ibendport = &ibendport; return avc_has_perm(&selinux_state, sec->sid, sid, SECCLASS_INFINIBAND_ENDPORT, INFINIBAND_ENDPORT__MANAGE_SUBNET, &ad); } static int selinux_ib_alloc_security(void **ib_sec) { struct ib_security_struct *sec; sec = kzalloc(sizeof(*sec), GFP_KERNEL); if (!sec) return -ENOMEM; sec->sid = current_sid(); *ib_sec = sec; return 0; } static void selinux_ib_free_security(void *ib_sec) { kfree(ib_sec); } #endif #ifdef CONFIG_BPF_SYSCALL static int selinux_bpf(int cmd, union bpf_attr *attr, unsigned int size) { u32 sid = current_sid(); int ret; switch (cmd) { case BPF_MAP_CREATE: ret = avc_has_perm(&selinux_state, sid, sid, SECCLASS_BPF, BPF__MAP_CREATE, NULL); break; case BPF_PROG_LOAD: ret = avc_has_perm(&selinux_state, sid, sid, SECCLASS_BPF, BPF__PROG_LOAD, NULL); break; default: ret = 0; break; } return ret; } static u32 bpf_map_fmode_to_av(fmode_t fmode) { u32 av = 0; if (fmode & FMODE_READ) av |= BPF__MAP_READ; if (fmode & FMODE_WRITE) av |= BPF__MAP_WRITE; return av; } /* This function will check the file pass through unix socket or binder to see * if it is a bpf related object. And apply correspinding checks on the bpf * object based on the type. The bpf maps and programs, not like other files and * socket, are using a shared anonymous inode inside the kernel as their inode. * So checking that inode cannot identify if the process have privilege to * access the bpf object and that's why we have to add this additional check in * selinux_file_receive and selinux_binder_transfer_files. */ static int bpf_fd_pass(struct file *file, u32 sid) { struct bpf_security_struct *bpfsec; struct bpf_prog *prog; struct bpf_map *map; int ret; if (file->f_op == &bpf_map_fops) { map = file->private_data; bpfsec = map->security; ret = avc_has_perm(&selinux_state, sid, bpfsec->sid, SECCLASS_BPF, bpf_map_fmode_to_av(file->f_mode), NULL); if (ret) return ret; } else if (file->f_op == &bpf_prog_fops) { prog = file->private_data; bpfsec = prog->aux->security; ret = avc_has_perm(&selinux_state, sid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_RUN, NULL); if (ret) return ret; } return 0; } static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode) { u32 sid = current_sid(); struct bpf_security_struct *bpfsec; bpfsec = map->security; return avc_has_perm(&selinux_state, sid, bpfsec->sid, SECCLASS_BPF, bpf_map_fmode_to_av(fmode), NULL); } static int selinux_bpf_prog(struct bpf_prog *prog) { u32 sid = current_sid(); struct bpf_security_struct *bpfsec; bpfsec = prog->aux->security; return avc_has_perm(&selinux_state, sid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_RUN, NULL); } static int selinux_bpf_map_alloc(struct bpf_map *map) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); map->security = bpfsec; return 0; } static void selinux_bpf_map_free(struct bpf_map *map) { struct bpf_security_struct *bpfsec = map->security; map->security = NULL; kfree(bpfsec); } static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) { struct bpf_security_struct *bpfsec; bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); if (!bpfsec) return -ENOMEM; bpfsec->sid = current_sid(); aux->security = bpfsec; return 0; } static void selinux_bpf_prog_free(struct bpf_prog_aux *aux) { struct bpf_security_struct *bpfsec = aux->security; aux->security = NULL; kfree(bpfsec); } #endif static int selinux_lockdown(enum lockdown_reason what) { struct common_audit_data ad; u32 sid = current_sid(); int invalid_reason = (what <= LOCKDOWN_NONE) || (what == LOCKDOWN_INTEGRITY_MAX) || (what >= LOCKDOWN_CONFIDENTIALITY_MAX); if (WARN(invalid_reason, "Invalid lockdown reason")) { audit_log(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR, "lockdown_reason=invalid"); return -EINVAL; } ad.type = LSM_AUDIT_DATA_LOCKDOWN; ad.u.reason = what; if (what <= LOCKDOWN_INTEGRITY_MAX) return avc_has_perm(&selinux_state, sid, sid, SECCLASS_LOCKDOWN, LOCKDOWN__INTEGRITY, &ad); else return avc_has_perm(&selinux_state, sid, sid, SECCLASS_LOCKDOWN, LOCKDOWN__CONFIDENTIALITY, &ad); } struct lsm_blob_sizes selinux_blob_sizes __lsm_ro_after_init = { .lbs_cred = sizeof(struct task_security_struct), .lbs_file = sizeof(struct file_security_struct), .lbs_inode = sizeof(struct inode_security_struct), .lbs_ipc = sizeof(struct ipc_security_struct), .lbs_msg_msg = sizeof(struct msg_security_struct), }; #ifdef CONFIG_PERF_EVENTS static int selinux_perf_event_open(struct perf_event_attr *attr, int type) { u32 requested, sid = current_sid(); if (type == PERF_SECURITY_OPEN) requested = PERF_EVENT__OPEN; else if (type == PERF_SECURITY_CPU) requested = PERF_EVENT__CPU; else if (type == PERF_SECURITY_KERNEL) requested = PERF_EVENT__KERNEL; else if (type == PERF_SECURITY_TRACEPOINT) requested = PERF_EVENT__TRACEPOINT; else return -EINVAL; return avc_has_perm(&selinux_state, sid, sid, SECCLASS_PERF_EVENT, requested, NULL); } static int selinux_perf_event_alloc(struct perf_event *event) { struct perf_event_security_struct *perfsec; perfsec = kzalloc(sizeof(*perfsec), GFP_KERNEL); if (!perfsec) return -ENOMEM; perfsec->sid = current_sid(); event->security = perfsec; return 0; } static void selinux_perf_event_free(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; event->security = NULL; kfree(perfsec); } static int selinux_perf_event_read(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; u32 sid = current_sid(); return avc_has_perm(&selinux_state, sid, perfsec->sid, SECCLASS_PERF_EVENT, PERF_EVENT__READ, NULL); } static int selinux_perf_event_write(struct perf_event *event) { struct perf_event_security_struct *perfsec = event->security; u32 sid = current_sid(); return avc_has_perm(&selinux_state, sid, perfsec->sid, SECCLASS_PERF_EVENT, PERF_EVENT__WRITE, NULL); } #endif /* * IMPORTANT NOTE: When adding new hooks, please be careful to keep this order: * 1. any hooks that don't belong to (2.) or (3.) below, * 2. hooks that both access structures allocated by other hooks, and allocate * structures that can be later accessed by other hooks (mostly "cloning" * hooks), * 3. hooks that only allocate structures that can be later accessed by other * hooks ("allocating" hooks). * * Please follow block comment delimiters in the list to keep this order. * * This ordering is needed for SELinux runtime disable to work at least somewhat * safely. Breaking the ordering rules above might lead to NULL pointer derefs * when disabling SELinux at runtime. */ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr), LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction), LSM_HOOK_INIT(binder_transfer_binder, selinux_binder_transfer_binder), LSM_HOOK_INIT(binder_transfer_file, selinux_binder_transfer_file), LSM_HOOK_INIT(ptrace_access_check, selinux_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, selinux_ptrace_traceme), LSM_HOOK_INIT(capget, selinux_capget), LSM_HOOK_INIT(capset, selinux_capset), LSM_HOOK_INIT(capable, selinux_capable), LSM_HOOK_INIT(quotactl, selinux_quotactl), LSM_HOOK_INIT(quota_on, selinux_quota_on), LSM_HOOK_INIT(syslog, selinux_syslog), LSM_HOOK_INIT(vm_enough_memory, selinux_vm_enough_memory), LSM_HOOK_INIT(netlink_send, selinux_netlink_send), LSM_HOOK_INIT(bprm_creds_for_exec, selinux_bprm_creds_for_exec), LSM_HOOK_INIT(bprm_committing_creds, selinux_bprm_committing_creds), LSM_HOOK_INIT(bprm_committed_creds, selinux_bprm_committed_creds), LSM_HOOK_INIT(sb_free_security, selinux_sb_free_security), LSM_HOOK_INIT(sb_free_mnt_opts, selinux_free_mnt_opts), LSM_HOOK_INIT(sb_remount, selinux_sb_remount), LSM_HOOK_INIT(sb_kern_mount, selinux_sb_kern_mount), LSM_HOOK_INIT(sb_show_options, selinux_sb_show_options), LSM_HOOK_INIT(sb_statfs, selinux_sb_statfs), LSM_HOOK_INIT(sb_mount, selinux_mount), LSM_HOOK_INIT(sb_umount, selinux_umount), LSM_HOOK_INIT(sb_set_mnt_opts, selinux_set_mnt_opts), LSM_HOOK_INIT(sb_clone_mnt_opts, selinux_sb_clone_mnt_opts), LSM_HOOK_INIT(move_mount, selinux_move_mount), LSM_HOOK_INIT(dentry_init_security, selinux_dentry_init_security), LSM_HOOK_INIT(dentry_create_files_as, selinux_dentry_create_files_as), LSM_HOOK_INIT(inode_free_security, selinux_inode_free_security), LSM_HOOK_INIT(inode_init_security, selinux_inode_init_security), LSM_HOOK_INIT(inode_create, selinux_inode_create), LSM_HOOK_INIT(inode_link, selinux_inode_link), LSM_HOOK_INIT(inode_unlink, selinux_inode_unlink), LSM_HOOK_INIT(inode_symlink, selinux_inode_symlink), LSM_HOOK_INIT(inode_mkdir, selinux_inode_mkdir), LSM_HOOK_INIT(inode_rmdir, selinux_inode_rmdir), LSM_HOOK_INIT(inode_mknod, selinux_inode_mknod), LSM_HOOK_INIT(inode_rename, selinux_inode_rename), LSM_HOOK_INIT(inode_readlink, selinux_inode_readlink), LSM_HOOK_INIT(inode_follow_link, selinux_inode_follow_link), LSM_HOOK_INIT(inode_permission, selinux_inode_permission), LSM_HOOK_INIT(inode_setattr, selinux_inode_setattr), LSM_HOOK_INIT(inode_getattr, selinux_inode_getattr), LSM_HOOK_INIT(inode_setxattr, selinux_inode_setxattr), LSM_HOOK_INIT(inode_post_setxattr, selinux_inode_post_setxattr), LSM_HOOK_INIT(inode_getxattr, selinux_inode_getxattr), LSM_HOOK_INIT(inode_listxattr, selinux_inode_listxattr), LSM_HOOK_INIT(inode_removexattr, selinux_inode_removexattr), LSM_HOOK_INIT(inode_getsecurity, selinux_inode_getsecurity), LSM_HOOK_INIT(inode_setsecurity, selinux_inode_setsecurity), LSM_HOOK_INIT(inode_listsecurity, selinux_inode_listsecurity), LSM_HOOK_INIT(inode_getsecid, selinux_inode_getsecid), LSM_HOOK_INIT(inode_copy_up, selinux_inode_copy_up), LSM_HOOK_INIT(inode_copy_up_xattr, selinux_inode_copy_up_xattr), LSM_HOOK_INIT(path_notify, selinux_path_notify), LSM_HOOK_INIT(kernfs_init_security, selinux_kernfs_init_security), LSM_HOOK_INIT(file_permission, selinux_file_permission), LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security), LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl), LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat), LSM_HOOK_INIT(mmap_file, selinux_mmap_file), LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr), LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect), LSM_HOOK_INIT(file_lock, selinux_file_lock), LSM_HOOK_INIT(file_fcntl, selinux_file_fcntl), LSM_HOOK_INIT(file_set_fowner, selinux_file_set_fowner), LSM_HOOK_INIT(file_send_sigiotask, selinux_file_send_sigiotask), LSM_HOOK_INIT(file_receive, selinux_file_receive), LSM_HOOK_INIT(file_open, selinux_file_open), LSM_HOOK_INIT(task_alloc, selinux_task_alloc), LSM_HOOK_INIT(cred_prepare, selinux_cred_prepare), LSM_HOOK_INIT(cred_transfer, selinux_cred_transfer), LSM_HOOK_INIT(cred_getsecid, selinux_cred_getsecid), LSM_HOOK_INIT(kernel_act_as, selinux_kernel_act_as), LSM_HOOK_INIT(kernel_create_files_as, selinux_kernel_create_files_as), LSM_HOOK_INIT(kernel_module_request, selinux_kernel_module_request), LSM_HOOK_INIT(kernel_load_data, selinux_kernel_load_data), LSM_HOOK_INIT(kernel_read_file, selinux_kernel_read_file), LSM_HOOK_INIT(task_setpgid, selinux_task_setpgid), LSM_HOOK_INIT(task_getpgid, selinux_task_getpgid), LSM_HOOK_INIT(task_getsid, selinux_task_getsid), LSM_HOOK_INIT(task_getsecid, selinux_task_getsecid), LSM_HOOK_INIT(task_setnice, selinux_task_setnice), LSM_HOOK_INIT(task_setioprio, selinux_task_setioprio), LSM_HOOK_INIT(task_getioprio, selinux_task_getioprio), LSM_HOOK_INIT(task_prlimit, selinux_task_prlimit), LSM_HOOK_INIT(task_setrlimit, selinux_task_setrlimit), LSM_HOOK_INIT(task_setscheduler, selinux_task_setscheduler), LSM_HOOK_INIT(task_getscheduler, selinux_task_getscheduler), LSM_HOOK_INIT(task_movememory, selinux_task_movememory), LSM_HOOK_INIT(task_kill, selinux_task_kill), LSM_HOOK_INIT(task_to_inode, selinux_task_to_inode), LSM_HOOK_INIT(ipc_permission, selinux_ipc_permission), LSM_HOOK_INIT(ipc_getsecid, selinux_ipc_getsecid), LSM_HOOK_INIT(msg_queue_associate, selinux_msg_queue_associate), LSM_HOOK_INIT(msg_queue_msgctl, selinux_msg_queue_msgctl), LSM_HOOK_INIT(msg_queue_msgsnd, selinux_msg_queue_msgsnd), LSM_HOOK_INIT(msg_queue_msgrcv, selinux_msg_queue_msgrcv), LSM_HOOK_INIT(shm_associate, selinux_shm_associate), LSM_HOOK_INIT(shm_shmctl, selinux_shm_shmctl), LSM_HOOK_INIT(shm_shmat, selinux_shm_shmat), LSM_HOOK_INIT(sem_associate, selinux_sem_associate), LSM_HOOK_INIT(sem_semctl, selinux_sem_semctl), LSM_HOOK_INIT(sem_semop, selinux_sem_semop), LSM_HOOK_INIT(d_instantiate, selinux_d_instantiate), LSM_HOOK_INIT(getprocattr, selinux_getprocattr), LSM_HOOK_INIT(setprocattr, selinux_setprocattr), LSM_HOOK_INIT(ismaclabel, selinux_ismaclabel), LSM_HOOK_INIT(secctx_to_secid, selinux_secctx_to_secid), LSM_HOOK_INIT(release_secctx, selinux_release_secctx), LSM_HOOK_INIT(inode_invalidate_secctx, selinux_inode_invalidate_secctx), LSM_HOOK_INIT(inode_notifysecctx, selinux_inode_notifysecctx), LSM_HOOK_INIT(inode_setsecctx, selinux_inode_setsecctx), LSM_HOOK_INIT(unix_stream_connect, selinux_socket_unix_stream_connect), LSM_HOOK_INIT(unix_may_send, selinux_socket_unix_may_send), LSM_HOOK_INIT(socket_create, selinux_socket_create), LSM_HOOK_INIT(socket_post_create, selinux_socket_post_create), LSM_HOOK_INIT(socket_socketpair, selinux_socket_socketpair), LSM_HOOK_INIT(socket_bind, selinux_socket_bind), LSM_HOOK_INIT(socket_connect, selinux_socket_connect), LSM_HOOK_INIT(socket_listen, selinux_socket_listen), LSM_HOOK_INIT(socket_accept, selinux_socket_accept), LSM_HOOK_INIT(socket_sendmsg, selinux_socket_sendmsg), LSM_HOOK_INIT(socket_recvmsg, selinux_socket_recvmsg), LSM_HOOK_INIT(socket_getsockname, selinux_socket_getsockname), LSM_HOOK_INIT(socket_getpeername, selinux_socket_getpeername), LSM_HOOK_INIT(socket_getsockopt, selinux_socket_getsockopt), LSM_HOOK_INIT(socket_setsockopt, selinux_socket_setsockopt), LSM_HOOK_INIT(socket_shutdown, selinux_socket_shutdown), LSM_HOOK_INIT(socket_sock_rcv_skb, selinux_socket_sock_rcv_skb), LSM_HOOK_INIT(socket_getpeersec_stream, selinux_socket_getpeersec_stream), LSM_HOOK_INIT(socket_getpeersec_dgram, selinux_socket_getpeersec_dgram), LSM_HOOK_INIT(sk_free_security, selinux_sk_free_security), LSM_HOOK_INIT(sk_clone_security, selinux_sk_clone_security), LSM_HOOK_INIT(sk_getsecid, selinux_sk_getsecid), LSM_HOOK_INIT(sock_graft, selinux_sock_graft), LSM_HOOK_INIT(sctp_assoc_request, selinux_sctp_assoc_request), LSM_HOOK_INIT(sctp_sk_clone, selinux_sctp_sk_clone), LSM_HOOK_INIT(sctp_bind_connect, selinux_sctp_bind_connect), LSM_HOOK_INIT(inet_conn_request, selinux_inet_conn_request), LSM_HOOK_INIT(inet_csk_clone, selinux_inet_csk_clone), LSM_HOOK_INIT(inet_conn_established, selinux_inet_conn_established), LSM_HOOK_INIT(secmark_relabel_packet, selinux_secmark_relabel_packet), LSM_HOOK_INIT(secmark_refcount_inc, selinux_secmark_refcount_inc), LSM_HOOK_INIT(secmark_refcount_dec, selinux_secmark_refcount_dec), LSM_HOOK_INIT(req_classify_flow, selinux_req_classify_flow), LSM_HOOK_INIT(tun_dev_free_security, selinux_tun_dev_free_security), LSM_HOOK_INIT(tun_dev_create, selinux_tun_dev_create), LSM_HOOK_INIT(tun_dev_attach_queue, selinux_tun_dev_attach_queue), LSM_HOOK_INIT(tun_dev_attach, selinux_tun_dev_attach), LSM_HOOK_INIT(tun_dev_open, selinux_tun_dev_open), #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK_INIT(ib_pkey_access, selinux_ib_pkey_access), LSM_HOOK_INIT(ib_endport_manage_subnet, selinux_ib_endport_manage_subnet), LSM_HOOK_INIT(ib_free_security, selinux_ib_free_security), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_free_security, selinux_xfrm_policy_free), LSM_HOOK_INIT(xfrm_policy_delete_security, selinux_xfrm_policy_delete), LSM_HOOK_INIT(xfrm_state_free_security, selinux_xfrm_state_free), LSM_HOOK_INIT(xfrm_state_delete_security, selinux_xfrm_state_delete), LSM_HOOK_INIT(xfrm_policy_lookup, selinux_xfrm_policy_lookup), LSM_HOOK_INIT(xfrm_state_pol_flow_match, selinux_xfrm_state_pol_flow_match), LSM_HOOK_INIT(xfrm_decode_session, selinux_xfrm_decode_session), #endif #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_free, selinux_key_free), LSM_HOOK_INIT(key_permission, selinux_key_permission), LSM_HOOK_INIT(key_getsecurity, selinux_key_getsecurity), #ifdef CONFIG_KEY_NOTIFICATIONS LSM_HOOK_INIT(watch_key, selinux_watch_key), #endif #endif #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_known, selinux_audit_rule_known), LSM_HOOK_INIT(audit_rule_match, selinux_audit_rule_match), LSM_HOOK_INIT(audit_rule_free, selinux_audit_rule_free), #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf, selinux_bpf), LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free), LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_open, selinux_perf_event_open), LSM_HOOK_INIT(perf_event_free, selinux_perf_event_free), LSM_HOOK_INIT(perf_event_read, selinux_perf_event_read), LSM_HOOK_INIT(perf_event_write, selinux_perf_event_write), #endif LSM_HOOK_INIT(locked_down, selinux_lockdown), /* * PUT "CLONING" (ACCESSING + ALLOCATING) HOOKS HERE */ LSM_HOOK_INIT(fs_context_dup, selinux_fs_context_dup), LSM_HOOK_INIT(fs_context_parse_param, selinux_fs_context_parse_param), LSM_HOOK_INIT(sb_eat_lsm_opts, selinux_sb_eat_lsm_opts), LSM_HOOK_INIT(sb_add_mnt_opt, selinux_add_mnt_opt), #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_clone_security, selinux_xfrm_policy_clone), #endif /* * PUT "ALLOCATING" HOOKS HERE */ LSM_HOOK_INIT(msg_msg_alloc_security, selinux_msg_msg_alloc_security), LSM_HOOK_INIT(msg_queue_alloc_security, selinux_msg_queue_alloc_security), LSM_HOOK_INIT(shm_alloc_security, selinux_shm_alloc_security), LSM_HOOK_INIT(sb_alloc_security, selinux_sb_alloc_security), LSM_HOOK_INIT(inode_alloc_security, selinux_inode_alloc_security), LSM_HOOK_INIT(sem_alloc_security, selinux_sem_alloc_security), LSM_HOOK_INIT(secid_to_secctx, selinux_secid_to_secctx), LSM_HOOK_INIT(inode_getsecctx, selinux_inode_getsecctx), LSM_HOOK_INIT(sk_alloc_security, selinux_sk_alloc_security), LSM_HOOK_INIT(tun_dev_alloc_security, selinux_tun_dev_alloc_security), #ifdef CONFIG_SECURITY_INFINIBAND LSM_HOOK_INIT(ib_alloc_security, selinux_ib_alloc_security), #endif #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_alloc_security, selinux_xfrm_policy_alloc), LSM_HOOK_INIT(xfrm_state_alloc, selinux_xfrm_state_alloc), LSM_HOOK_INIT(xfrm_state_alloc_acquire, selinux_xfrm_state_alloc_acquire), #endif #ifdef CONFIG_KEYS LSM_HOOK_INIT(key_alloc, selinux_key_alloc), #endif #ifdef CONFIG_AUDIT LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init), #endif #ifdef CONFIG_BPF_SYSCALL LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc), LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc), #endif }; static __init int selinux_init(void) { pr_info("SELinux: Initializing.\n"); memset(&selinux_state, 0, sizeof(selinux_state)); enforcing_set(&selinux_state, selinux_enforcing_boot); checkreqprot_set(&selinux_state, selinux_checkreqprot_boot); selinux_avc_init(&selinux_state.avc); mutex_init(&selinux_state.status_lock); mutex_init(&selinux_state.policy_mutex); /* Set the security state for the initial task. */ cred_init_security(); default_noexec = !(VM_DATA_DEFAULT_FLAGS & VM_EXEC); avc_init(); avtab_cache_init(); ebitmap_cache_init(); hashtab_cache_init(); security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks), "selinux"); if (avc_add_callback(selinux_netcache_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC netcache callback\n"); if (avc_add_callback(selinux_lsm_notifier_avc_callback, AVC_CALLBACK_RESET)) panic("SELinux: Unable to register AVC LSM notifier callback\n"); if (selinux_enforcing_boot) pr_debug("SELinux: Starting in enforcing mode\n"); else pr_debug("SELinux: Starting in permissive mode\n"); fs_validate_description("selinux", selinux_fs_parameters); return 0; } static void delayed_superblock_init(struct super_block *sb, void *unused) { selinux_set_mnt_opts(sb, NULL, 0, NULL); } void selinux_complete_init(void) { pr_debug("SELinux: Completing initialization.\n"); /* Set up any superblocks initialized prior to the policy load. */ pr_debug("SELinux: Setting up existing superblocks.\n"); iterate_supers(delayed_superblock_init, NULL); } /* SELinux requires early initialization in order to label all processes and objects when they are created. */ DEFINE_LSM(selinux) = { .name = "selinux", .flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE, .enabled = &selinux_enabled_boot, .blobs = &selinux_blob_sizes, .init = selinux_init, }; #if defined(CONFIG_NETFILTER) static const struct nf_hook_ops selinux_nf_ops[] = { { .hook = selinux_ipv4_postroute, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_SELINUX_LAST, }, { .hook = selinux_ipv4_forward, .pf = NFPROTO_IPV4, .hooknum = NF_INET_FORWARD, .priority = NF_IP_PRI_SELINUX_FIRST, }, { .hook = selinux_ipv4_output, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_SELINUX_FIRST, }, #if IS_ENABLED(CONFIG_IPV6) { .hook = selinux_ipv6_postroute, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_SELINUX_LAST, }, { .hook = selinux_ipv6_forward, .pf = NFPROTO_IPV6, .hooknum = NF_INET_FORWARD, .priority = NF_IP6_PRI_SELINUX_FIRST, }, { .hook = selinux_ipv6_output, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_SELINUX_FIRST, }, #endif /* IPV6 */ }; static int __net_init selinux_nf_register(struct net *net) { return nf_register_net_hooks(net, selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops)); } static void __net_exit selinux_nf_unregister(struct net *net) { nf_unregister_net_hooks(net, selinux_nf_ops, ARRAY_SIZE(selinux_nf_ops)); } static struct pernet_operations selinux_net_ops = { .init = selinux_nf_register, .exit = selinux_nf_unregister, }; static int __init selinux_nf_ip_init(void) { int err; if (!selinux_enabled_boot) return 0; pr_debug("SELinux: Registering netfilter hooks\n"); err = register_pernet_subsys(&selinux_net_ops); if (err) panic("SELinux: register_pernet_subsys: error %d\n", err); return 0; } __initcall(selinux_nf_ip_init); #ifdef CONFIG_SECURITY_SELINUX_DISABLE static void selinux_nf_ip_exit(void) { pr_debug("SELinux: Unregistering netfilter hooks\n"); unregister_pernet_subsys(&selinux_net_ops); } #endif #else /* CONFIG_NETFILTER */ #ifdef CONFIG_SECURITY_SELINUX_DISABLE #define selinux_nf_ip_exit() #endif #endif /* CONFIG_NETFILTER */ #ifdef CONFIG_SECURITY_SELINUX_DISABLE int selinux_disable(struct selinux_state *state) { if (selinux_initialized(state)) { /* Not permitted after initial policy load. */ return -EINVAL; } if (selinux_disabled(state)) { /* Only do this once. */ return -EINVAL; } selinux_mark_disabled(state); pr_info("SELinux: Disabled at runtime.\n"); /* * Unregister netfilter hooks. * Must be done before security_delete_hooks() to avoid breaking * runtime disable. */ selinux_nf_ip_exit(); security_delete_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks)); /* Try to destroy the avc node cache */ avc_disable(); /* Unregister selinuxfs. */ exit_sel_fs(); return 0; } #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 | // SPDX-License-Identifier: GPL-2.0 /* * Fast batching percpu counters. */ #include <linux/percpu_counter.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/debugobjects.h> #ifdef CONFIG_HOTPLUG_CPU static LIST_HEAD(percpu_counters); static DEFINE_SPINLOCK(percpu_counters_lock); #endif #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER static const struct debug_obj_descr percpu_counter_debug_descr; static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state) { struct percpu_counter *fbc = addr; switch (state) { case ODEBUG_STATE_ACTIVE: percpu_counter_destroy(fbc); debug_object_free(fbc, &percpu_counter_debug_descr); return true; default: return false; } } static const struct debug_obj_descr percpu_counter_debug_descr = { .name = "percpu_counter", .fixup_free = percpu_counter_fixup_free, }; static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { debug_object_init(fbc, &percpu_counter_debug_descr); debug_object_activate(fbc, &percpu_counter_debug_descr); } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { debug_object_deactivate(fbc, &percpu_counter_debug_descr); debug_object_free(fbc, &percpu_counter_debug_descr); } #else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { } #endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); for_each_possible_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); *pcount = 0; } fbc->count = amount; raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_set); /** * This function is both preempt and irq safe. The former is due to explicit * preemption disable. The latter is guaranteed by the fact that the slow path * is explicitly protected by an irq-safe spinlock whereas the fast patch uses * this_cpu_add which is irq-safe by definition. Hence there is no need muck * with irq state before calling this one */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; preempt_disable(); count = __this_cpu_read(*fbc->counters) + amount; if (abs(count) >= batch) { unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); fbc->count += count; __this_cpu_sub(*fbc->counters, count - amount); raw_spin_unlock_irqrestore(&fbc->lock, flags); } else { this_cpu_add(*fbc->counters, amount); } preempt_enable(); } EXPORT_SYMBOL(percpu_counter_add_batch); /* * For percpu_counter with a big batch, the devication of its count could * be big, and there is requirement to reduce the deviation, like when the * counter's batch could be runtime decreased to get a better accuracy, * which can be achieved by running this sync function on each CPU. */ void percpu_counter_sync(struct percpu_counter *fbc) { unsigned long flags; s64 count; raw_spin_lock_irqsave(&fbc->lock, flags); count = __this_cpu_read(*fbc->counters); fbc->count += count; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_sync); /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive() */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); ret = fbc->count; for_each_online_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; } raw_spin_unlock_irqrestore(&fbc->lock, flags); return ret; } EXPORT_SYMBOL(__percpu_counter_sum); int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, struct lock_class_key *key) { unsigned long flags __maybe_unused; raw_spin_lock_init(&fbc->lock); lockdep_set_class(&fbc->lock, key); fbc->count = amount; fbc->counters = alloc_percpu_gfp(s32, gfp); if (!fbc->counters) return -ENOMEM; debug_percpu_counter_activate(fbc); #ifdef CONFIG_HOTPLUG_CPU INIT_LIST_HEAD(&fbc->list); spin_lock_irqsave(&percpu_counters_lock, flags); list_add(&fbc->list, &percpu_counters); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif return 0; } EXPORT_SYMBOL(__percpu_counter_init); void percpu_counter_destroy(struct percpu_counter *fbc) { unsigned long flags __maybe_unused; if (!fbc->counters) return; debug_percpu_counter_deactivate(fbc); #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); list_del(&fbc->list); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif free_percpu(fbc->counters); fbc->counters = NULL; } EXPORT_SYMBOL(percpu_counter_destroy); int percpu_counter_batch __read_mostly = 32; EXPORT_SYMBOL(percpu_counter_batch); static int compute_batch_value(unsigned int cpu) { int nr = num_online_cpus(); percpu_counter_batch = max(32, nr*2); return 0; } static int percpu_counter_cpu_dead(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU struct percpu_counter *fbc; compute_batch_value(cpu); spin_lock_irq(&percpu_counters_lock); list_for_each_entry(fbc, &percpu_counters, list) { s32 *pcount; raw_spin_lock(&fbc->lock); pcount = per_cpu_ptr(fbc->counters, cpu); fbc->count += *pcount; *pcount = 0; raw_spin_unlock(&fbc->lock); } spin_unlock_irq(&percpu_counters_lock); #endif return 0; } /* * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else return -1; } /* Need to use precise count */ count = percpu_counter_sum(fbc); if (count > rhs) return 1; else if (count < rhs) return -1; else return 0; } EXPORT_SYMBOL(__percpu_counter_compare); static int __init percpu_counter_startup(void) { int ret; ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online", compute_batch_value, NULL); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD, "lib/percpu_cnt:dead", NULL, percpu_counter_cpu_dead); WARN_ON(ret < 0); return 0; } module_init(percpu_counter_startup); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 | /* SPDX-License-Identifier: GPL-2.0+ */ #ifndef _LINUX_XARRAY_H #define _LINUX_XARRAY_H /* * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation * Author: Matthew Wilcox <willy@infradead.org> * * See Documentation/core-api/xarray.rst for how to use the XArray. */ #include <linux/bug.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/kconfig.h> #include <linux/kernel.h> #include <linux/rcupdate.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/types.h> /* * The bottom two bits of the entry determine how the XArray interprets * the contents: * * 00: Pointer entry * 10: Internal entry * x1: Value entry or tagged pointer * * Attempting to store internal entries in the XArray is a bug. * * Most internal entries are pointers to the next node in the tree. * The following internal entries have a special meaning: * * 0-62: Sibling entries * 256: Retry entry * 257: Zero entry * * Errors are also represented as internal entries, but use the negative * space (-4094 to -2). They're never stored in the slots array; only * returned by the normal API. */ #define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) /** * xa_mk_value() - Create an XArray entry from an integer. * @v: Value to store in XArray. * * Context: Any context. * Return: An entry suitable for storing in the XArray. */ static inline void *xa_mk_value(unsigned long v) { WARN_ON((long)v < 0); return (void *)((v << 1) | 1); } /** * xa_to_value() - Get value stored in an XArray entry. * @entry: XArray entry. * * Context: Any context. * Return: The value stored in the XArray entry. */ static inline unsigned long xa_to_value(const void *entry) { return (unsigned long)entry >> 1; } /** * xa_is_value() - Determine if an entry is a value. * @entry: XArray entry. * * Context: Any context. * Return: True if the entry is a value, false if it is a pointer. */ static inline bool xa_is_value(const void *entry) { return (unsigned long)entry & 1; } /** * xa_tag_pointer() - Create an XArray entry for a tagged pointer. * @p: Plain pointer. * @tag: Tag value (0, 1 or 3). * * If the user of the XArray prefers, they can tag their pointers instead * of storing value entries. Three tags are available (0, 1 and 3). * These are distinct from the xa_mark_t as they are not replicated up * through the array and cannot be searched for. * * Context: Any context. * Return: An XArray entry. */ static inline void *xa_tag_pointer(void *p, unsigned long tag) { return (void *)((unsigned long)p | tag); } /** * xa_untag_pointer() - Turn an XArray entry into a plain pointer. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the untagged version of the pointer. * * Context: Any context. * Return: A pointer. */ static inline void *xa_untag_pointer(void *entry) { return (void *)((unsigned long)entry & ~3UL); } /** * xa_pointer_tag() - Get the tag stored in an XArray entry. * @entry: XArray entry. * * If you have stored a tagged pointer in the XArray, call this function * to get the tag of that pointer. * * Context: Any context. * Return: A tag. */ static inline unsigned int xa_pointer_tag(void *entry) { return (unsigned long)entry & 3UL; } /* * xa_mk_internal() - Create an internal entry. * @v: Value to turn into an internal entry. * * Internal entries are used for a number of purposes. Entries 0-255 are * used for sibling entries (only 0-62 are used by the current code). 256 * is used for the retry entry. 257 is used for the reserved / zero entry. * Negative internal entries are used to represent errnos. Node pointers * are also tagged as internal entries in some situations. * * Context: Any context. * Return: An XArray internal entry corresponding to this value. */ static inline void *xa_mk_internal(unsigned long v) { return (void *)((v << 2) | 2); } /* * xa_to_internal() - Extract the value from an internal entry. * @entry: XArray entry. * * Context: Any context. * Return: The value which was stored in the internal entry. */ static inline unsigned long xa_to_internal(const void *entry) { return (unsigned long)entry >> 2; } /* * xa_is_internal() - Is the entry an internal entry? * @entry: XArray entry. * * Context: Any context. * Return: %true if the entry is an internal entry. */ static inline bool xa_is_internal(const void *entry) { return ((unsigned long)entry & 3) == 2; } #define XA_ZERO_ENTRY xa_mk_internal(257) /** * xa_is_zero() - Is the entry a zero entry? * @entry: Entry retrieved from the XArray * * The normal API will return NULL as the contents of a slot containing * a zero entry. You can only see zero entries by using the advanced API. * * Return: %true if the entry is a zero entry. */ static inline bool xa_is_zero(const void *entry) { return unlikely(entry == XA_ZERO_ENTRY); } /** * xa_is_err() - Report whether an XArray operation returned an error * @entry: Result from calling an XArray function * * If an XArray operation cannot complete an operation, it will return * a special value indicating an error. This function tells you * whether an error occurred; xa_err() tells you which error occurred. * * Context: Any context. * Return: %true if the entry indicates an error. */ static inline bool xa_is_err(const void *entry) { return unlikely(xa_is_internal(entry) && entry >= xa_mk_internal(-MAX_ERRNO)); } /** * xa_err() - Turn an XArray result into an errno. * @entry: Result from calling an XArray function. * * If an XArray operation cannot complete an operation, it will return * a special pointer value which encodes an errno. This function extracts * the errno from the pointer value, or returns 0 if the pointer does not * represent an errno. * * Context: Any context. * Return: A negative errno or 0. */ static inline int xa_err(void *entry) { /* xa_to_internal() would not do sign extension. */ if (xa_is_err(entry)) return (long)entry >> 2; return 0; } /** * struct xa_limit - Represents a range of IDs. * @min: The lowest ID to allocate (inclusive). * @max: The maximum ID to allocate (inclusive). * * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. * Two common ranges are predefined for you: * * xa_limit_32b - [0 - UINT_MAX] * * xa_limit_31b - [0 - INT_MAX] */ struct xa_limit { u32 max; u32 min; }; #define XA_LIMIT(_min, _max) (struct xa_limit) { .min = _min, .max = _max } #define xa_limit_32b XA_LIMIT(0, UINT_MAX) #define xa_limit_31b XA_LIMIT(0, INT_MAX) typedef unsigned __bitwise xa_mark_t; #define XA_MARK_0 ((__force xa_mark_t)0U) #define XA_MARK_1 ((__force xa_mark_t)1U) #define XA_MARK_2 ((__force xa_mark_t)2U) #define XA_PRESENT ((__force xa_mark_t)8U) #define XA_MARK_MAX XA_MARK_2 #define XA_FREE_MARK XA_MARK_0 enum xa_lock_type { XA_LOCK_IRQ = 1, XA_LOCK_BH = 2, }; /* * Values for xa_flags. The radix tree stores its GFP flags in the xa_flags, * and we remain compatible with that. */ #define XA_FLAGS_LOCK_IRQ ((__force gfp_t)XA_LOCK_IRQ) #define XA_FLAGS_LOCK_BH ((__force gfp_t)XA_LOCK_BH) #define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U) #define XA_FLAGS_ALLOC_WRAPPED ((__force gfp_t)16U) #define XA_FLAGS_ACCOUNT ((__force gfp_t)32U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) /* ALLOC is for a normal 0-based alloc. ALLOC1 is for an 1-based alloc */ #define XA_FLAGS_ALLOC (XA_FLAGS_TRACK_FREE | XA_FLAGS_MARK(XA_FREE_MARK)) #define XA_FLAGS_ALLOC1 (XA_FLAGS_TRACK_FREE | XA_FLAGS_ZERO_BUSY) /** * struct xarray - The anchor of the XArray. * @xa_lock: Lock that protects the contents of the XArray. * * To use the xarray, define it statically or embed it in your data structure. * It is a very small data structure, so it does not usually make sense to * allocate it separately and keep a pointer to it in your data structure. * * You may use the xa_lock to protect your own data structures as well. */ /* * If all of the entries in the array are NULL, @xa_head is a NULL pointer. * If the only non-NULL entry in the array is at index 0, @xa_head is that * entry. If any other entry in the array is non-NULL, @xa_head points * to an @xa_node. */ struct xarray { spinlock_t xa_lock; /* private: The rest of the data structure is not to be used directly. */ gfp_t xa_flags; void __rcu * xa_head; }; #define XARRAY_INIT(name, flags) { \ .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ .xa_flags = flags, \ .xa_head = NULL, \ } /** * DEFINE_XARRAY_FLAGS() - Define an XArray with custom flags. * @name: A string that names your XArray. * @flags: XA_FLAG values. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name and flags. It is * equivalent to calling xa_init_flags() on the array, but it does the * initialisation at compiletime instead of runtime. */ #define DEFINE_XARRAY_FLAGS(name, flags) \ struct xarray name = XARRAY_INIT(name, flags) /** * DEFINE_XARRAY() - Define an XArray. * @name: A string that names your XArray. * * This is intended for file scope definitions of XArrays. It declares * and initialises an empty XArray with the chosen name. It is equivalent * to calling xa_init() on the array, but it does the initialisation at * compiletime instead of runtime. */ #define DEFINE_XARRAY(name) DEFINE_XARRAY_FLAGS(name, 0) /** * DEFINE_XARRAY_ALLOC() - Define an XArray which allocates IDs starting at 0. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) /** * DEFINE_XARRAY_ALLOC1() - Define an XArray which allocates IDs starting at 1. * @name: A string that names your XArray. * * This is intended for file scope definitions of allocating XArrays. * See also DEFINE_XARRAY(). */ #define DEFINE_XARRAY_ALLOC1(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC1) void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_erase(struct xarray *, unsigned long index); void *xa_store_range(struct xarray *, unsigned long first, unsigned long last, void *entry, gfp_t); bool xa_get_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); void *xa_find(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); void *xa_find_after(struct xarray *xa, unsigned long *index, unsigned long max, xa_mark_t) __attribute__((nonnull(2))); unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); void xa_destroy(struct xarray *); /** * xa_init_flags() - Initialise an empty XArray with flags. * @xa: XArray. * @flags: XA_FLAG values. * * If you need to initialise an XArray with special flags (eg you need * to take the lock from interrupt context), use this function instead * of xa_init(). * * Context: Any context. */ static inline void xa_init_flags(struct xarray *xa, gfp_t flags) { spin_lock_init(&xa->xa_lock); xa->xa_flags = flags; xa->xa_head = NULL; } /** * xa_init() - Initialise an empty XArray. * @xa: XArray. * * An empty XArray is full of NULL entries. * * Context: Any context. */ static inline void xa_init(struct xarray *xa) { xa_init_flags(xa, 0); } /** * xa_empty() - Determine if an array has any present entries. * @xa: XArray. * * Context: Any context. * Return: %true if the array contains only NULL pointers. */ static inline bool xa_empty(const struct xarray *xa) { return xa->xa_head == NULL; } /** * xa_marked() - Inquire whether any entry in this array has a mark set * @xa: Array * @mark: Mark value * * Context: Any context. * Return: %true if any entry has this mark set. */ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) { return xa->xa_flags & XA_FLAGS_MARK(mark); } /** * xa_for_each_range() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * @last: Last index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_range() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_range(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_range(xa, index, entry, start, last) \ for (index = start, \ entry = xa_find(xa, &index, last, XA_PRESENT); \ entry; \ entry = xa_find_after(xa, &index, last, XA_PRESENT)) /** * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @start: First index to retrieve from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you * want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set * to NULL and @index will have a value less than or equal to max. * * xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). * xa_for_each_start() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each() iterator instead. * The xas_for_each() iterator will expand into more inline code than * xa_for_each_start(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_start(xa, index, entry, start) \ xa_for_each_range(xa, index, entry, start, ULONG_MAX) /** * xa_for_each() - Iterate over present entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. You may modify @index during the iteration if you want * to skip or reprocess indices. It is safe to modify the array during the * iteration. At the end of the iteration, @entry will be set to NULL and * @index will have a value less than or equal to max. * * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock * after each iteration, it will also end up being O(n.log(n)). xa_for_each() * will spin if it hits a retry entry; if you intend to see retry entries, * you should use the xas_for_each() iterator instead. The xas_for_each() * iterator will expand into more inline code than xa_for_each(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each(xa, index, entry) \ xa_for_each_start(xa, index, entry, 0) /** * xa_for_each_marked() - Iterate over marked entries in an XArray. * @xa: XArray. * @index: Index of @entry. * @entry: Entry retrieved from array. * @filter: Selection criterion. * * During the iteration, @entry will have the value of the entry stored * in @xa at @index. The iteration will skip all entries in the array * which do not match @filter. You may modify @index during the iteration * if you want to skip or reprocess indices. It is safe to modify the array * during the iteration. At the end of the iteration, @entry will be set to * NULL and @index will have a value less than or equal to max. * * xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n). * You have to handle your own locking with xas_for_each(), and if you have * to unlock after each iteration, it will also end up being O(n.log(n)). * xa_for_each_marked() will spin if it hits a retry entry; if you intend to * see retry entries, you should use the xas_for_each_marked() iterator * instead. The xas_for_each_marked() iterator will expand into more inline * code than xa_for_each_marked(). * * Context: Any context. Takes and releases the RCU lock. */ #define xa_for_each_marked(xa, index, entry, filter) \ for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \ entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter)) #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) #define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) #define xa_lock_bh(xa) spin_lock_bh(&(xa)->xa_lock) #define xa_unlock_bh(xa) spin_unlock_bh(&(xa)->xa_lock) #define xa_lock_irq(xa) spin_lock_irq(&(xa)->xa_lock) #define xa_unlock_irq(xa) spin_unlock_irq(&(xa)->xa_lock) #define xa_lock_irqsave(xa, flags) \ spin_lock_irqsave(&(xa)->xa_lock, flags) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) #define xa_lock_nested(xa, subclass) \ spin_lock_nested(&(xa)->xa_lock, subclass) #define xa_lock_bh_nested(xa, subclass) \ spin_lock_bh_nested(&(xa)->xa_lock, subclass) #define xa_lock_irq_nested(xa, subclass) \ spin_lock_irq_nested(&(xa)->xa_lock, subclass) #define xa_lock_irqsave_nested(xa, flags, subclass) \ spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass) /* * Versions of the normal API which require the caller to hold the * xa_lock. If the GFP flags allow it, they will drop the lock to * allocate memory, then reacquire it afterwards. These functions * may also re-enable interrupts if the XArray flags indicate the * locking should be interrupt safe. */ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); int __must_check __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __must_check __xa_alloc(struct xarray *, u32 *id, void *entry, struct xa_limit, gfp_t); int __must_check __xa_alloc_cyclic(struct xarray *, u32 *id, void *entry, struct xa_limit, u32 *next, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); /** * xa_store_bh() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_store_irq() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * This function is like calling xa_store() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The old entry at this index or xa_err() if an error happened. */ static inline void *xa_store_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_erase_bh() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: The entry which used to be at this index. */ static inline void *xa_erase_bh(struct xarray *xa, unsigned long index) { void *entry; xa_lock_bh(xa); entry = __xa_erase(xa, index); xa_unlock_bh(xa); return entry; } /** * xa_erase_irq() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: The entry which used to be at this index. */ static inline void *xa_erase_irq(struct xarray *xa, unsigned long index) { void *entry; xa_lock_irq(xa); entry = __xa_erase(xa, index); xa_unlock_irq(xa); return entry; } /** * xa_cmpxchg() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * If the entry at @index is the same as @old, replace it with @entry. * If the return value is equal to @old, then the exchange was successful. * * Context: Any context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock(xa); return curr; } /** * xa_cmpxchg_bh() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables softirqs * while holding the array lock. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_bh(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_bh(xa); return curr; } /** * xa_cmpxchg_irq() - Conditionally replace an entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New value to place in array. * @gfp: Memory allocation flags. * * This function is like calling xa_cmpxchg() except it disables interrupts * while holding the array lock. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: The old value at this index or xa_err() if an error happened. */ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { void *curr; might_alloc(gfp); xa_lock_irq(xa); curr = __xa_cmpxchg(xa, index, old, entry, gfp); xa_unlock_irq(xa); return curr; } /** * xa_insert() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock(xa); return err; } /** * xa_insert_bh() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_bh(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_bh(xa); return err; } /** * xa_insert_irq() - Store this entry in the XArray unless another entry is * already present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int __must_check xa_insert_irq(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_insert(xa, index, entry, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline __must_check int xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock(xa); return err; } /** * xa_alloc_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc(xa, id, entry, limit, gfp); xa_unlock_irq(xa); return err; } /** * xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Takes and releases the xa_lock. May sleep if * the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock(xa); return err; } /** * xa_alloc_cyclic_bh() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_bh(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_bh(xa); return err; } /** * xa_alloc_cyclic_irq() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. May sleep if the @gfp flags permit. * Return: 0 if the allocation succeeded without wrapping. 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated or -EBUSY if there are no free entries in @limit. */ static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { int err; might_alloc(gfp); xa_lock_irq(xa); err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp); xa_unlock_irq(xa); return err; } /** * xa_reserve() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * Ensures there is somewhere to store an entry at @index in the array. * If there is already something stored at @index, this function does * nothing. If there was nothing there, the entry is marked as reserved. * Loading from a reserved entry returns a %NULL pointer. * * If you do not use the entry that you have reserved, call xa_release() * or xa_erase() to free any unnecessary memory. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_bh() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * A softirq-disabling version of xa_reserve(). * * Context: Any context. Takes and releases the xa_lock while * disabling softirqs. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_bh(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_bh(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_reserve_irq() - Reserve this index in the XArray. * @xa: XArray. * @index: Index into array. * @gfp: Memory allocation flags. * * An interrupt-disabling version of xa_reserve(). * * Context: Process context. Takes and releases the xa_lock while * disabling interrupts. * Return: 0 if the reservation succeeded or -ENOMEM if it failed. */ static inline __must_check int xa_reserve_irq(struct xarray *xa, unsigned long index, gfp_t gfp) { return xa_err(xa_cmpxchg_irq(xa, index, NULL, XA_ZERO_ENTRY, gfp)); } /** * xa_release() - Release a reserved entry. * @xa: XArray. * @index: Index of entry. * * After calling xa_reserve(), you can call this function to release the * reservation. If the entry at @index has been stored to, this function * will do nothing. */ static inline void xa_release(struct xarray *xa, unsigned long index) { xa_cmpxchg(xa, index, XA_ZERO_ENTRY, NULL, 0); } /* Everything below here is the Advanced API. Proceed with caution. */ /* * The xarray is constructed out of a set of 'chunks' of pointers. Choosing * the best chunk size requires some tradeoffs. A power of two recommends * itself so that we can walk the tree based purely on shifts and masks. * Generally, the larger the better; as the number of slots per level of the * tree increases, the less tall the tree needs to be. But that needs to be * balanced against the memory consumption of each node. On a 64-bit system, * xa_node is currently 576 bytes, and we get 7 of them per 4kB page. If we * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. */ #ifndef XA_CHUNK_SHIFT #define XA_CHUNK_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) #define XA_MAX_MARKS 3 #define XA_MARK_LONGS DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG) /* * @count is the count of every non-NULL element in the ->slots array * whether that is a value entry, a retry entry, a user pointer, * a sibling entry or a pointer to the next level of the tree. * @nr_values is the count of every element in ->slots which is * either a value entry or a sibling of a value entry. */ struct xa_node { unsigned char shift; /* Bits remaining in each slot */ unsigned char offset; /* Slot offset in parent */ unsigned char count; /* Total entry count */ unsigned char nr_values; /* Value entry count */ struct xa_node __rcu *parent; /* NULL at top of tree */ struct xarray *array; /* The array we belong to */ union { struct list_head private_list; /* For tree user */ struct rcu_head rcu_head; /* Used when freeing node */ }; void __rcu *slots[XA_CHUNK_SIZE]; union { unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS]; unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS]; }; }; void xa_dump(const struct xarray *); void xa_dump_node(const struct xa_node *); #ifdef XA_DEBUG #define XA_BUG_ON(xa, x) do { \ if (x) { \ xa_dump(xa); \ BUG(); \ } \ } while (0) #define XA_NODE_BUG_ON(node, x) do { \ if (x) { \ if (node) xa_dump_node(node); \ BUG(); \ } \ } while (0) #else #define XA_BUG_ON(xa, x) do { } while (0) #define XA_NODE_BUG_ON(node, x) do { } while (0) #endif /* Private */ static inline void *xa_head(const struct xarray *xa) { return rcu_dereference_check(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_head_locked(const struct xarray *xa) { return rcu_dereference_protected(xa->xa_head, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_check(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_entry_locked(const struct xarray *xa, const struct xa_node *node, unsigned int offset) { XA_NODE_BUG_ON(node, offset >= XA_CHUNK_SIZE); return rcu_dereference_protected(node->slots[offset], lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_check(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline struct xa_node *xa_parent_locked(const struct xarray *xa, const struct xa_node *node) { return rcu_dereference_protected(node->parent, lockdep_is_held(&xa->xa_lock)); } /* Private */ static inline void *xa_mk_node(const struct xa_node *node) { return (void *)((unsigned long)node | 2); } /* Private */ static inline struct xa_node *xa_to_node(const void *entry) { return (struct xa_node *)((unsigned long)entry - 2); } /* Private */ static inline bool xa_is_node(const void *entry) { return xa_is_internal(entry) && (unsigned long)entry > 4096; } /* Private */ static inline void *xa_mk_sibling(unsigned int offset) { return xa_mk_internal(offset); } /* Private */ static inline unsigned long xa_to_sibling(const void *entry) { return xa_to_internal(entry); } /** * xa_is_sibling() - Is the entry a sibling entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a sibling entry. */ static inline bool xa_is_sibling(const void *entry) { return IS_ENABLED(CONFIG_XARRAY_MULTI) && xa_is_internal(entry) && (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } #define XA_RETRY_ENTRY xa_mk_internal(256) /** * xa_is_retry() - Is the entry a retry entry? * @entry: Entry retrieved from the XArray * * Return: %true if the entry is a retry entry. */ static inline bool xa_is_retry(const void *entry) { return unlikely(entry == XA_RETRY_ENTRY); } /** * xa_is_advanced() - Is the entry only permitted for the advanced API? * @entry: Entry to be stored in the XArray. * * Return: %true if the entry cannot be stored by the normal API. */ static inline bool xa_is_advanced(const void *entry) { return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY); } /** * typedef xa_update_node_t - A callback function from the XArray. * @node: The node which is being processed * * This function is called every time the XArray updates the count of * present and value entries in a node. It allows advanced users to * maintain the private_list in the node. * * Context: The xa_lock is held and interrupts may be disabled. * Implementations should not drop the xa_lock, nor re-enable * interrupts. */ typedef void (*xa_update_node_t)(struct xa_node *node); void xa_delete_node(struct xa_node *, xa_update_node_t); /* * The xa_state is opaque to its users. It contains various different pieces * of state involved in the current operation on the XArray. It should be * declared on the stack and passed between the various internal routines. * The various elements in it should not be accessed directly, but only * through the provided accessor functions. The below documentation is for * the benefit of those working on the code, not for users of the XArray. * * @xa_node usually points to the xa_node containing the slot we're operating * on (and @xa_offset is the offset in the slots array). If there is a * single entry in the array at index 0, there are no allocated xa_nodes to * point to, and so we store %NULL in @xa_node. @xa_node is set to * the value %XAS_RESTART if the xa_state is not walked to the correct * position in the tree of nodes for this operation. If an error occurs * during an operation, it is set to an %XAS_ERROR value. If we run off the * end of the allocated nodes, it is set to %XAS_BOUNDS. */ struct xa_state { struct xarray *xa; unsigned long xa_index; unsigned char xa_shift; unsigned char xa_sibs; unsigned char xa_offset; unsigned char xa_pad; /* Helps gcc generate better code */ struct xa_node *xa_node; struct xa_node *xa_alloc; xa_update_node_t xa_update; }; /* * We encode errnos in the xas->xa_node. If an error has happened, we need to * drop the lock to fix it, and once we've done so the xa_state is invalid. */ #define XA_ERROR(errno) ((struct xa_node *)(((unsigned long)errno << 2) | 2UL)) #define XAS_BOUNDS ((struct xa_node *)1UL) #define XAS_RESTART ((struct xa_node *)3UL) #define __XA_STATE(array, index, shift, sibs) { \ .xa = array, \ .xa_index = index, \ .xa_shift = shift, \ .xa_sibs = sibs, \ .xa_offset = 0, \ .xa_pad = 0, \ .xa_node = XAS_RESTART, \ .xa_alloc = NULL, \ .xa_update = NULL \ } /** * XA_STATE() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * * Declare and initialise an xa_state on the stack. */ #define XA_STATE(name, array, index) \ struct xa_state name = __XA_STATE(array, index, 0, 0) /** * XA_STATE_ORDER() - Declare an XArray operation state. * @name: Name of this operation state (usually xas). * @array: Array to operate on. * @index: Initial index of interest. * @order: Order of entry. * * Declare and initialise an xa_state on the stack. This variant of * XA_STATE() allows you to specify the 'order' of the element you * want to operate on.` */ #define XA_STATE_ORDER(name, array, index, order) \ struct xa_state name = __XA_STATE(array, \ (index >> order) << order, \ order - (order % XA_CHUNK_SHIFT), \ (1U << (order % XA_CHUNK_SHIFT)) - 1) #define xas_marked(xas, mark) xa_marked((xas)->xa, (mark)) #define xas_trylock(xas) xa_trylock((xas)->xa) #define xas_lock(xas) xa_lock((xas)->xa) #define xas_unlock(xas) xa_unlock((xas)->xa) #define xas_lock_bh(xas) xa_lock_bh((xas)->xa) #define xas_unlock_bh(xas) xa_unlock_bh((xas)->xa) #define xas_lock_irq(xas) xa_lock_irq((xas)->xa) #define xas_unlock_irq(xas) xa_unlock_irq((xas)->xa) #define xas_lock_irqsave(xas, flags) \ xa_lock_irqsave((xas)->xa, flags) #define xas_unlock_irqrestore(xas, flags) \ xa_unlock_irqrestore((xas)->xa, flags) /** * xas_error() - Return an errno stored in the xa_state. * @xas: XArray operation state. * * Return: 0 if no error has been noted. A negative errno if one has. */ static inline int xas_error(const struct xa_state *xas) { return xa_err(xas->xa_node); } /** * xas_set_err() - Note an error in the xa_state. * @xas: XArray operation state. * @err: Negative error number. * * Only call this function with a negative @err; zero or positive errors * will probably not behave the way you think they should. If you want * to clear the error from an xa_state, use xas_reset(). */ static inline void xas_set_err(struct xa_state *xas, long err) { xas->xa_node = XA_ERROR(err); } /** * xas_invalid() - Is the xas in a retry or error state? * @xas: XArray operation state. * * Return: %true if the xas cannot be used for operations. */ static inline bool xas_invalid(const struct xa_state *xas) { return (unsigned long)xas->xa_node & 3; } /** * xas_valid() - Is the xas a valid cursor into the array? * @xas: XArray operation state. * * Return: %true if the xas can be used for operations. */ static inline bool xas_valid(const struct xa_state *xas) { return !xas_invalid(xas); } /** * xas_is_node() - Does the xas point to a node? * @xas: XArray operation state. * * Return: %true if the xas currently references a node. */ static inline bool xas_is_node(const struct xa_state *xas) { return xas_valid(xas) && xas->xa_node; } /* True if the pointer is something other than a node */ static inline bool xas_not_node(struct xa_node *node) { return ((unsigned long)node & 3) || !node; } /* True if the node represents RESTART or an error */ static inline bool xas_frozen(struct xa_node *node) { return (unsigned long)node & 2; } /* True if the node represents head-of-tree, RESTART or BOUNDS */ static inline bool xas_top(struct xa_node *node) { return node <= XAS_RESTART; } /** * xas_reset() - Reset an XArray operation state. * @xas: XArray operation state. * * Resets the error or walk state of the @xas so future walks of the * array will start from the root. Use this if you have dropped the * xarray lock and want to reuse the xa_state. * * Context: Any context. */ static inline void xas_reset(struct xa_state *xas) { xas->xa_node = XAS_RESTART; } /** * xas_retry() - Retry the operation if appropriate. * @xas: XArray operation state. * @entry: Entry from xarray. * * The advanced functions may sometimes return an internal entry, such as * a retry entry or a zero entry. This function sets up the @xas to restart * the walk from the head of the array if needed. * * Context: Any context. * Return: true if the operation needs to be retried. */ static inline bool xas_retry(struct xa_state *xas, const void *entry) { if (xa_is_zero(entry)) return true; if (!xa_is_retry(entry)) return false; xas_reset(xas); return true; } void *xas_load(struct xa_state *); void *xas_store(struct xa_state *, void *entry); void *xas_find(struct xa_state *, unsigned long max); void *xas_find_conflict(struct xa_state *); bool xas_get_mark(const struct xa_state *, xa_mark_t); void xas_set_mark(const struct xa_state *, xa_mark_t); void xas_clear_mark(const struct xa_state *, xa_mark_t); void *xas_find_marked(struct xa_state *, unsigned long max, xa_mark_t); void xas_init_marks(const struct xa_state *); bool xas_nomem(struct xa_state *, gfp_t); void xas_pause(struct xa_state *); void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); #else static inline int xa_get_order(struct xarray *xa, unsigned long index) { return 0; } static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { xas_store(xas, entry); } static inline void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { } #endif /** * xas_reload() - Refetch an entry from the xarray. * @xas: XArray operation state. * * Use this function to check that a previously loaded entry still has * the same value. This is useful for the lockless pagecache lookup where * we walk the array with only the RCU lock to protect us, lock the page, * then check that the page hasn't moved since we looked it up. * * The caller guarantees that @xas is still valid. If it may be in an * error or restart state, call xas_load() instead. * * Return: The entry at this location in the xarray. */ static inline void *xas_reload(struct xa_state *xas) { struct xa_node *node = xas->xa_node; void *entry; char offset; if (!node) return xa_head(xas->xa); if (IS_ENABLED(CONFIG_XARRAY_MULTI)) { offset = (xas->xa_index >> node->shift) & XA_CHUNK_MASK; entry = xa_entry(xas->xa, node, offset); if (!xa_is_sibling(entry)) return entry; offset = xa_to_sibling(entry); } else { offset = xas->xa_offset; } return xa_entry(xas->xa, node, offset); } /** * xas_set() - Set up XArray operation state for a different index. * @xas: XArray operation state. * @index: New index into the XArray. * * Move the operation state to refer to a different index. This will * have the effect of starting a walk from the top; see xas_next() * to move to an adjacent index. */ static inline void xas_set(struct xa_state *xas, unsigned long index) { xas->xa_index = index; xas->xa_node = XAS_RESTART; } /** * xas_set_order() - Set up XArray operation state for a multislot entry. * @xas: XArray operation state. * @index: Target of the operation. * @order: Entry occupies 2^@order indices. */ static inline void xas_set_order(struct xa_state *xas, unsigned long index, unsigned int order) { #ifdef CONFIG_XARRAY_MULTI xas->xa_index = order < BITS_PER_LONG ? (index >> order) << order : 0; xas->xa_shift = order - (order % XA_CHUNK_SHIFT); xas->xa_sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; xas->xa_node = XAS_RESTART; #else BUG_ON(order > 0); xas_set(xas, index); #endif } /** * xas_set_update() - Set up XArray operation state for a callback. * @xas: XArray operation state. * @update: Function to call when updating a node. * * The XArray can notify a caller after it has updated an xa_node. * This is advanced functionality and is only needed by the page cache. */ static inline void xas_set_update(struct xa_state *xas, xa_update_node_t update) { xas->xa_update = update; } /** * xas_next_entry() - Advance iterator to next present entry. * @xas: XArray operation state. * @max: Highest index to return. * * xas_next_entry() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find(), and will call xas_find() * for all the hard cases. * * Return: The next present entry after the one currently referred to by @xas. */ static inline void *xas_next_entry(struct xa_state *xas, unsigned long max) { struct xa_node *node = xas->xa_node; void *entry; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK))) return xas_find(xas, max); do { if (unlikely(xas->xa_index >= max)) return xas_find(xas, max); if (unlikely(xas->xa_offset == XA_CHUNK_MASK)) return xas_find(xas, max); entry = xa_entry(xas->xa, node, xas->xa_offset + 1); if (unlikely(xa_is_internal(entry))) return xas_find(xas, max); xas->xa_offset++; xas->xa_index++; } while (!entry); return entry; } /* Private */ static inline unsigned int xas_find_chunk(struct xa_state *xas, bool advance, xa_mark_t mark) { unsigned long *addr = xas->xa_node->marks[(__force unsigned)mark]; unsigned int offset = xas->xa_offset; if (advance) offset++; if (XA_CHUNK_SIZE == BITS_PER_LONG) { if (offset < XA_CHUNK_SIZE) { unsigned long data = *addr & (~0UL << offset); if (data) return __ffs(data); } return XA_CHUNK_SIZE; } return find_next_bit(addr, XA_CHUNK_SIZE, offset); } /** * xas_next_marked() - Advance iterator to next marked entry. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark to search for. * * xas_next_marked() is an inline function to optimise xarray traversal for * speed. It is equivalent to calling xas_find_marked(), and will call * xas_find_marked() for all the hard cases. * * Return: The next marked entry after the one currently referred to by @xas. */ static inline void *xas_next_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { struct xa_node *node = xas->xa_node; void *entry; unsigned int offset; if (unlikely(xas_not_node(node) || node->shift)) return xas_find_marked(xas, max, mark); offset = xas_find_chunk(xas, true, mark); xas->xa_offset = offset; xas->xa_index = (xas->xa_index & ~XA_CHUNK_MASK) + offset; if (xas->xa_index > max) return NULL; if (offset == XA_CHUNK_SIZE) return xas_find_marked(xas, max, mark); entry = xa_entry(xas->xa, node, offset); if (!entry) return xas_find_marked(xas, max, mark); return entry; } /* * If iterating while holding a lock, drop the lock and reschedule * every %XA_CHECK_SCHED loops. */ enum { XA_CHECK_SCHED = 4096, }; /** * xas_for_each() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * * The loop body will be executed for each entry present in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each(xas, entry, max) \ for (entry = xas_find(xas, max); entry; \ entry = xas_next_entry(xas, max)) /** * xas_for_each_marked() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * @max: Maximum index to retrieve from array. * @mark: Mark to search for. * * The loop body will be executed for each marked entry in the xarray * between the current xas position and @max. @entry will be set to * the entry retrieved from the xarray. It is safe to delete entries * from the array in the loop body. You should hold either the RCU lock * or the xa_lock while iterating. If you need to drop the lock, call * xas_pause() first. */ #define xas_for_each_marked(xas, entry, max, mark) \ for (entry = xas_find_marked(xas, max, mark); entry; \ entry = xas_next_marked(xas, max, mark)) /** * xas_for_each_conflict() - Iterate over a range of an XArray. * @xas: XArray operation state. * @entry: Entry retrieved from the array. * * The loop body will be executed for each entry in the XArray that * lies within the range specified by @xas. If the loop terminates * normally, @entry will be %NULL. The user may break out of the loop, * which will leave @entry set to the conflicting entry. The caller * may also call xa_set_err() to exit the loop while setting an error * to record the reason. */ #define xas_for_each_conflict(xas, entry) \ while ((entry = xas_find_conflict(xas))) void *__xas_next(struct xa_state *); void *__xas_prev(struct xa_state *); /** * xas_prev() - Move iterator to previous index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * subtracted from the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index 0, this function wraps * around to %ULONG_MAX. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_prev(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == 0)) return __xas_prev(xas); xas->xa_index--; xas->xa_offset--; return xa_entry(xas->xa, node, xas->xa_offset); } /** * xas_next() - Move state to next index. * @xas: XArray operation state. * * If the @xas was in an error state, it will remain in an error state * and this function will return %NULL. If the @xas has never been walked, * it will have the effect of calling xas_load(). Otherwise one will be * added to the index and the state will be walked to the correct * location in the array for the next operation. * * If the iterator was referencing index %ULONG_MAX, this function wraps * around to 0. * * Return: The entry at the new index. This may be %NULL or an internal * entry. */ static inline void *xas_next(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (unlikely(xas_not_node(node) || node->shift || xas->xa_offset == XA_CHUNK_MASK)) return __xas_next(xas); xas->xa_index++; xas->xa_offset++; return xa_entry(xas->xa, node, xas->xa_offset); } #endif /* _LINUX_XARRAY_H */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 | /* SPDX-License-Identifier: GPL-2.0 */ /* * A hash table (hashtab) maintains associations between * key values and datum values. The type of the key values * and the type of the datum values is arbitrary. The * functions for hash computation and key comparison are * provided by the creator of the table. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ #ifndef _SS_HASHTAB_H_ #define _SS_HASHTAB_H_ #include <linux/types.h> #include <linux/errno.h> #include <linux/sched.h> #define HASHTAB_MAX_NODES U32_MAX struct hashtab_key_params { u32 (*hash)(const void *key); /* hash function */ int (*cmp)(const void *key1, const void *key2); /* key comparison function */ }; struct hashtab_node { void *key; void *datum; struct hashtab_node *next; }; struct hashtab { struct hashtab_node **htable; /* hash table */ u32 size; /* number of slots in hash table */ u32 nel; /* number of elements in hash table */ }; struct hashtab_info { u32 slots_used; u32 max_chain_len; }; /* * Initializes a new hash table with the specified characteristics. * * Returns -ENOMEM if insufficient space is available or 0 otherwise. */ int hashtab_init(struct hashtab *h, u32 nel_hint); int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst, void *key, void *datum); /* * Inserts the specified (key, datum) pair into the specified hash table. * * Returns -ENOMEM on memory allocation error, * -EEXIST if there is already an entry with the same key, * -EINVAL for general errors or 0 otherwise. */ static inline int hashtab_insert(struct hashtab *h, void *key, void *datum, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *prev, *cur; cond_resched(); if (!h->size || h->nel == HASHTAB_MAX_NODES) return -EINVAL; hvalue = key_params.hash(key) & (h->size - 1); prev = NULL; cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return -EEXIST; if (cmp < 0) break; prev = cur; cur = cur->next; } return __hashtab_insert(h, prev ? &prev->next : &h->htable[hvalue], key, datum); } /* * Searches for the entry with the specified key in the hash table. * * Returns NULL if no entry has the specified key or * the datum of the entry otherwise. */ static inline void *hashtab_search(struct hashtab *h, const void *key, struct hashtab_key_params key_params) { u32 hvalue; struct hashtab_node *cur; if (!h->size) return NULL; hvalue = key_params.hash(key) & (h->size - 1); cur = h->htable[hvalue]; while (cur) { int cmp = key_params.cmp(key, cur->key); if (cmp == 0) return cur->datum; if (cmp < 0) break; cur = cur->next; } return NULL; } /* * Destroys the specified hash table. */ void hashtab_destroy(struct hashtab *h); /* * Applies the specified apply function to (key,datum,args) * for each entry in the specified hash table. * * The order in which the function is applied to the entries * is dependent upon the internal structure of the hash table. * * If apply returns a non-zero status, then hashtab_map will cease * iterating through the hash table and will propagate the error * return to its caller. */ int hashtab_map(struct hashtab *h, int (*apply)(void *k, void *d, void *args), void *args); int hashtab_duplicate(struct hashtab *new, struct hashtab *orig, int (*copy)(struct hashtab_node *new, struct hashtab_node *orig, void *args), int (*destroy)(void *k, void *d, void *args), void *args); /* Fill info with some hash table statistics */ void hashtab_stat(struct hashtab *h, struct hashtab_info *info); #endif /* _SS_HASHTAB_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 | #ifdef CONFIG_PREEMPTIRQ_TRACEPOINTS #undef TRACE_SYSTEM #define TRACE_SYSTEM preemptirq #if !defined(_TRACE_PREEMPTIRQ_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PREEMPTIRQ_H #include <linux/ktime.h> #include <linux/tracepoint.h> #include <linux/string.h> #include <asm/sections.h> DECLARE_EVENT_CLASS(preemptirq_template, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip), TP_STRUCT__entry( __field(s32, caller_offs) __field(s32, parent_offs) ), TP_fast_assign( __entry->caller_offs = (s32)(ip - (unsigned long)_stext); __entry->parent_offs = (s32)(parent_ip - (unsigned long)_stext); ), TP_printk("caller=%pS parent=%pS", (void *)((unsigned long)(_stext) + __entry->caller_offs), (void *)((unsigned long)(_stext) + __entry->parent_offs)) ); #ifdef CONFIG_TRACE_IRQFLAGS DEFINE_EVENT(preemptirq_template, irq_disable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); DEFINE_EVENT(preemptirq_template, irq_enable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); #else #define trace_irq_enable(...) #define trace_irq_disable(...) #define trace_irq_enable_rcuidle(...) #define trace_irq_disable_rcuidle(...) #endif #ifdef CONFIG_TRACE_PREEMPT_TOGGLE DEFINE_EVENT(preemptirq_template, preempt_disable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); DEFINE_EVENT(preemptirq_template, preempt_enable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); #else #define trace_preempt_enable(...) #define trace_preempt_disable(...) #define trace_preempt_enable_rcuidle(...) #define trace_preempt_disable_rcuidle(...) #endif #endif /* _TRACE_PREEMPTIRQ_H */ #include <trace/define_trace.h> #else /* !CONFIG_PREEMPTIRQ_TRACEPOINTS */ #define trace_irq_enable(...) #define trace_irq_disable(...) #define trace_irq_enable_rcuidle(...) #define trace_irq_disable_rcuidle(...) #define trace_preempt_enable(...) #define trace_preempt_disable(...) #define trace_preempt_enable_rcuidle(...) #define trace_preempt_disable_rcuidle(...) #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Kernel Probes (KProbes) * kernel/kprobes.c * * Copyright (C) IBM Corporation, 2002, 2004 * * 2002-Oct Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel * Probes initial implementation (includes suggestions from * Rusty Russell). * 2004-Aug Updated by Prasanna S Panchamukhi <prasanna@in.ibm.com> with * hlists and exceptions notifier as suggested by Andi Kleen. * 2004-July Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes * interface to access function arguments. * 2004-Sep Prasanna S Panchamukhi <prasanna@in.ibm.com> Changed Kprobes * exceptions notifier to be first on the priority list. * 2005-May Hien Nguyen <hien@us.ibm.com>, Jim Keniston * <jkenisto@us.ibm.com> and Prasanna S Panchamukhi * <prasanna@in.ibm.com> added function-return probes. */ #include <linux/kprobes.h> #include <linux/hash.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/stddef.h> #include <linux/export.h> #include <linux/moduleloader.h> #include <linux/kallsyms.h> #include <linux/freezer.h> #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/sysctl.h> #include <linux/kdebug.h> #include <linux/memory.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/jump_label.h> #include <linux/perf_event.h> #include <linux/static_call.h> #include <asm/sections.h> #include <asm/cacheflush.h> #include <asm/errno.h> #include <linux/uaccess.h> #define KPROBE_HASH_BITS 6 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS) static int kprobes_initialized; /* kprobe_table can be accessed by * - Normal hlist traversal and RCU add/del under kprobe_mutex is held. * Or * - RCU hlist traversal under disabling preempt (breakpoint handlers) */ static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE]; static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE]; /* NOTE: change this value only with kprobe_mutex held */ static bool kprobes_all_disarmed; /* This protects kprobe_table and optimizing_list */ static DEFINE_MUTEX(kprobe_mutex); static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; static struct { raw_spinlock_t lock ____cacheline_aligned_in_smp; } kretprobe_table_locks[KPROBE_TABLE_SIZE]; kprobe_opcode_t * __weak kprobe_lookup_name(const char *name, unsigned int __unused) { return ((kprobe_opcode_t *)(kallsyms_lookup_name(name))); } static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash) { return &(kretprobe_table_locks[hash].lock); } /* Blacklist -- list of struct kprobe_blacklist_entry */ static LIST_HEAD(kprobe_blacklist); #ifdef __ARCH_WANT_KPROBES_INSN_SLOT /* * kprobe->ainsn.insn points to the copy of the instruction to be * single-stepped. x86_64, POWER4 and above have no-exec support and * stepping on the instruction on a vmalloced/kmalloced/data page * is a recipe for disaster */ struct kprobe_insn_page { struct list_head list; kprobe_opcode_t *insns; /* Page of instruction slots */ struct kprobe_insn_cache *cache; int nused; int ngarbage; char slot_used[]; }; #define KPROBE_INSN_PAGE_SIZE(slots) \ (offsetof(struct kprobe_insn_page, slot_used) + \ (sizeof(char) * (slots))) static int slots_per_page(struct kprobe_insn_cache *c) { return PAGE_SIZE/(c->insn_size * sizeof(kprobe_opcode_t)); } enum kprobe_slot_state { SLOT_CLEAN = 0, SLOT_DIRTY = 1, SLOT_USED = 2, }; void __weak *alloc_insn_page(void) { return module_alloc(PAGE_SIZE); } void __weak free_insn_page(void *page) { module_memfree(page); } struct kprobe_insn_cache kprobe_insn_slots = { .mutex = __MUTEX_INITIALIZER(kprobe_insn_slots.mutex), .alloc = alloc_insn_page, .free = free_insn_page, .sym = KPROBE_INSN_PAGE_SYM, .pages = LIST_HEAD_INIT(kprobe_insn_slots.pages), .insn_size = MAX_INSN_SIZE, .nr_garbage = 0, }; static int collect_garbage_slots(struct kprobe_insn_cache *c); /** * __get_insn_slot() - Find a slot on an executable page for an instruction. * We allocate an executable page if there's no room on existing ones. */ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip; kprobe_opcode_t *slot = NULL; /* Since the slot array is not protected by rcu, we need a mutex */ mutex_lock(&c->mutex); retry: rcu_read_lock(); list_for_each_entry_rcu(kip, &c->pages, list) { if (kip->nused < slots_per_page(c)) { int i; for (i = 0; i < slots_per_page(c); i++) { if (kip->slot_used[i] == SLOT_CLEAN) { kip->slot_used[i] = SLOT_USED; kip->nused++; slot = kip->insns + (i * c->insn_size); rcu_read_unlock(); goto out; } } /* kip->nused is broken. Fix it. */ kip->nused = slots_per_page(c); WARN_ON(1); } } rcu_read_unlock(); /* If there are any garbage slots, collect it and try again. */ if (c->nr_garbage && collect_garbage_slots(c) == 0) goto retry; /* All out of space. Need to allocate a new page. */ kip = kmalloc(KPROBE_INSN_PAGE_SIZE(slots_per_page(c)), GFP_KERNEL); if (!kip) goto out; /* * Use module_alloc so this page is within +/- 2GB of where the * kernel image and loaded module images reside. This is required * so x86_64 can correctly handle the %rip-relative fixups. */ kip->insns = c->alloc(); if (!kip->insns) { kfree(kip); goto out; } INIT_LIST_HEAD(&kip->list); memset(kip->slot_used, SLOT_CLEAN, slots_per_page(c)); kip->slot_used[0] = SLOT_USED; kip->nused = 1; kip->ngarbage = 0; kip->cache = c; list_add_rcu(&kip->list, &c->pages); slot = kip->insns; /* Record the perf ksymbol register event after adding the page */ perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns, PAGE_SIZE, false, c->sym); out: mutex_unlock(&c->mutex); return slot; } /* Return 1 if all garbages are collected, otherwise 0. */ static int collect_one_slot(struct kprobe_insn_page *kip, int idx) { kip->slot_used[idx] = SLOT_CLEAN; kip->nused--; if (kip->nused == 0) { /* * Page is no longer in use. Free it unless * it's the last one. We keep the last one * so as not to have to set it up again the * next time somebody inserts a probe. */ if (!list_is_singular(&kip->list)) { /* * Record perf ksymbol unregister event before removing * the page. */ perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_OOL, (unsigned long)kip->insns, PAGE_SIZE, true, kip->cache->sym); list_del_rcu(&kip->list); synchronize_rcu(); kip->cache->free(kip->insns); kfree(kip); } return 1; } return 0; } static int collect_garbage_slots(struct kprobe_insn_cache *c) { struct kprobe_insn_page *kip, *next; /* Ensure no-one is interrupted on the garbages */ synchronize_rcu(); list_for_each_entry_safe(kip, next, &c->pages, list) { int i; if (kip->ngarbage == 0) continue; kip->ngarbage = 0; /* we will collect all garbages */ for (i = 0; i < slots_per_page(c); i++) { if (kip->slot_used[i] == SLOT_DIRTY && collect_one_slot(kip, i)) break; } } c->nr_garbage = 0; return 0; } void __free_insn_slot(struct kprobe_insn_cache *c, kprobe_opcode_t *slot, int dirty) { struct kprobe_insn_page *kip; long idx; mutex_lock(&c->mutex); rcu_read_lock(); list_for_each_entry_rcu(kip, &c->pages, list) { idx = ((long)slot - (long)kip->insns) / (c->insn_size * sizeof(kprobe_opcode_t)); if (idx >= 0 && idx < slots_per_page(c)) goto out; } /* Could not find this slot. */ WARN_ON(1); kip = NULL; out: rcu_read_unlock(); /* Mark and sweep: this may sleep */ if (kip) { /* Check double free */ WARN_ON(kip->slot_used[idx] != SLOT_USED); if (dirty) { kip->slot_used[idx] = SLOT_DIRTY; kip->ngarbage++; if (++c->nr_garbage > slots_per_page(c)) collect_garbage_slots(c); } else { collect_one_slot(kip, idx); } } mutex_unlock(&c->mutex); } /* * Check given address is on the page of kprobe instruction slots. * This will be used for checking whether the address on a stack * is on a text area or not. */ bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr) { struct kprobe_insn_page *kip; bool ret = false; rcu_read_lock(); list_for_each_entry_rcu(kip, &c->pages, list) { if (addr >= (unsigned long)kip->insns && addr < (unsigned long)kip->insns + PAGE_SIZE) { ret = true; break; } } rcu_read_unlock(); return ret; } int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum, unsigned long *value, char *type, char *sym) { struct kprobe_insn_page *kip; int ret = -ERANGE; rcu_read_lock(); list_for_each_entry_rcu(kip, &c->pages, list) { if ((*symnum)--) continue; strlcpy(sym, c->sym, KSYM_NAME_LEN); *type = 't'; *value = (unsigned long)kip->insns; ret = 0; break; } rcu_read_unlock(); return ret; } #ifdef CONFIG_OPTPROBES /* For optimized_kprobe buffer */ struct kprobe_insn_cache kprobe_optinsn_slots = { .mutex = __MUTEX_INITIALIZER(kprobe_optinsn_slots.mutex), .alloc = alloc_insn_page, .free = free_insn_page, .sym = KPROBE_OPTINSN_PAGE_SYM, .pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages), /* .insn_size is initialized later */ .nr_garbage = 0, }; #endif #endif /* We have preemption disabled.. so it is safe to use __ versions */ static inline void set_kprobe_instance(struct kprobe *kp) { __this_cpu_write(kprobe_instance, kp); } static inline void reset_kprobe_instance(void) { __this_cpu_write(kprobe_instance, NULL); } /* * This routine is called either: * - under the kprobe_mutex - during kprobe_[un]register() * OR * - with preemption disabled - from arch/xxx/kernel/kprobes.c */ struct kprobe *get_kprobe(void *addr) { struct hlist_head *head; struct kprobe *p; head = &kprobe_table[hash_ptr(addr, KPROBE_HASH_BITS)]; hlist_for_each_entry_rcu(p, head, hlist, lockdep_is_held(&kprobe_mutex)) { if (p->addr == addr) return p; } return NULL; } NOKPROBE_SYMBOL(get_kprobe); static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs); /* Return true if the kprobe is an aggregator */ static inline int kprobe_aggrprobe(struct kprobe *p) { return p->pre_handler == aggr_pre_handler; } /* Return true(!0) if the kprobe is unused */ static inline int kprobe_unused(struct kprobe *p) { return kprobe_aggrprobe(p) && kprobe_disabled(p) && list_empty(&p->list); } /* * Keep all fields in the kprobe consistent */ static inline void copy_kprobe(struct kprobe *ap, struct kprobe *p) { memcpy(&p->opcode, &ap->opcode, sizeof(kprobe_opcode_t)); memcpy(&p->ainsn, &ap->ainsn, sizeof(struct arch_specific_insn)); } #ifdef CONFIG_OPTPROBES /* NOTE: change this value only with kprobe_mutex held */ static bool kprobes_allow_optimization; /* * Call all pre_handler on the list, but ignores its return value. * This must be called from arch-dep optimized caller. */ void opt_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { if (kp->pre_handler && likely(!kprobe_disabled(kp))) { set_kprobe_instance(kp); kp->pre_handler(kp, regs); } reset_kprobe_instance(); } } NOKPROBE_SYMBOL(opt_pre_handler); /* Free optimized instructions and optimized_kprobe */ static void free_aggr_kprobe(struct kprobe *p) { struct optimized_kprobe *op; op = container_of(p, struct optimized_kprobe, kp); arch_remove_optimized_kprobe(op); arch_remove_kprobe(p); kfree(op); } /* Return true(!0) if the kprobe is ready for optimization. */ static inline int kprobe_optready(struct kprobe *p) { struct optimized_kprobe *op; if (kprobe_aggrprobe(p)) { op = container_of(p, struct optimized_kprobe, kp); return arch_prepared_optinsn(&op->optinsn); } return 0; } /* Return true if the kprobe is disarmed. Note: p must be on hash list */ bool kprobe_disarmed(struct kprobe *p) { struct optimized_kprobe *op; /* If kprobe is not aggr/opt probe, just return kprobe is disabled */ if (!kprobe_aggrprobe(p)) return kprobe_disabled(p); op = container_of(p, struct optimized_kprobe, kp); return kprobe_disabled(p) && list_empty(&op->list); } /* Return true(!0) if the probe is queued on (un)optimizing lists */ static int kprobe_queued(struct kprobe *p) { struct optimized_kprobe *op; if (kprobe_aggrprobe(p)) { op = container_of(p, struct optimized_kprobe, kp); if (!list_empty(&op->list)) return 1; } return 0; } /* * Return an optimized kprobe whose optimizing code replaces * instructions including addr (exclude breakpoint). */ static struct kprobe *get_optimized_kprobe(unsigned long addr) { int i; struct kprobe *p = NULL; struct optimized_kprobe *op; /* Don't check i == 0, since that is a breakpoint case. */ for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH; i++) p = get_kprobe((void *)(addr - i)); if (p && kprobe_optready(p)) { op = container_of(p, struct optimized_kprobe, kp); if (arch_within_optimized_kprobe(op, addr)) return p; } return NULL; } /* Optimization staging list, protected by kprobe_mutex */ static LIST_HEAD(optimizing_list); static LIST_HEAD(unoptimizing_list); static LIST_HEAD(freeing_list); static void kprobe_optimizer(struct work_struct *work); static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); #define OPTIMIZE_DELAY 5 /* * Optimize (replace a breakpoint with a jump) kprobes listed on * optimizing_list. */ static void do_optimize_kprobes(void) { lockdep_assert_held(&text_mutex); /* * The optimization/unoptimization refers online_cpus via * stop_machine() and cpu-hotplug modifies online_cpus. * And same time, text_mutex will be held in cpu-hotplug and here. * This combination can cause a deadlock (cpu-hotplug try to lock * text_mutex but stop_machine can not be done because online_cpus * has been changed) * To avoid this deadlock, caller must have locked cpu hotplug * for preventing cpu-hotplug outside of text_mutex locking. */ lockdep_assert_cpus_held(); /* Optimization never be done when disarmed */ if (kprobes_all_disarmed || !kprobes_allow_optimization || list_empty(&optimizing_list)) return; arch_optimize_kprobes(&optimizing_list); } /* * Unoptimize (replace a jump with a breakpoint and remove the breakpoint * if need) kprobes listed on unoptimizing_list. */ static void do_unoptimize_kprobes(void) { struct optimized_kprobe *op, *tmp; lockdep_assert_held(&text_mutex); /* See comment in do_optimize_kprobes() */ lockdep_assert_cpus_held(); if (!list_empty(&unoptimizing_list)) arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); /* Loop on 'freeing_list' for disarming and removing from kprobe hash list */ list_for_each_entry_safe(op, tmp, &freeing_list, list) { /* Switching from detour code to origin */ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; /* Disarm probes if marked disabled and not gone */ if (kprobe_disabled(&op->kp) && !kprobe_gone(&op->kp)) arch_disarm_kprobe(&op->kp); if (kprobe_unused(&op->kp)) { /* * Remove unused probes from hash list. After waiting * for synchronization, these probes are reclaimed. * (reclaiming is done by do_free_cleaned_kprobes.) */ hlist_del_rcu(&op->kp.hlist); } else list_del_init(&op->list); } } /* Reclaim all kprobes on the free_list */ static void do_free_cleaned_kprobes(void) { struct optimized_kprobe *op, *tmp; list_for_each_entry_safe(op, tmp, &freeing_list, list) { list_del_init(&op->list); if (WARN_ON_ONCE(!kprobe_unused(&op->kp))) { /* * This must not happen, but if there is a kprobe * still in use, keep it on kprobes hash list. */ continue; } free_aggr_kprobe(&op->kp); } } /* Start optimizer after OPTIMIZE_DELAY passed */ static void kick_kprobe_optimizer(void) { schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY); } /* Kprobe jump optimizer */ static void kprobe_optimizer(struct work_struct *work) { mutex_lock(&kprobe_mutex); cpus_read_lock(); mutex_lock(&text_mutex); /* * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed) * kprobes before waiting for quiesence period. */ do_unoptimize_kprobes(); /* * Step 2: Wait for quiesence period to ensure all potentially * preempted tasks to have normally scheduled. Because optprobe * may modify multiple instructions, there is a chance that Nth * instruction is preempted. In that case, such tasks can return * to 2nd-Nth byte of jump instruction. This wait is for avoiding it. * Note that on non-preemptive kernel, this is transparently converted * to synchronoze_sched() to wait for all interrupts to have completed. */ synchronize_rcu_tasks(); /* Step 3: Optimize kprobes after quiesence period */ do_optimize_kprobes(); /* Step 4: Free cleaned kprobes after quiesence period */ do_free_cleaned_kprobes(); mutex_unlock(&text_mutex); cpus_read_unlock(); /* Step 5: Kick optimizer again if needed */ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) kick_kprobe_optimizer(); mutex_unlock(&kprobe_mutex); } /* Wait for completing optimization and unoptimization */ void wait_for_kprobe_optimizer(void) { mutex_lock(&kprobe_mutex); while (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) { mutex_unlock(&kprobe_mutex); /* this will also make optimizing_work execute immmediately */ flush_delayed_work(&optimizing_work); /* @optimizing_work might not have been queued yet, relax */ cpu_relax(); mutex_lock(&kprobe_mutex); } mutex_unlock(&kprobe_mutex); } bool optprobe_queued_unopt(struct optimized_kprobe *op) { struct optimized_kprobe *_op; list_for_each_entry(_op, &unoptimizing_list, list) { if (op == _op) return true; } return false; } /* Optimize kprobe if p is ready to be optimized */ static void optimize_kprobe(struct kprobe *p) { struct optimized_kprobe *op; /* Check if the kprobe is disabled or not ready for optimization. */ if (!kprobe_optready(p) || !kprobes_allow_optimization || (kprobe_disabled(p) || kprobes_all_disarmed)) return; /* kprobes with post_handler can not be optimized */ if (p->post_handler) return; op = container_of(p, struct optimized_kprobe, kp); /* Check there is no other kprobes at the optimized instructions */ if (arch_check_optimized_kprobe(op) < 0) return; /* Check if it is already optimized. */ if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) { if (optprobe_queued_unopt(op)) { /* This is under unoptimizing. Just dequeue the probe */ list_del_init(&op->list); } return; } op->kp.flags |= KPROBE_FLAG_OPTIMIZED; /* On unoptimizing/optimizing_list, op must have OPTIMIZED flag */ if (WARN_ON_ONCE(!list_empty(&op->list))) return; list_add(&op->list, &optimizing_list); kick_kprobe_optimizer(); } /* Short cut to direct unoptimizing */ static void force_unoptimize_kprobe(struct optimized_kprobe *op) { lockdep_assert_cpus_held(); arch_unoptimize_kprobe(op); op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; } /* Unoptimize a kprobe if p is optimized */ static void unoptimize_kprobe(struct kprobe *p, bool force) { struct optimized_kprobe *op; if (!kprobe_aggrprobe(p) || kprobe_disarmed(p)) return; /* This is not an optprobe nor optimized */ op = container_of(p, struct optimized_kprobe, kp); if (!kprobe_optimized(p)) return; if (!list_empty(&op->list)) { if (optprobe_queued_unopt(op)) { /* Queued in unoptimizing queue */ if (force) { /* * Forcibly unoptimize the kprobe here, and queue it * in the freeing list for release afterwards. */ force_unoptimize_kprobe(op); list_move(&op->list, &freeing_list); } } else { /* Dequeue from the optimizing queue */ list_del_init(&op->list); op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; } return; } /* Optimized kprobe case */ if (force) { /* Forcibly update the code: this is a special case */ force_unoptimize_kprobe(op); } else { list_add(&op->list, &unoptimizing_list); kick_kprobe_optimizer(); } } /* Cancel unoptimizing for reusing */ static int reuse_unused_kprobe(struct kprobe *ap) { struct optimized_kprobe *op; /* * Unused kprobe MUST be on the way of delayed unoptimizing (means * there is still a relative jump) and disabled. */ op = container_of(ap, struct optimized_kprobe, kp); WARN_ON_ONCE(list_empty(&op->list)); /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ if (!kprobe_optready(ap)) return -EINVAL; optimize_kprobe(ap); return 0; } /* Remove optimized instructions */ static void kill_optimized_kprobe(struct kprobe *p) { struct optimized_kprobe *op; op = container_of(p, struct optimized_kprobe, kp); if (!list_empty(&op->list)) /* Dequeue from the (un)optimization queue */ list_del_init(&op->list); op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (kprobe_unused(p)) { /* * Unused kprobe is on unoptimizing or freeing list. We move it * to freeing_list and let the kprobe_optimizer() remove it from * the kprobe hash list and free it. */ if (optprobe_queued_unopt(op)) list_move(&op->list, &freeing_list); } /* Don't touch the code, because it is already freed. */ arch_remove_optimized_kprobe(op); } static inline void __prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *p) { if (!kprobe_ftrace(p)) arch_prepare_optimized_kprobe(op, p); } /* Try to prepare optimized instructions */ static void prepare_optimized_kprobe(struct kprobe *p) { struct optimized_kprobe *op; op = container_of(p, struct optimized_kprobe, kp); __prepare_optimized_kprobe(op, p); } /* Allocate new optimized_kprobe and try to prepare optimized instructions */ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) { struct optimized_kprobe *op; op = kzalloc(sizeof(struct optimized_kprobe), GFP_KERNEL); if (!op) return NULL; INIT_LIST_HEAD(&op->list); op->kp.addr = p->addr; __prepare_optimized_kprobe(op, p); return &op->kp; } static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p); /* * Prepare an optimized_kprobe and optimize it * NOTE: p must be a normal registered kprobe */ static void try_to_optimize_kprobe(struct kprobe *p) { struct kprobe *ap; struct optimized_kprobe *op; /* Impossible to optimize ftrace-based kprobe */ if (kprobe_ftrace(p)) return; /* For preparing optimization, jump_label_text_reserved() is called */ cpus_read_lock(); jump_label_lock(); mutex_lock(&text_mutex); ap = alloc_aggr_kprobe(p); if (!ap) goto out; op = container_of(ap, struct optimized_kprobe, kp); if (!arch_prepared_optinsn(&op->optinsn)) { /* If failed to setup optimizing, fallback to kprobe */ arch_remove_optimized_kprobe(op); kfree(op); goto out; } init_aggr_kprobe(ap, p); optimize_kprobe(ap); /* This just kicks optimizer thread */ out: mutex_unlock(&text_mutex); jump_label_unlock(); cpus_read_unlock(); } static void optimize_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i; mutex_lock(&kprobe_mutex); /* If optimization is already allowed, just return */ if (kprobes_allow_optimization) goto out; cpus_read_lock(); kprobes_allow_optimization = true; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) if (!kprobe_disabled(p)) optimize_kprobe(p); } cpus_read_unlock(); printk(KERN_INFO "Kprobes globally optimized\n"); out: mutex_unlock(&kprobe_mutex); } #ifdef CONFIG_SYSCTL static void unoptimize_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i; mutex_lock(&kprobe_mutex); /* If optimization is already prohibited, just return */ if (!kprobes_allow_optimization) { mutex_unlock(&kprobe_mutex); return; } cpus_read_lock(); kprobes_allow_optimization = false; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) { if (!kprobe_disabled(p)) unoptimize_kprobe(p, false); } } cpus_read_unlock(); mutex_unlock(&kprobe_mutex); /* Wait for unoptimizing completion */ wait_for_kprobe_optimizer(); printk(KERN_INFO "Kprobes globally unoptimized\n"); } static DEFINE_MUTEX(kprobe_sysctl_mutex); int sysctl_kprobes_optimization; int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { int ret; mutex_lock(&kprobe_sysctl_mutex); sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); if (sysctl_kprobes_optimization) optimize_all_kprobes(); else unoptimize_all_kprobes(); mutex_unlock(&kprobe_sysctl_mutex); return ret; } #endif /* CONFIG_SYSCTL */ /* Put a breakpoint for a probe. Must be called with text_mutex locked */ static void __arm_kprobe(struct kprobe *p) { struct kprobe *_p; /* Check collision with other optimized kprobes */ _p = get_optimized_kprobe((unsigned long)p->addr); if (unlikely(_p)) /* Fallback to unoptimized kprobe */ unoptimize_kprobe(_p, true); arch_arm_kprobe(p); optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */ } /* Remove the breakpoint of a probe. Must be called with text_mutex locked */ static void __disarm_kprobe(struct kprobe *p, bool reopt) { struct kprobe *_p; /* Try to unoptimize */ unoptimize_kprobe(p, kprobes_all_disarmed); if (!kprobe_queued(p)) { arch_disarm_kprobe(p); /* If another kprobe was blocked, optimize it. */ _p = get_optimized_kprobe((unsigned long)p->addr); if (unlikely(_p) && reopt) optimize_kprobe(_p); } /* TODO: reoptimize others after unoptimized this probe */ } #else /* !CONFIG_OPTPROBES */ #define optimize_kprobe(p) do {} while (0) #define unoptimize_kprobe(p, f) do {} while (0) #define kill_optimized_kprobe(p) do {} while (0) #define prepare_optimized_kprobe(p) do {} while (0) #define try_to_optimize_kprobe(p) do {} while (0) #define __arm_kprobe(p) arch_arm_kprobe(p) #define __disarm_kprobe(p, o) arch_disarm_kprobe(p) #define kprobe_disarmed(p) kprobe_disabled(p) #define wait_for_kprobe_optimizer() do {} while (0) static int reuse_unused_kprobe(struct kprobe *ap) { /* * If the optimized kprobe is NOT supported, the aggr kprobe is * released at the same time that the last aggregated kprobe is * unregistered. * Thus there should be no chance to reuse unused kprobe. */ printk(KERN_ERR "Error: There should be no unused kprobe here.\n"); return -EINVAL; } static void free_aggr_kprobe(struct kprobe *p) { arch_remove_kprobe(p); kfree(p); } static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) { return kzalloc(sizeof(struct kprobe), GFP_KERNEL); } #endif /* CONFIG_OPTPROBES */ #ifdef CONFIG_KPROBES_ON_FTRACE static struct ftrace_ops kprobe_ftrace_ops __read_mostly = { .func = kprobe_ftrace_handler, .flags = FTRACE_OPS_FL_SAVE_REGS, }; static struct ftrace_ops kprobe_ipmodify_ops __read_mostly = { .func = kprobe_ftrace_handler, .flags = FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_IPMODIFY, }; static int kprobe_ipmodify_enabled; static int kprobe_ftrace_enabled; /* Must ensure p->addr is really on ftrace */ static int prepare_kprobe(struct kprobe *p) { if (!kprobe_ftrace(p)) return arch_prepare_kprobe(p); return arch_prepare_kprobe_ftrace(p); } /* Caller must lock kprobe_mutex */ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) { int ret = 0; ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 0, 0); if (ret) { pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n", p->addr, ret); return ret; } if (*cnt == 0) { ret = register_ftrace_function(ops); if (ret) { pr_debug("Failed to init kprobe-ftrace (%d)\n", ret); goto err_ftrace; } } (*cnt)++; return ret; err_ftrace: /* * At this point, sinec ops is not registered, we should be sefe from * registering empty filter. */ ftrace_set_filter_ip(ops, (unsigned long)p->addr, 1, 0); return ret; } static int arm_kprobe_ftrace(struct kprobe *p) { bool ipmodify = (p->post_handler != NULL); return __arm_kprobe_ftrace(p, ipmodify ? &kprobe_ipmodify_ops : &kprobe_ftrace_ops, ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } /* Caller must lock kprobe_mutex */ static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) { int ret = 0; if (*cnt == 1) { ret = unregister_ftrace_function(ops); if (WARN(ret < 0, "Failed to unregister kprobe-ftrace (%d)\n", ret)) return ret; } (*cnt)--; ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 1, 0); WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n", p->addr, ret); return ret; } static int disarm_kprobe_ftrace(struct kprobe *p) { bool ipmodify = (p->post_handler != NULL); return __disarm_kprobe_ftrace(p, ipmodify ? &kprobe_ipmodify_ops : &kprobe_ftrace_ops, ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } #else /* !CONFIG_KPROBES_ON_FTRACE */ static inline int prepare_kprobe(struct kprobe *p) { return arch_prepare_kprobe(p); } static inline int arm_kprobe_ftrace(struct kprobe *p) { return -ENODEV; } static inline int disarm_kprobe_ftrace(struct kprobe *p) { return -ENODEV; } #endif /* Arm a kprobe with text_mutex */ static int arm_kprobe(struct kprobe *kp) { if (unlikely(kprobe_ftrace(kp))) return arm_kprobe_ftrace(kp); cpus_read_lock(); mutex_lock(&text_mutex); __arm_kprobe(kp); mutex_unlock(&text_mutex); cpus_read_unlock(); return 0; } /* Disarm a kprobe with text_mutex */ static int disarm_kprobe(struct kprobe *kp, bool reopt) { if (unlikely(kprobe_ftrace(kp))) return disarm_kprobe_ftrace(kp); cpus_read_lock(); mutex_lock(&text_mutex); __disarm_kprobe(kp, reopt); mutex_unlock(&text_mutex); cpus_read_unlock(); return 0; } /* * Aggregate handlers for multiple kprobes support - these handlers * take care of invoking the individual kprobe handlers on p->list */ static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { if (kp->pre_handler && likely(!kprobe_disabled(kp))) { set_kprobe_instance(kp); if (kp->pre_handler(kp, regs)) return 1; } reset_kprobe_instance(); } return 0; } NOKPROBE_SYMBOL(aggr_pre_handler); static void aggr_post_handler(struct kprobe *p, struct pt_regs *regs, unsigned long flags) { struct kprobe *kp; list_for_each_entry_rcu(kp, &p->list, list) { if (kp->post_handler && likely(!kprobe_disabled(kp))) { set_kprobe_instance(kp); kp->post_handler(kp, regs, flags); reset_kprobe_instance(); } } } NOKPROBE_SYMBOL(aggr_post_handler); static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr) { struct kprobe *cur = __this_cpu_read(kprobe_instance); /* * if we faulted "during" the execution of a user specified * probe handler, invoke just that probe's fault handler */ if (cur && cur->fault_handler) { if (cur->fault_handler(cur, regs, trapnr)) return 1; } return 0; } NOKPROBE_SYMBOL(aggr_fault_handler); /* Walks the list and increments nmissed count for multiprobe case */ void kprobes_inc_nmissed_count(struct kprobe *p) { struct kprobe *kp; if (!kprobe_aggrprobe(p)) { p->nmissed++; } else { list_for_each_entry_rcu(kp, &p->list, list) kp->nmissed++; } return; } NOKPROBE_SYMBOL(kprobes_inc_nmissed_count); static void recycle_rp_inst(struct kretprobe_instance *ri) { struct kretprobe *rp = ri->rp; /* remove rp inst off the rprobe_inst_table */ hlist_del(&ri->hlist); INIT_HLIST_NODE(&ri->hlist); if (likely(rp)) { raw_spin_lock(&rp->lock); hlist_add_head(&ri->hlist, &rp->free_instances); raw_spin_unlock(&rp->lock); } else kfree_rcu(ri, rcu); } NOKPROBE_SYMBOL(recycle_rp_inst); static void kretprobe_hash_lock(struct task_struct *tsk, struct hlist_head **head, unsigned long *flags) __acquires(hlist_lock) { unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); raw_spinlock_t *hlist_lock; *head = &kretprobe_inst_table[hash]; hlist_lock = kretprobe_table_lock_ptr(hash); /* * Nested is a workaround that will soon not be needed. * There's other protections that make sure the same lock * is not taken on the same CPU that lockdep is unaware of. * Differentiate when it is taken in NMI context. */ raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi()); } NOKPROBE_SYMBOL(kretprobe_hash_lock); static void kretprobe_table_lock(unsigned long hash, unsigned long *flags) __acquires(hlist_lock) { raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); /* * Nested is a workaround that will soon not be needed. * There's other protections that make sure the same lock * is not taken on the same CPU that lockdep is unaware of. * Differentiate when it is taken in NMI context. */ raw_spin_lock_irqsave_nested(hlist_lock, *flags, !!in_nmi()); } NOKPROBE_SYMBOL(kretprobe_table_lock); static void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags) __releases(hlist_lock) { unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS); raw_spinlock_t *hlist_lock; hlist_lock = kretprobe_table_lock_ptr(hash); raw_spin_unlock_irqrestore(hlist_lock, *flags); } NOKPROBE_SYMBOL(kretprobe_hash_unlock); static void kretprobe_table_unlock(unsigned long hash, unsigned long *flags) __releases(hlist_lock) { raw_spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash); raw_spin_unlock_irqrestore(hlist_lock, *flags); } NOKPROBE_SYMBOL(kretprobe_table_unlock); static struct kprobe kprobe_busy = { .addr = (void *) get_kprobe, }; void kprobe_busy_begin(void) { struct kprobe_ctlblk *kcb; preempt_disable(); __this_cpu_write(current_kprobe, &kprobe_busy); kcb = get_kprobe_ctlblk(); kcb->kprobe_status = KPROBE_HIT_ACTIVE; } void kprobe_busy_end(void) { __this_cpu_write(current_kprobe, NULL); preempt_enable(); } /* * This function is called from finish_task_switch when task tk becomes dead, * so that we can recycle any function-return probe instances associated * with this task. These left over instances represent probed functions * that have been called but will never return. */ void kprobe_flush_task(struct task_struct *tk) { struct kretprobe_instance *ri; struct hlist_head *head; struct hlist_node *tmp; unsigned long hash, flags = 0; if (unlikely(!kprobes_initialized)) /* Early boot. kretprobe_table_locks not yet initialized. */ return; kprobe_busy_begin(); hash = hash_ptr(tk, KPROBE_HASH_BITS); head = &kretprobe_inst_table[hash]; kretprobe_table_lock(hash, &flags); hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task == tk) recycle_rp_inst(ri); } kretprobe_table_unlock(hash, &flags); kprobe_busy_end(); } NOKPROBE_SYMBOL(kprobe_flush_task); static inline void free_rp_inst(struct kretprobe *rp) { struct kretprobe_instance *ri; struct hlist_node *next; hlist_for_each_entry_safe(ri, next, &rp->free_instances, hlist) { hlist_del(&ri->hlist); kfree(ri); } } static void cleanup_rp_inst(struct kretprobe *rp) { unsigned long flags, hash; struct kretprobe_instance *ri; struct hlist_node *next; struct hlist_head *head; /* To avoid recursive kretprobe by NMI, set kprobe busy here */ kprobe_busy_begin(); for (hash = 0; hash < KPROBE_TABLE_SIZE; hash++) { kretprobe_table_lock(hash, &flags); head = &kretprobe_inst_table[hash]; hlist_for_each_entry_safe(ri, next, head, hlist) { if (ri->rp == rp) ri->rp = NULL; } kretprobe_table_unlock(hash, &flags); } kprobe_busy_end(); free_rp_inst(rp); } NOKPROBE_SYMBOL(cleanup_rp_inst); /* Add the new probe to ap->list */ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) { if (p->post_handler) unoptimize_kprobe(ap, true); /* Fall back to normal kprobe */ list_add_rcu(&p->list, &ap->list); if (p->post_handler && !ap->post_handler) ap->post_handler = aggr_post_handler; return 0; } /* * Fill in the required fields of the "manager kprobe". Replace the * earlier kprobe in the hlist with the manager kprobe */ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) { /* Copy p's insn slot to ap */ copy_kprobe(p, ap); flush_insn_slot(ap); ap->addr = p->addr; ap->flags = p->flags & ~KPROBE_FLAG_OPTIMIZED; ap->pre_handler = aggr_pre_handler; ap->fault_handler = aggr_fault_handler; /* We don't care the kprobe which has gone. */ if (p->post_handler && !kprobe_gone(p)) ap->post_handler = aggr_post_handler; INIT_LIST_HEAD(&ap->list); INIT_HLIST_NODE(&ap->hlist); list_add_rcu(&p->list, &ap->list); hlist_replace_rcu(&p->hlist, &ap->hlist); } /* * This is the second or subsequent kprobe at the address - handle * the intricacies */ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) { int ret = 0; struct kprobe *ap = orig_p; cpus_read_lock(); /* For preparing optimization, jump_label_text_reserved() is called */ jump_label_lock(); mutex_lock(&text_mutex); if (!kprobe_aggrprobe(orig_p)) { /* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */ ap = alloc_aggr_kprobe(orig_p); if (!ap) { ret = -ENOMEM; goto out; } init_aggr_kprobe(ap, orig_p); } else if (kprobe_unused(ap)) { /* This probe is going to die. Rescue it */ ret = reuse_unused_kprobe(ap); if (ret) goto out; } if (kprobe_gone(ap)) { /* * Attempting to insert new probe at the same location that * had a probe in the module vaddr area which already * freed. So, the instruction slot has already been * released. We need a new slot for the new probe. */ ret = arch_prepare_kprobe(ap); if (ret) /* * Even if fail to allocate new slot, don't need to * free aggr_probe. It will be used next time, or * freed by unregister_kprobe. */ goto out; /* Prepare optimized instructions if possible. */ prepare_optimized_kprobe(ap); /* * Clear gone flag to prevent allocating new slot again, and * set disabled flag because it is not armed yet. */ ap->flags = (ap->flags & ~KPROBE_FLAG_GONE) | KPROBE_FLAG_DISABLED; } /* Copy ap's insn slot to p */ copy_kprobe(ap, p); ret = add_new_kprobe(ap, p); out: mutex_unlock(&text_mutex); jump_label_unlock(); cpus_read_unlock(); if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { ap->flags &= ~KPROBE_FLAG_DISABLED; if (!kprobes_all_disarmed) { /* Arm the breakpoint again. */ ret = arm_kprobe(ap); if (ret) { ap->flags |= KPROBE_FLAG_DISABLED; list_del_rcu(&p->list); synchronize_rcu(); } } } return ret; } bool __weak arch_within_kprobe_blacklist(unsigned long addr) { /* The __kprobes marked functions and entry code must not be probed */ return addr >= (unsigned long)__kprobes_text_start && addr < (unsigned long)__kprobes_text_end; } static bool __within_kprobe_blacklist(unsigned long addr) { struct kprobe_blacklist_entry *ent; if (arch_within_kprobe_blacklist(addr)) return true; /* * If there exists a kprobe_blacklist, verify and * fail any probe registration in the prohibited area */ list_for_each_entry(ent, &kprobe_blacklist, list) { if (addr >= ent->start_addr && addr < ent->end_addr) return true; } return false; } bool within_kprobe_blacklist(unsigned long addr) { char symname[KSYM_NAME_LEN], *p; if (__within_kprobe_blacklist(addr)) return true; /* Check if the address is on a suffixed-symbol */ if (!lookup_symbol_name(addr, symname)) { p = strchr(symname, '.'); if (!p) return false; *p = '\0'; addr = (unsigned long)kprobe_lookup_name(symname, 0); if (addr) return __within_kprobe_blacklist(addr); } return false; } /* * If we have a symbol_name argument, look it up and add the offset field * to it. This way, we can specify a relative address to a symbol. * This returns encoded errors if it fails to look up symbol or invalid * combination of parameters. */ static kprobe_opcode_t *_kprobe_addr(kprobe_opcode_t *addr, const char *symbol_name, unsigned int offset) { if ((symbol_name && addr) || (!symbol_name && !addr)) goto invalid; if (symbol_name) { addr = kprobe_lookup_name(symbol_name, offset); if (!addr) return ERR_PTR(-ENOENT); } addr = (kprobe_opcode_t *)(((char *)addr) + offset); if (addr) return addr; invalid: return ERR_PTR(-EINVAL); } static kprobe_opcode_t *kprobe_addr(struct kprobe *p) { return _kprobe_addr(p->addr, p->symbol_name, p->offset); } /* Check passed kprobe is valid and return kprobe in kprobe_table. */ static struct kprobe *__get_valid_kprobe(struct kprobe *p) { struct kprobe *ap, *list_p; lockdep_assert_held(&kprobe_mutex); ap = get_kprobe(p->addr); if (unlikely(!ap)) return NULL; if (p != ap) { list_for_each_entry(list_p, &ap->list, list) if (list_p == p) /* kprobe p is a valid probe */ goto valid; return NULL; } valid: return ap; } /* Return error if the kprobe is being re-registered */ static inline int check_kprobe_rereg(struct kprobe *p) { int ret = 0; mutex_lock(&kprobe_mutex); if (__get_valid_kprobe(p)) ret = -EINVAL; mutex_unlock(&kprobe_mutex); return ret; } int __weak arch_check_ftrace_location(struct kprobe *p) { unsigned long addr = (unsigned long)p->addr; if (ftrace_location(addr) == addr) { #ifdef CONFIG_KPROBES_ON_FTRACE p->flags |= KPROBE_FLAG_FTRACE; #else /* !CONFIG_KPROBES_ON_FTRACE */ return -EINVAL; #endif } return 0; } static bool is_cfi_preamble_symbol(unsigned long addr) { char symbuf[KSYM_NAME_LEN]; if (lookup_symbol_name(addr, symbuf)) return false; return str_has_prefix(symbuf, "__cfi_") || str_has_prefix(symbuf, "__pfx_"); } static int check_kprobe_address_safe(struct kprobe *p, struct module **probed_mod) { int ret; ret = arch_check_ftrace_location(p); if (ret) return ret; jump_label_lock(); preempt_disable(); /* Ensure the address is in a text area, and find a module if exists. */ *probed_mod = NULL; if (!core_kernel_text((unsigned long) p->addr)) { *probed_mod = __module_text_address((unsigned long) p->addr); if (!(*probed_mod)) { ret = -EINVAL; goto out; } } /* Ensure it is not in reserved area. */ if (in_gate_area_no_mm((unsigned long) p->addr) || within_kprobe_blacklist((unsigned long) p->addr) || jump_label_text_reserved(p->addr, p->addr) || static_call_text_reserved(p->addr, p->addr) || find_bug((unsigned long)p->addr) || is_cfi_preamble_symbol((unsigned long)p->addr)) { ret = -EINVAL; goto out; } /* Get module refcount and reject __init functions for loaded modules. */ if (*probed_mod) { /* * We must hold a refcount of the probed module while updating * its code to prohibit unexpected unloading. */ if (unlikely(!try_module_get(*probed_mod))) { ret = -ENOENT; goto out; } /* * If the module freed .init.text, we couldn't insert * kprobes in there. */ if (within_module_init((unsigned long)p->addr, *probed_mod) && (*probed_mod)->state != MODULE_STATE_COMING) { module_put(*probed_mod); *probed_mod = NULL; ret = -ENOENT; } } out: preempt_enable(); jump_label_unlock(); return ret; } int register_kprobe(struct kprobe *p) { int ret; struct kprobe *old_p; struct module *probed_mod; kprobe_opcode_t *addr; /* Adjust probe address from symbol */ addr = kprobe_addr(p); if (IS_ERR(addr)) return PTR_ERR(addr); p->addr = addr; ret = check_kprobe_rereg(p); if (ret) return ret; /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ p->flags &= KPROBE_FLAG_DISABLED; p->nmissed = 0; INIT_LIST_HEAD(&p->list); ret = check_kprobe_address_safe(p, &probed_mod); if (ret) return ret; mutex_lock(&kprobe_mutex); old_p = get_kprobe(p->addr); if (old_p) { /* Since this may unoptimize old_p, locking text_mutex. */ ret = register_aggr_kprobe(old_p, p); goto out; } cpus_read_lock(); /* Prevent text modification */ mutex_lock(&text_mutex); ret = prepare_kprobe(p); mutex_unlock(&text_mutex); cpus_read_unlock(); if (ret) goto out; INIT_HLIST_NODE(&p->hlist); hlist_add_head_rcu(&p->hlist, &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); if (!kprobes_all_disarmed && !kprobe_disabled(p)) { ret = arm_kprobe(p); if (ret) { hlist_del_rcu(&p->hlist); synchronize_rcu(); goto out; } } /* Try to optimize kprobe */ try_to_optimize_kprobe(p); out: mutex_unlock(&kprobe_mutex); if (probed_mod) module_put(probed_mod); return ret; } EXPORT_SYMBOL_GPL(register_kprobe); /* Check if all probes on the aggrprobe are disabled */ static int aggr_kprobe_disabled(struct kprobe *ap) { struct kprobe *kp; lockdep_assert_held(&kprobe_mutex); list_for_each_entry(kp, &ap->list, list) if (!kprobe_disabled(kp)) /* * There is an active probe on the list. * We can't disable this ap. */ return 0; return 1; } /* Disable one kprobe: Make sure called under kprobe_mutex is locked */ static struct kprobe *__disable_kprobe(struct kprobe *p) { struct kprobe *orig_p; int ret; /* Get an original kprobe for return */ orig_p = __get_valid_kprobe(p); if (unlikely(orig_p == NULL)) return ERR_PTR(-EINVAL); if (!kprobe_disabled(p)) { /* Disable probe if it is a child probe */ if (p != orig_p) p->flags |= KPROBE_FLAG_DISABLED; /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { /* * Don't be lazy here. Even if 'kprobes_all_disarmed' * is false, 'orig_p' might not have been armed yet. * Note arm_all_kprobes() __tries__ to arm all kprobes * on the best effort basis. */ if (!kprobes_all_disarmed && !kprobe_disabled(orig_p)) { ret = disarm_kprobe(orig_p, true); if (ret) { p->flags &= ~KPROBE_FLAG_DISABLED; return ERR_PTR(ret); } } orig_p->flags |= KPROBE_FLAG_DISABLED; } } return orig_p; } /* * Unregister a kprobe without a scheduler synchronization. */ static int __unregister_kprobe_top(struct kprobe *p) { struct kprobe *ap, *list_p; /* Disable kprobe. This will disarm it if needed. */ ap = __disable_kprobe(p); if (IS_ERR(ap)) return PTR_ERR(ap); if (ap == p) /* * This probe is an independent(and non-optimized) kprobe * (not an aggrprobe). Remove from the hash list. */ goto disarmed; /* Following process expects this probe is an aggrprobe */ WARN_ON(!kprobe_aggrprobe(ap)); if (list_is_singular(&ap->list) && kprobe_disarmed(ap)) /* * !disarmed could be happen if the probe is under delayed * unoptimizing. */ goto disarmed; else { /* If disabling probe has special handlers, update aggrprobe */ if (p->post_handler && !kprobe_gone(p)) { list_for_each_entry(list_p, &ap->list, list) { if ((list_p != p) && (list_p->post_handler)) goto noclean; } /* * For the kprobe-on-ftrace case, we keep the * post_handler setting to identify this aggrprobe * armed with kprobe_ipmodify_ops. */ if (!kprobe_ftrace(ap)) ap->post_handler = NULL; } noclean: /* * Remove from the aggrprobe: this path will do nothing in * __unregister_kprobe_bottom(). */ list_del_rcu(&p->list); if (!kprobe_disabled(ap) && !kprobes_all_disarmed) /* * Try to optimize this probe again, because post * handler may have been changed. */ optimize_kprobe(ap); } return 0; disarmed: hlist_del_rcu(&ap->hlist); return 0; } static void __unregister_kprobe_bottom(struct kprobe *p) { struct kprobe *ap; if (list_empty(&p->list)) /* This is an independent kprobe */ arch_remove_kprobe(p); else if (list_is_singular(&p->list)) { /* This is the last child of an aggrprobe */ ap = list_entry(p->list.next, struct kprobe, list); list_del(&p->list); free_aggr_kprobe(ap); } /* Otherwise, do nothing. */ } int register_kprobes(struct kprobe **kps, int num) { int i, ret = 0; if (num <= 0) return -EINVAL; for (i = 0; i < num; i++) { ret = register_kprobe(kps[i]); if (ret < 0) { if (i > 0) unregister_kprobes(kps, i); break; } } return ret; } EXPORT_SYMBOL_GPL(register_kprobes); void unregister_kprobe(struct kprobe *p) { unregister_kprobes(&p, 1); } EXPORT_SYMBOL_GPL(unregister_kprobe); void unregister_kprobes(struct kprobe **kps, int num) { int i; if (num <= 0) return; mutex_lock(&kprobe_mutex); for (i = 0; i < num; i++) if (__unregister_kprobe_top(kps[i]) < 0) kps[i]->addr = NULL; mutex_unlock(&kprobe_mutex); synchronize_rcu(); for (i = 0; i < num; i++) if (kps[i]->addr) __unregister_kprobe_bottom(kps[i]); } EXPORT_SYMBOL_GPL(unregister_kprobes); int __weak kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) { return NOTIFY_DONE; } NOKPROBE_SYMBOL(kprobe_exceptions_notify); static struct notifier_block kprobe_exceptions_nb = { .notifier_call = kprobe_exceptions_notify, .priority = 0x7fffffff /* we need to be notified first */ }; unsigned long __weak arch_deref_entry_point(void *entry) { return (unsigned long)entry; } #ifdef CONFIG_KRETPROBES unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, void *trampoline_address, void *frame_pointer) { struct kretprobe_instance *ri = NULL, *last = NULL; struct hlist_head *head; struct hlist_node *tmp; unsigned long flags; kprobe_opcode_t *correct_ret_addr = NULL; bool skipped = false; kretprobe_hash_lock(current, &head, &flags); /* * It is possible to have multiple instances associated with a given * task either because multiple functions in the call path have * return probes installed on them, and/or more than one * return probe was registered for a target function. * * We can handle this because: * - instances are always pushed into the head of the list * - when multiple return probes are registered for the same * function, the (chronologically) first instance's ret_addr * will be the real return address, and all the rest will * point to kretprobe_trampoline. */ hlist_for_each_entry(ri, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; /* * Return probes must be pushed on this hash list correct * order (same as return order) so that it can be popped * correctly. However, if we find it is pushed it incorrect * order, this means we find a function which should not be * probed, because the wrong order entry is pushed on the * path of processing other kretprobe itself. */ if (ri->fp != frame_pointer) { if (!skipped) pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n"); skipped = true; continue; } correct_ret_addr = ri->ret_addr; if (skipped) pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n", ri->rp->kp.addr); if (correct_ret_addr != trampoline_address) /* * This is the real return address. Any other * instances associated with this task are for * other calls deeper on the call stack */ break; } BUG_ON(!correct_ret_addr || (correct_ret_addr == trampoline_address)); last = ri; hlist_for_each_entry_safe(ri, tmp, head, hlist) { if (ri->task != current) /* another task is sharing our hash bucket */ continue; if (ri->fp != frame_pointer) continue; if (ri->rp && ri->rp->handler) { struct kprobe *prev = kprobe_running(); __this_cpu_write(current_kprobe, &ri->rp->kp); ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); __this_cpu_write(current_kprobe, prev); } recycle_rp_inst(ri); if (ri == last) break; } kretprobe_hash_unlock(current, &flags); return (unsigned long)correct_ret_addr; } NOKPROBE_SYMBOL(__kretprobe_trampoline_handler) /* * This kprobe pre_handler is registered with every kretprobe. When probe * hits it will set up the return probe. */ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) { struct kretprobe *rp = container_of(p, struct kretprobe, kp); unsigned long hash, flags = 0; struct kretprobe_instance *ri; /* TODO: consider to only swap the RA after the last pre_handler fired */ hash = hash_ptr(current, KPROBE_HASH_BITS); /* * Nested is a workaround that will soon not be needed. * There's other protections that make sure the same lock * is not taken on the same CPU that lockdep is unaware of. */ raw_spin_lock_irqsave_nested(&rp->lock, flags, 1); if (!hlist_empty(&rp->free_instances)) { ri = hlist_entry(rp->free_instances.first, struct kretprobe_instance, hlist); hlist_del(&ri->hlist); raw_spin_unlock_irqrestore(&rp->lock, flags); ri->rp = rp; ri->task = current; if (rp->entry_handler && rp->entry_handler(ri, regs)) { raw_spin_lock_irqsave_nested(&rp->lock, flags, 1); hlist_add_head(&ri->hlist, &rp->free_instances); raw_spin_unlock_irqrestore(&rp->lock, flags); return 0; } arch_prepare_kretprobe(ri, regs); /* XXX(hch): why is there no hlist_move_head? */ INIT_HLIST_NODE(&ri->hlist); kretprobe_table_lock(hash, &flags); hlist_add_head(&ri->hlist, &kretprobe_inst_table[hash]); kretprobe_table_unlock(hash, &flags); } else { rp->nmissed++; raw_spin_unlock_irqrestore(&rp->lock, flags); } return 0; } NOKPROBE_SYMBOL(pre_handler_kretprobe); bool __weak arch_kprobe_on_func_entry(unsigned long offset) { return !offset; } /** * kprobe_on_func_entry() -- check whether given address is function entry * @addr: Target address * @sym: Target symbol name * @offset: The offset from the symbol or the address * * This checks whether the given @addr+@offset or @sym+@offset is on the * function entry address or not. * This returns 0 if it is the function entry, or -EINVAL if it is not. * And also it returns -ENOENT if it fails the symbol or address lookup. * Caller must pass @addr or @sym (either one must be NULL), or this * returns -EINVAL. */ int kprobe_on_func_entry(kprobe_opcode_t *addr, const char *sym, unsigned long offset) { kprobe_opcode_t *kp_addr = _kprobe_addr(addr, sym, offset); if (IS_ERR(kp_addr)) return PTR_ERR(kp_addr); if (!kallsyms_lookup_size_offset((unsigned long)kp_addr, NULL, &offset)) return -ENOENT; if (!arch_kprobe_on_func_entry(offset)) return -EINVAL; return 0; } int register_kretprobe(struct kretprobe *rp) { int ret; struct kretprobe_instance *inst; int i; void *addr; ret = kprobe_on_func_entry(rp->kp.addr, rp->kp.symbol_name, rp->kp.offset); if (ret) return ret; /* If only rp->kp.addr is specified, check reregistering kprobes */ if (rp->kp.addr && check_kprobe_rereg(&rp->kp)) return -EINVAL; if (kretprobe_blacklist_size) { addr = kprobe_addr(&rp->kp); if (IS_ERR(addr)) return PTR_ERR(addr); for (i = 0; kretprobe_blacklist[i].name != NULL; i++) { if (kretprobe_blacklist[i].addr == addr) return -EINVAL; } } if (rp->data_size > KRETPROBE_MAX_DATA_SIZE) return -E2BIG; rp->kp.pre_handler = pre_handler_kretprobe; rp->kp.post_handler = NULL; rp->kp.fault_handler = NULL; /* Pre-allocate memory for max kretprobe instances */ if (rp->maxactive <= 0) { #ifdef CONFIG_PREEMPTION rp->maxactive = max_t(unsigned int, 10, 2*num_possible_cpus()); #else rp->maxactive = num_possible_cpus(); #endif } raw_spin_lock_init(&rp->lock); INIT_HLIST_HEAD(&rp->free_instances); for (i = 0; i < rp->maxactive; i++) { inst = kmalloc(sizeof(struct kretprobe_instance) + rp->data_size, GFP_KERNEL); if (inst == NULL) { free_rp_inst(rp); return -ENOMEM; } INIT_HLIST_NODE(&inst->hlist); hlist_add_head(&inst->hlist, &rp->free_instances); } rp->nmissed = 0; /* Establish function entry probe point */ ret = register_kprobe(&rp->kp); if (ret != 0) free_rp_inst(rp); return ret; } EXPORT_SYMBOL_GPL(register_kretprobe); int register_kretprobes(struct kretprobe **rps, int num) { int ret = 0, i; if (num <= 0) return -EINVAL; for (i = 0; i < num; i++) { ret = register_kretprobe(rps[i]); if (ret < 0) { if (i > 0) unregister_kretprobes(rps, i); break; } } return ret; } EXPORT_SYMBOL_GPL(register_kretprobes); void unregister_kretprobe(struct kretprobe *rp) { unregister_kretprobes(&rp, 1); } EXPORT_SYMBOL_GPL(unregister_kretprobe); void unregister_kretprobes(struct kretprobe **rps, int num) { int i; if (num <= 0) return; mutex_lock(&kprobe_mutex); for (i = 0; i < num; i++) if (__unregister_kprobe_top(&rps[i]->kp) < 0) rps[i]->kp.addr = NULL; mutex_unlock(&kprobe_mutex); synchronize_rcu(); for (i = 0; i < num; i++) { if (rps[i]->kp.addr) { __unregister_kprobe_bottom(&rps[i]->kp); cleanup_rp_inst(rps[i]); } } } EXPORT_SYMBOL_GPL(unregister_kretprobes); #else /* CONFIG_KRETPROBES */ int register_kretprobe(struct kretprobe *rp) { return -ENOSYS; } EXPORT_SYMBOL_GPL(register_kretprobe); int register_kretprobes(struct kretprobe **rps, int num) { return -ENOSYS; } EXPORT_SYMBOL_GPL(register_kretprobes); void unregister_kretprobe(struct kretprobe *rp) { } EXPORT_SYMBOL_GPL(unregister_kretprobe); void unregister_kretprobes(struct kretprobe **rps, int num) { } EXPORT_SYMBOL_GPL(unregister_kretprobes); static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs) { return 0; } NOKPROBE_SYMBOL(pre_handler_kretprobe); #endif /* CONFIG_KRETPROBES */ /* Set the kprobe gone and remove its instruction buffer. */ static void kill_kprobe(struct kprobe *p) { struct kprobe *kp; lockdep_assert_held(&kprobe_mutex); if (WARN_ON_ONCE(kprobe_gone(p))) return; p->flags |= KPROBE_FLAG_GONE; if (kprobe_aggrprobe(p)) { /* * If this is an aggr_kprobe, we have to list all the * chained probes and mark them GONE. */ list_for_each_entry(kp, &p->list, list) kp->flags |= KPROBE_FLAG_GONE; p->post_handler = NULL; kill_optimized_kprobe(p); } /* * Here, we can remove insn_slot safely, because no thread calls * the original probed function (which will be freed soon) any more. */ arch_remove_kprobe(p); /* * The module is going away. We should disarm the kprobe which * is using ftrace, because ftrace framework is still available at * MODULE_STATE_GOING notification. */ if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed) disarm_kprobe_ftrace(p); } /* Disable one kprobe */ int disable_kprobe(struct kprobe *kp) { int ret = 0; struct kprobe *p; mutex_lock(&kprobe_mutex); /* Disable this kprobe */ p = __disable_kprobe(kp); if (IS_ERR(p)) ret = PTR_ERR(p); mutex_unlock(&kprobe_mutex); return ret; } EXPORT_SYMBOL_GPL(disable_kprobe); /* Enable one kprobe */ int enable_kprobe(struct kprobe *kp) { int ret = 0; struct kprobe *p; mutex_lock(&kprobe_mutex); /* Check whether specified probe is valid. */ p = __get_valid_kprobe(kp); if (unlikely(p == NULL)) { ret = -EINVAL; goto out; } if (kprobe_gone(kp)) { /* This kprobe has gone, we couldn't enable it. */ ret = -EINVAL; goto out; } if (p != kp) kp->flags &= ~KPROBE_FLAG_DISABLED; if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; ret = arm_kprobe(p); if (ret) { p->flags |= KPROBE_FLAG_DISABLED; if (p != kp) kp->flags |= KPROBE_FLAG_DISABLED; } } out: mutex_unlock(&kprobe_mutex); return ret; } EXPORT_SYMBOL_GPL(enable_kprobe); /* Caller must NOT call this in usual path. This is only for critical case */ void dump_kprobe(struct kprobe *kp) { pr_err("Dumping kprobe:\n"); pr_err("Name: %s\nOffset: %x\nAddress: %pS\n", kp->symbol_name, kp->offset, kp->addr); } NOKPROBE_SYMBOL(dump_kprobe); int kprobe_add_ksym_blacklist(unsigned long entry) { struct kprobe_blacklist_entry *ent; unsigned long offset = 0, size = 0; if (!kernel_text_address(entry) || !kallsyms_lookup_size_offset(entry, &size, &offset)) return -EINVAL; ent = kmalloc(sizeof(*ent), GFP_KERNEL); if (!ent) return -ENOMEM; ent->start_addr = entry; ent->end_addr = entry + size; INIT_LIST_HEAD(&ent->list); list_add_tail(&ent->list, &kprobe_blacklist); return (int)size; } /* Add all symbols in given area into kprobe blacklist */ int kprobe_add_area_blacklist(unsigned long start, unsigned long end) { unsigned long entry; int ret = 0; for (entry = start; entry < end; entry += ret) { ret = kprobe_add_ksym_blacklist(entry); if (ret < 0) return ret; if (ret == 0) /* In case of alias symbol */ ret = 1; } return 0; } /* Remove all symbols in given area from kprobe blacklist */ static void kprobe_remove_area_blacklist(unsigned long start, unsigned long end) { struct kprobe_blacklist_entry *ent, *n; list_for_each_entry_safe(ent, n, &kprobe_blacklist, list) { if (ent->start_addr < start || ent->start_addr >= end) continue; list_del(&ent->list); kfree(ent); } } static void kprobe_remove_ksym_blacklist(unsigned long entry) { kprobe_remove_area_blacklist(entry, entry + 1); } int __weak arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value, char *type, char *sym) { return -ERANGE; } int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { #ifdef __ARCH_WANT_KPROBES_INSN_SLOT if (!kprobe_cache_get_kallsym(&kprobe_insn_slots, &symnum, value, type, sym)) return 0; #ifdef CONFIG_OPTPROBES if (!kprobe_cache_get_kallsym(&kprobe_optinsn_slots, &symnum, value, type, sym)) return 0; #endif #endif if (!arch_kprobe_get_kallsym(&symnum, value, type, sym)) return 0; return -ERANGE; } int __init __weak arch_populate_kprobe_blacklist(void) { return 0; } /* * Lookup and populate the kprobe_blacklist. * * Unlike the kretprobe blacklist, we'll need to determine * the range of addresses that belong to the said functions, * since a kprobe need not necessarily be at the beginning * of a function. */ static int __init populate_kprobe_blacklist(unsigned long *start, unsigned long *end) { unsigned long entry; unsigned long *iter; int ret; for (iter = start; iter < end; iter++) { entry = arch_deref_entry_point((void *)*iter); ret = kprobe_add_ksym_blacklist(entry); if (ret == -EINVAL) continue; if (ret < 0) return ret; } /* Symbols in __kprobes_text are blacklisted */ ret = kprobe_add_area_blacklist((unsigned long)__kprobes_text_start, (unsigned long)__kprobes_text_end); if (ret) return ret; /* Symbols in noinstr section are blacklisted */ ret = kprobe_add_area_blacklist((unsigned long)__noinstr_text_start, (unsigned long)__noinstr_text_end); return ret ? : arch_populate_kprobe_blacklist(); } static void add_module_kprobe_blacklist(struct module *mod) { unsigned long start, end; int i; if (mod->kprobe_blacklist) { for (i = 0; i < mod->num_kprobe_blacklist; i++) kprobe_add_ksym_blacklist(mod->kprobe_blacklist[i]); } start = (unsigned long)mod->kprobes_text_start; if (start) { end = start + mod->kprobes_text_size; kprobe_add_area_blacklist(start, end); } start = (unsigned long)mod->noinstr_text_start; if (start) { end = start + mod->noinstr_text_size; kprobe_add_area_blacklist(start, end); } } static void remove_module_kprobe_blacklist(struct module *mod) { unsigned long start, end; int i; if (mod->kprobe_blacklist) { for (i = 0; i < mod->num_kprobe_blacklist; i++) kprobe_remove_ksym_blacklist(mod->kprobe_blacklist[i]); } start = (unsigned long)mod->kprobes_text_start; if (start) { end = start + mod->kprobes_text_size; kprobe_remove_area_blacklist(start, end); } start = (unsigned long)mod->noinstr_text_start; if (start) { end = start + mod->noinstr_text_size; kprobe_remove_area_blacklist(start, end); } } /* Module notifier call back, checking kprobes on the module */ static int kprobes_module_callback(struct notifier_block *nb, unsigned long val, void *data) { struct module *mod = data; struct hlist_head *head; struct kprobe *p; unsigned int i; int checkcore = (val == MODULE_STATE_GOING); if (val == MODULE_STATE_COMING) { mutex_lock(&kprobe_mutex); add_module_kprobe_blacklist(mod); mutex_unlock(&kprobe_mutex); } if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE) return NOTIFY_DONE; /* * When MODULE_STATE_GOING was notified, both of module .text and * .init.text sections would be freed. When MODULE_STATE_LIVE was * notified, only .init.text section would be freed. We need to * disable kprobes which have been inserted in the sections. */ mutex_lock(&kprobe_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) { if (kprobe_gone(p)) continue; if (within_module_init((unsigned long)p->addr, mod) || (checkcore && within_module_core((unsigned long)p->addr, mod))) { /* * The vaddr this probe is installed will soon * be vfreed buy not synced to disk. Hence, * disarming the breakpoint isn't needed. * * Note, this will also move any optimized probes * that are pending to be removed from their * corresponding lists to the freeing_list and * will not be touched by the delayed * kprobe_optimizer work handler. */ kill_kprobe(p); } } } if (val == MODULE_STATE_GOING) remove_module_kprobe_blacklist(mod); mutex_unlock(&kprobe_mutex); return NOTIFY_DONE; } static struct notifier_block kprobe_module_nb = { .notifier_call = kprobes_module_callback, .priority = 0 }; /* Markers of _kprobe_blacklist section */ extern unsigned long __start_kprobe_blacklist[]; extern unsigned long __stop_kprobe_blacklist[]; void kprobe_free_init_mem(void) { void *start = (void *)(&__init_begin); void *end = (void *)(&__init_end); struct hlist_head *head; struct kprobe *p; int i; mutex_lock(&kprobe_mutex); /* Kill all kprobes on initmem */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) { if (start <= (void *)p->addr && (void *)p->addr < end) kill_kprobe(p); } } mutex_unlock(&kprobe_mutex); } static int __init init_kprobes(void) { int i, err = 0; /* FIXME allocate the probe table, currently defined statically */ /* initialize all list heads */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { INIT_HLIST_HEAD(&kprobe_table[i]); INIT_HLIST_HEAD(&kretprobe_inst_table[i]); raw_spin_lock_init(&(kretprobe_table_locks[i].lock)); } err = populate_kprobe_blacklist(__start_kprobe_blacklist, __stop_kprobe_blacklist); if (err) { pr_err("kprobes: failed to populate blacklist: %d\n", err); pr_err("Please take care of using kprobes.\n"); } if (kretprobe_blacklist_size) { /* lookup the function address from its name */ for (i = 0; kretprobe_blacklist[i].name != NULL; i++) { kretprobe_blacklist[i].addr = kprobe_lookup_name(kretprobe_blacklist[i].name, 0); if (!kretprobe_blacklist[i].addr) printk("kretprobe: lookup failed: %s\n", kretprobe_blacklist[i].name); } } /* By default, kprobes are armed */ kprobes_all_disarmed = false; #if defined(CONFIG_OPTPROBES) && defined(__ARCH_WANT_KPROBES_INSN_SLOT) /* Init kprobe_optinsn_slots for allocation */ kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; #endif err = arch_init_kprobes(); if (!err) err = register_die_notifier(&kprobe_exceptions_nb); if (!err) err = register_module_notifier(&kprobe_module_nb); kprobes_initialized = (err == 0); if (!err) init_test_probes(); return err; } early_initcall(init_kprobes); #if defined(CONFIG_OPTPROBES) static int __init init_optprobes(void) { /* * Enable kprobe optimization - this kicks the optimizer which * depends on synchronize_rcu_tasks() and ksoftirqd, that is * not spawned in early initcall. So delay the optimization. */ optimize_all_kprobes(); return 0; } subsys_initcall(init_optprobes); #endif #ifdef CONFIG_DEBUG_FS static void report_probe(struct seq_file *pi, struct kprobe *p, const char *sym, int offset, char *modname, struct kprobe *pp) { char *kprobe_type; void *addr = p->addr; if (p->pre_handler == pre_handler_kretprobe) kprobe_type = "r"; else kprobe_type = "k"; if (!kallsyms_show_value(pi->file->f_cred)) addr = NULL; if (sym) seq_printf(pi, "%px %s %s+0x%x %s ", addr, kprobe_type, sym, offset, (modname ? modname : " ")); else /* try to use %pS */ seq_printf(pi, "%px %s %pS ", addr, kprobe_type, p->addr); if (!pp) pp = p; seq_printf(pi, "%s%s%s%s\n", (kprobe_gone(p) ? "[GONE]" : ""), ((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""), (kprobe_optimized(pp) ? "[OPTIMIZED]" : ""), (kprobe_ftrace(pp) ? "[FTRACE]" : "")); } static void *kprobe_seq_start(struct seq_file *f, loff_t *pos) { return (*pos < KPROBE_TABLE_SIZE) ? pos : NULL; } static void *kprobe_seq_next(struct seq_file *f, void *v, loff_t *pos) { (*pos)++; if (*pos >= KPROBE_TABLE_SIZE) return NULL; return pos; } static void kprobe_seq_stop(struct seq_file *f, void *v) { /* Nothing to do */ } static int show_kprobe_addr(struct seq_file *pi, void *v) { struct hlist_head *head; struct kprobe *p, *kp; const char *sym = NULL; unsigned int i = *(loff_t *) v; unsigned long offset = 0; char *modname, namebuf[KSYM_NAME_LEN]; head = &kprobe_table[i]; preempt_disable(); hlist_for_each_entry_rcu(p, head, hlist) { sym = kallsyms_lookup((unsigned long)p->addr, NULL, &offset, &modname, namebuf); if (kprobe_aggrprobe(p)) { list_for_each_entry_rcu(kp, &p->list, list) report_probe(pi, kp, sym, offset, modname, p); } else report_probe(pi, p, sym, offset, modname, NULL); } preempt_enable(); return 0; } static const struct seq_operations kprobes_sops = { .start = kprobe_seq_start, .next = kprobe_seq_next, .stop = kprobe_seq_stop, .show = show_kprobe_addr }; DEFINE_SEQ_ATTRIBUTE(kprobes); /* kprobes/blacklist -- shows which functions can not be probed */ static void *kprobe_blacklist_seq_start(struct seq_file *m, loff_t *pos) { mutex_lock(&kprobe_mutex); return seq_list_start(&kprobe_blacklist, *pos); } static void *kprobe_blacklist_seq_next(struct seq_file *m, void *v, loff_t *pos) { return seq_list_next(v, &kprobe_blacklist, pos); } static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) { struct kprobe_blacklist_entry *ent = list_entry(v, struct kprobe_blacklist_entry, list); /* * If /proc/kallsyms is not showing kernel address, we won't * show them here either. */ if (!kallsyms_show_value(m->file->f_cred)) seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL, (void *)ent->start_addr); else seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr, (void *)ent->end_addr, (void *)ent->start_addr); return 0; } static void kprobe_blacklist_seq_stop(struct seq_file *f, void *v) { mutex_unlock(&kprobe_mutex); } static const struct seq_operations kprobe_blacklist_sops = { .start = kprobe_blacklist_seq_start, .next = kprobe_blacklist_seq_next, .stop = kprobe_blacklist_seq_stop, .show = kprobe_blacklist_seq_show, }; DEFINE_SEQ_ATTRIBUTE(kprobe_blacklist); static int arm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i, total = 0, errors = 0; int err, ret = 0; mutex_lock(&kprobe_mutex); /* If kprobes are armed, just return */ if (!kprobes_all_disarmed) goto already_enabled; /* * optimize_kprobe() called by arm_kprobe() checks * kprobes_all_disarmed, so set kprobes_all_disarmed before * arm_kprobe. */ kprobes_all_disarmed = false; /* Arming kprobes doesn't optimize kprobe itself */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; /* Arm all kprobes on a best-effort basis */ hlist_for_each_entry(p, head, hlist) { if (!kprobe_disabled(p)) { err = arm_kprobe(p); if (err) { errors++; ret = err; } total++; } } } if (errors) pr_warn("Kprobes globally enabled, but failed to arm %d out of %d probes\n", errors, total); else pr_info("Kprobes globally enabled\n"); already_enabled: mutex_unlock(&kprobe_mutex); return ret; } static int disarm_all_kprobes(void) { struct hlist_head *head; struct kprobe *p; unsigned int i, total = 0, errors = 0; int err, ret = 0; mutex_lock(&kprobe_mutex); /* If kprobes are already disarmed, just return */ if (kprobes_all_disarmed) { mutex_unlock(&kprobe_mutex); return 0; } kprobes_all_disarmed = true; for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; /* Disarm all kprobes on a best-effort basis */ hlist_for_each_entry(p, head, hlist) { if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) { err = disarm_kprobe(p, false); if (err) { errors++; ret = err; } total++; } } } if (errors) pr_warn("Kprobes globally disabled, but failed to disarm %d out of %d probes\n", errors, total); else pr_info("Kprobes globally disabled\n"); mutex_unlock(&kprobe_mutex); /* Wait for disarming all kprobes by optimizer */ wait_for_kprobe_optimizer(); return ret; } /* * XXX: The debugfs bool file interface doesn't allow for callbacks * when the bool state is switched. We can reuse that facility when * available */ static ssize_t read_enabled_file_bool(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { char buf[3]; if (!kprobes_all_disarmed) buf[0] = '1'; else buf[0] = '0'; buf[1] = '\n'; buf[2] = 0x00; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); } static ssize_t write_enabled_file_bool(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { char buf[32]; size_t buf_size; int ret = 0; buf_size = min(count, (sizeof(buf)-1)); if (copy_from_user(buf, user_buf, buf_size)) return -EFAULT; buf[buf_size] = '\0'; switch (buf[0]) { case 'y': case 'Y': case '1': ret = arm_all_kprobes(); break; case 'n': case 'N': case '0': ret = disarm_all_kprobes(); break; default: return -EINVAL; } if (ret) return ret; return count; } static const struct file_operations fops_kp = { .read = read_enabled_file_bool, .write = write_enabled_file_bool, .llseek = default_llseek, }; static int __init debugfs_kprobe_init(void) { struct dentry *dir; dir = debugfs_create_dir("kprobes", NULL); debugfs_create_file("list", 0400, dir, NULL, &kprobes_fops); debugfs_create_file("enabled", 0600, dir, NULL, &fops_kp); debugfs_create_file("blacklist", 0400, dir, NULL, &kprobe_blacklist_fops); return 0; } late_initcall(debugfs_kprobe_init); #endif /* CONFIG_DEBUG_FS */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Filesystem access notification for Linux * * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #ifndef __LINUX_FSNOTIFY_BACKEND_H #define __LINUX_FSNOTIFY_BACKEND_H #ifdef __KERNEL__ #include <linux/idr.h> /* inotify uses this */ #include <linux/fs.h> /* struct inode */ #include <linux/list.h> #include <linux/path.h> /* struct path */ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/mempool.h> #include <linux/sched/mm.h> /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily * convert between them. dnotify only needs conversion at watch creation * so no perf loss there. fanotify isn't defined yet, so it can use the * wholes if it needs more events. */ #define FS_ACCESS 0x00000001 /* File was accessed */ #define FS_MODIFY 0x00000002 /* File was modified */ #define FS_ATTRIB 0x00000004 /* Metadata changed */ #define FS_CLOSE_WRITE 0x00000008 /* Writtable file was closed */ #define FS_CLOSE_NOWRITE 0x00000010 /* Unwrittable file closed */ #define FS_OPEN 0x00000020 /* File was opened */ #define FS_MOVED_FROM 0x00000040 /* File was moved from X */ #define FS_MOVED_TO 0x00000080 /* File was moved to Y */ #define FS_CREATE 0x00000100 /* Subfile was created */ #define FS_DELETE 0x00000200 /* Subfile was deleted */ #define FS_DELETE_SELF 0x00000400 /* Self was deleted */ #define FS_MOVE_SELF 0x00000800 /* Self was moved */ #define FS_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ #define FS_ERROR 0x00008000 /* Filesystem Error (fanotify) */ /* * FS_IN_IGNORED overloads FS_ERROR. It is only used internally by inotify * which does not support FS_ERROR. */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. * Set on inode/sb/mount marks that care about parent/name info. */ #define FS_EVENT_ON_CHILD 0x08000000 #define FS_RENAME 0x10000000 /* File was renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) /* * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ FS_OPEN_EXEC_PERM) /* * This is a list of all events that may get sent to a parent that is watching * with flag FS_EVENT_ON_CHILD based on fs event on a child of that directory. */ #define FS_EVENTS_POSS_ON_CHILD (ALL_FSNOTIFY_PERM_EVENTS | \ FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \ FS_OPEN | FS_OPEN_EXEC) /* * This is a list of all events that may get sent with the parent inode as the * @to_tell argument of fsnotify(). * It may include events that can be sent to an inode/sb/mount mark, but cannot * be sent to a parent watching children. */ #define FS_EVENTS_POSS_TO_PARENT (FS_EVENTS_POSS_ON_CHILD) /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_ISDIR | FS_EVENT_ON_CHILD | FS_DN_MULTISHOT) #define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark; struct fsnotify_event_private_data; struct fsnotify_fname; struct fsnotify_iter_info; struct mem_cgroup; /* * Each group much define these ops. The fsnotify infrastructure will call * these operations for each relevant group. * * handle_event - main call for a group to handle an fs event * @group: group to notify * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @cookie: inotify rename cookie * @iter_info: array of marks from this group that are interested in the event * * handle_inode_event - simple variant of handle_event() for groups that only * have inode marks and don't have ignore mask * @mark: mark to notify * @mask: event type and flags * @inode: inode that event happened on * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to. * Either @inode or @dir must be non-NULL. * @file_name: optional file name associated with event * @cookie: inotify rename cookie * * free_group_priv - called when a group refcnt hits 0 to clean up the private union * freeing_mark - called when a mark is being destroyed for some reason. The group * MUST be holding a reference on each mark and that reference must be * dropped in this function. inotify uses this function to send * userspace messages that marks have been removed. */ struct fsnotify_ops { int (*handle_event)(struct fsnotify_group *group, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info); int (*handle_inode_event)(struct fsnotify_mark *mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event); /* called on final put+free to free memory */ void (*free_mark)(struct fsnotify_mark *mark); }; /* * all of the information about the original object we want to now send to * a group. If you want to carry more info from the accessing task to the * listener this structure is where you need to be adding fields. */ struct fsnotify_event { struct list_head list; }; /* * A group is a "thing" that wants to receive notification about filesystem * events. The mask holds the subset of event types this group cares about. * refcnt on a group is up to the implementor and at any moment if it goes 0 * everything will be cleaned up. */ struct fsnotify_group { const struct fsnotify_ops *ops; /* how this group handles things */ /* * How the refcnt is used is up to each group. When the refcnt hits 0 * fsnotify will clean up all of the resources associated with this group. * As an example, the dnotify group will always have a refcnt=1 and that * will never change. Inotify, on the other hand, has a group per * inotify_init() and the refcnt will hit 0 only when that fd has been * closed. */ refcount_t refcnt; /* things with interest in this group */ /* needed to send notification to userspace */ spinlock_t notification_lock; /* protect the notification_list */ struct list_head notification_list; /* list of event_holder this group needs to send to userspace */ wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */ unsigned int q_len; /* events on the queue */ unsigned int max_events; /* maximum events allowed on the list */ /* * Valid fsnotify group priorities. Events are send in order from highest * priority to lowest priority. We default to the lowest priority. */ #define FS_PRIO_0 0 /* normal notifiers, no permissions */ #define FS_PRIO_1 1 /* fanotify content based access control */ #define FS_PRIO_2 2 /* fanotify pre-content access */ unsigned int priority; bool shutdown; /* group is being shut down, don't queue more events */ #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ #define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ #define FSNOTIFY_GROUP_NOFS 0x04 /* group lock is not direct reclaim safe */ int flags; unsigned int owner_flags; /* stored flags of mark_mutex owner */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ atomic_t user_waits; /* Number of tasks waiting for user * response */ struct list_head marks_list; /* all inode marks for this group */ struct fasync_struct *fsn_fa; /* async notification */ struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ struct mem_cgroup *memcg; /* memcg to charge allocations */ /* groups can define private fields here or use the void *private */ union { void *private; #ifdef CONFIG_INOTIFY_USER struct inotify_group_private_data { spinlock_t idr_lock; struct idr idr; struct ucounts *ucounts; } inotify_data; #endif #ifdef CONFIG_FANOTIFY struct fanotify_group_private_data { /* Hash table of events for merge */ struct hlist_head *merge_hash; /* allows a group to block waiting for a userspace response */ struct list_head access_list; wait_queue_head_t access_waitq; int flags; /* flags from fanotify_init() */ int f_flags; /* event_f_flags from fanotify_init() */ struct ucounts *ucounts; mempool_t error_events_pool; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; }; /* * These helpers are used to prevent deadlock when reclaiming inodes with * evictable marks of the same group that is allocating a new mark. */ static inline void fsnotify_group_lock(struct fsnotify_group *group) { mutex_lock(&group->mark_mutex); if (group->flags & FSNOTIFY_GROUP_NOFS) group->owner_flags = memalloc_nofs_save(); } static inline void fsnotify_group_unlock(struct fsnotify_group *group) { if (group->flags & FSNOTIFY_GROUP_NOFS) memalloc_nofs_restore(group->owner_flags); mutex_unlock(&group->mark_mutex); } static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) { WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); if (group->flags & FSNOTIFY_GROUP_NOFS) WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, FSNOTIFY_EVENT_ERROR, }; struct fs_error_report { int error; struct inode *inode; struct super_block *sb; }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return (struct inode *)data; case FSNOTIFY_EVENT_DENTRY: return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *)data)->inode; default: return NULL; } } static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_DENTRY: /* Non const is needed for dget() */ return (struct dentry *)data; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry; default: return NULL; } } static inline const struct path *fsnotify_data_path(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_PATH: return data; default: return NULL; } } static inline struct super_block *fsnotify_data_sb(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return ((struct inode *)data)->i_sb; case FSNOTIFY_EVENT_DENTRY: return ((struct dentry *)data)->d_sb; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry->d_sb; case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *) data)->sb; default: return NULL; } } static inline struct fs_error_report *fsnotify_data_error_report( const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_ERROR: return (struct fs_error_report *) data; default: return NULL; } } /* * Index to merged marks iterator array that correlates to a type of watch. * The type of watched object can be deduced from the iterator type, but not * the other way around, because an event can match different watched objects * of the same object type. * For example, both parent and child are watching an object of type inode. */ enum fsnotify_iter_type { FSNOTIFY_ITER_TYPE_INODE, FSNOTIFY_ITER_TYPE_VFSMOUNT, FSNOTIFY_ITER_TYPE_SB, FSNOTIFY_ITER_TYPE_PARENT, FSNOTIFY_ITER_TYPE_INODE2, FSNOTIFY_ITER_TYPE_COUNT }; /* The type of object that a mark is attached to */ enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_ANY = -1, FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; static inline bool fsnotify_valid_obj_type(unsigned int obj_type) { return (obj_type < FSNOTIFY_OBJ_TYPE_COUNT); } struct fsnotify_iter_info { struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT]; struct fsnotify_group *current_group; unsigned int report_mask; int srcu_idx; }; static inline bool fsnotify_iter_should_report_type( struct fsnotify_iter_info *iter_info, int iter_type) { return (iter_info->report_mask & (1U << iter_type)); } static inline void fsnotify_iter_set_report_type( struct fsnotify_iter_info *iter_info, int iter_type) { iter_info->report_mask |= (1U << iter_type); } static inline struct fsnotify_mark *fsnotify_iter_mark( struct fsnotify_iter_info *iter_info, int iter_type) { if (fsnotify_iter_should_report_type(iter_info, iter_type)) return iter_info->marks[iter_type]; return NULL; } static inline int fsnotify_iter_step(struct fsnotify_iter_info *iter, int type, struct fsnotify_mark **markp) { while (type < FSNOTIFY_ITER_TYPE_COUNT) { *markp = fsnotify_iter_mark(iter, type); if (*markp) break; type++; } return type; } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ return fsnotify_iter_mark(iter_info, FSNOTIFY_ITER_TYPE_##NAME); \ } FSNOTIFY_ITER_FUNCS(inode, INODE) FSNOTIFY_ITER_FUNCS(parent, PARENT) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_iter_type(type) \ for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++) #define fsnotify_foreach_iter_mark_type(iter, mark, type) \ for (type = 0; \ type = fsnotify_iter_step(iter, type, &mark), \ type < FSNOTIFY_ITER_TYPE_COUNT; \ type++) /* * fsnotify_connp_t is what we embed in objects which connector can be attached * to. fsnotify_connp_t * is how we refer from connector back to object. */ struct fsnotify_mark_connector; typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; /* * Inode/vfsmount/sb point to this structure which tracks all marks attached to * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached * to it. The structure is protected by fsnotify_mark_srcu. */ struct fsnotify_mark_connector { spinlock_t lock; unsigned short type; /* Type of object [lock] */ #define FSNOTIFY_CONN_FLAG_HAS_FSID 0x01 #define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ __kernel_fsid_t fsid; /* fsid of filesystem containing object */ union { /* Object pointer [lock] */ fsnotify_connp_t *obj; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; struct hlist_head list; }; /* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. * * These are flushed when an inode is evicted from core and may be flushed * when the inode is modified (as seen by fsnotify_access). Some fsnotify * users (such as dnotify) will flush these when the open fd is closed and not * at inode eviction or modification. * * Text in brackets is showing the lock(s) protecting modifications of a * particular entry. obj_lock means either inode->i_lock or * mnt->mnt_root->d_lock depending on the mark type. */ struct fsnotify_mark { /* Mask this mark is for [mark->lock, group->mark_mutex] */ __u32 mask; /* We hold one for presence in g_list. Also one ref for each 'thing' * in kernel that found and may be using this mark. */ refcount_t refcnt; /* Group this mark is for. Set on mark creation, stable until last ref * is dropped */ struct fsnotify_group *group; /* List of marks by group->marks_list. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ struct list_head g_list; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; /* List of marks for inode / vfsmount [connector->lock, mark ref] */ struct hlist_node obj_list; /* Head of list of marks for an object [mark ref] */ struct fsnotify_mark_connector *connector; /* Events types and flags to ignore [mark->lock, group->mark_mutex] */ __u32 ignore_mask; /* General fsnotify mark flags */ #define FSNOTIFY_MARK_FLAG_ALIVE 0x0001 #define FSNOTIFY_MARK_FLAG_ATTACHED 0x0002 /* inotify mark flags */ #define FSNOTIFY_MARK_FLAG_EXCL_UNLINK 0x0010 #define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020 /* fanotify mark flags */ #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 #define FSNOTIFY_MARK_FLAG_NO_IREF 0x0200 #define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS 0x0400 unsigned int flags; /* flags [mark->lock] */ }; #ifdef CONFIG_FSNOTIFY /* called from the vfs helpers */ /* main fsnotify call to send events */ extern int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie); extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern void fsnotify_sb_delete(struct super_block *sb); extern u32 fsnotify_get_cookie(void); static inline __u32 fsnotify_parent_needed_mask(__u32 mask) { /* FS_EVENT_ON_CHILD is set on marks that want parent/name info */ if (!(mask & FS_EVENT_ON_CHILD)) return 0; /* * This object might be watched by a mark that cares about parent/name * info, does it care about the specific set of events that can be * reported with parent/name info? */ return mask & FS_EVENTS_POSS_TO_PARENT; } static inline int fsnotify_inode_watches_children(struct inode *inode) { __u32 parent_mask = READ_ONCE(inode->i_fsnotify_mask); /* FS_EVENT_ON_CHILD is set if the inode may care */ if (!(parent_mask & FS_EVENT_ON_CHILD)) return 0; /* this inode might care about child events, does it care about the * specific set of events that can happen on a child? */ return parent_mask & FS_EVENTS_POSS_ON_CHILD; } /* * Update the dentry with a flag indicating the interest of its parent to receive * filesystem events when those events happens to this dentry->d_inode. */ static inline void fsnotify_update_flags(struct dentry *dentry) { assert_spin_locked(&dentry->d_lock); /* * Serialisation of setting PARENT_WATCHED on the dentries is provided * by d_lock. If inotify_inode_watched changes after we have taken * d_lock, the following fsnotify_set_children_dentry_flags call will * find our entry, so it will spin until we complete here, and update * us with the new state. */ if (fsnotify_inode_watches_children(dentry->d_parent->d_inode)) dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; else dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; } /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ extern struct fsnotify_group *fsnotify_alloc_group( const struct fsnotify_ops *ops, int flags); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); /* group destruction begins, stop queuing new events */ extern void fsnotify_group_stop_queueing(struct fsnotify_group *group); /* destroy group */ extern void fsnotify_destroy_group(struct fsnotify_group *group); /* fasync handler function */ extern int fsnotify_fasync(int fd, struct file *file, int on); /* Free event from memory */ extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ extern int fsnotify_insert_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *), void (*insert)(struct fsnotify_group *, struct fsnotify_event *)); static inline int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *)) { return fsnotify_insert_event(group, event, merge, NULL); } /* Queue overflow event to a notification group */ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) { fsnotify_add_event(group, group->overflow_event, NULL); } static inline bool fsnotify_is_overflow_event(u32 mask) { return mask & FS_Q_OVERFLOW; } static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group) { assert_spin_locked(&group->notification_lock); return list_empty(&group->notification_list); } extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group); /* return AND dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group); /* Remove event queued in the notification list */ extern void fsnotify_remove_queued_event(struct fsnotify_group *group, struct fsnotify_event *event); /* functions used to manipulate the marks attached to inodes */ /* * Canonical "ignore mask" including event flags. * * Note the subtle semantic difference from the legacy ->ignored_mask. * ->ignored_mask traditionally only meant which events should be ignored, * while ->ignore_mask also includes flags regarding the type of objects on * which events should be ignored. */ static inline __u32 fsnotify_ignore_mask(struct fsnotify_mark *mark) { __u32 ignore_mask = mark->ignore_mask; /* The event flags in ignore mask take effect */ if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS) return ignore_mask; /* * Legacy behavior: * - Always ignore events on dir * - Ignore events on child if parent is watching children */ ignore_mask |= FS_ISDIR; ignore_mask &= ~FS_EVENT_ON_CHILD; ignore_mask |= mark->mask & FS_EVENT_ON_CHILD; return ignore_mask; } /* Legacy ignored_mask - only event types to ignore */ static inline __u32 fsnotify_ignored_events(struct fsnotify_mark *mark) { return mark->ignore_mask & ALL_FSNOTIFY_EVENTS; } /* * Check if mask (or ignore mask) should be applied depending if victim is a * directory and whether it is reported to a watching parent. */ static inline bool fsnotify_mask_applicable(__u32 mask, bool is_dir, int iter_type) { /* Should mask be applied to a directory? */ if (is_dir && !(mask & FS_ISDIR)) return false; /* Should mask be applied to a child? */ if (iter_type == FSNOTIFY_ITER_TYPE_PARENT && !(mask & FS_EVENT_ON_CHILD)) return false; return true; } /* * Effective ignore mask taking into account if event victim is a * directory and whether it is reported to a watching parent. */ static inline __u32 fsnotify_effective_ignore_mask(struct fsnotify_mark *mark, bool is_dir, int iter_type) { __u32 ignore_mask = fsnotify_ignored_events(mark); if (!ignore_mask) return 0; /* For non-dir and non-child, no need to consult the event flags */ if (!is_dir && iter_type != FSNOTIFY_ITER_TYPE_PARENT) return ignore_mask; ignore_mask = fsnotify_ignore_mask(mark); if (!fsnotify_mask_applicable(ignore_mask, is_dir, iter_type)) return 0; return ignore_mask & ALL_FSNOTIFY_EVENTS; } /* Get mask for calculating object interest taking ignore mask into account */ static inline __u32 fsnotify_calc_mask(struct fsnotify_mark *mark) { __u32 mask = mark->mask; if (!fsnotify_ignored_events(mark)) return mask; /* Interest in FS_MODIFY may be needed for clearing ignore mask */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) mask |= FS_MODIFY; /* * If mark is interested in ignoring events on children, the object must * show interest in those events for fsnotify_parent() to notice it. */ return mask | mark->ignore_mask; } /* Get mask of events for a list of marks */ extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); extern void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* Find mark belonging to given group in the list of marks */ extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, struct fsnotify_group *group); /* Get cached fsid of filesystem containing object */ extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn, __kernel_fsid_t *fsid); /* attach the mark to the object */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, unsigned int obj_type, int add_flags, __kernel_fsid_t *fsid); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark(mark, &inode->i_fsnotify_marks, FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks, FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL); } /* given a group and a mark, flag mark to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* detach mark from inode / mount list, group list, drop inode reference */ extern void fsnotify_detach_mark(struct fsnotify_mark *mark); /* free mark */ extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); /* Clear all of the marks of a group attached to a given object type */ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type); /* run all the marks in a group, and clear all of the vfsmount marks */ static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT); } /* run all the marks in a group, and clear all of the inode marks */ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE); } /* run all the marks in a group, and clear all of the sn marks */ static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB); } extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); static inline void fsnotify_init_event(struct fsnotify_event *event) { INIT_LIST_HEAD(&event->list); } #else static inline int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie) { return 0; } static inline int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { return 0; } static inline void __fsnotify_inode_delete(struct inode *inode) {} static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) {} static inline void fsnotify_sb_delete(struct super_block *sb) {} static inline void fsnotify_update_flags(struct dentry *dentry) {} static inline u32 fsnotify_get_cookie(void) { return 0; } static inline void fsnotify_unmount_inodes(struct super_block *sb) {} #endif /* CONFIG_FSNOTIFY */ #endif /* __KERNEL __ */ #endif /* __LINUX_FSNOTIFY_BACKEND_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swap.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds */ /* * This file contains the default values for the operation of the * Linux VM subsystem. Fine-tuning documentation can be found in * Documentation/admin-guide/sysctl/vm.rst. * Started 18.12.91 * Swap aging added 23.2.95, Stephen Tweedie. * Buffermem limits added 12.3.98, Rik van Riel. */ #include <linux/mm.h> #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mm_inline.h> #include <linux/percpu_counter.h> #include <linux/memremap.h> #include <linux/percpu.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/backing-dev.h> #include <linux/memcontrol.h> #include <linux/gfp.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/page_idle.h> #include <linux/local_lock.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/pagemap.h> /* How many pages do we try to swap or page in/out together? */ int page_cluster; /* Protecting only lru_rotate.pvec which requires disabling interrupts */ struct lru_rotate { local_lock_t lock; struct pagevec pvec; }; static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = { .lock = INIT_LOCAL_LOCK(lock), }; /* * The following struct pagevec are grouped together because they are protected * by disabling preemption (and interrupts remain enabled). */ struct lru_pvecs { local_lock_t lock; struct pagevec lru_add; struct pagevec lru_deactivate_file; struct pagevec lru_deactivate; struct pagevec lru_lazyfree; #ifdef CONFIG_SMP struct pagevec activate_page; #endif }; static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = { .lock = INIT_LOCAL_LOCK(lock), }; /* * This path almost never happens for VM activity - pages are normally * freed via pagevecs. But it gets used by networking. */ static void __page_cache_release(struct page *page) { if (PageLRU(page)) { pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; unsigned long flags; spin_lock_irqsave(&pgdat->lru_lock, flags); lruvec = mem_cgroup_page_lruvec(page, pgdat); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); spin_unlock_irqrestore(&pgdat->lru_lock, flags); } __ClearPageWaiters(page); } static void __put_single_page(struct page *page) { __page_cache_release(page); mem_cgroup_uncharge(page); free_unref_page(page); } static void __put_compound_page(struct page *page) { /* * __page_cache_release() is supposed to be called for thp, not for * hugetlb. This is because hugetlb page does never have PageLRU set * (it's never listed to any LRU lists) and no memcg routines should * be called for hugetlb (it has a separate hugetlb_cgroup.) */ if (!PageHuge(page)) __page_cache_release(page); destroy_compound_page(page); } void __put_page(struct page *page) { if (is_zone_device_page(page)) { put_dev_pagemap(page->pgmap); /* * The page belongs to the device that created pgmap. Do * not return it to page allocator. */ return; } if (unlikely(PageCompound(page))) __put_compound_page(page); else __put_single_page(page); } EXPORT_SYMBOL(__put_page); /** * put_pages_list() - release a list of pages * @pages: list of pages threaded on page->lru * * Release a list of pages which are strung together on page.lru. Currently * used by read_cache_pages() and related error recovery code. */ void put_pages_list(struct list_head *pages) { while (!list_empty(pages)) { struct page *victim; victim = lru_to_page(pages); list_del(&victim->lru); put_page(victim); } } EXPORT_SYMBOL(put_pages_list); /* * get_kernel_pages() - pin kernel pages in memory * @kiov: An array of struct kvec structures * @nr_segs: number of segments to pin * @write: pinning for read/write, currently ignored * @pages: array that receives pointers to the pages pinned. * Should be at least nr_segs long. * * Returns number of pages pinned. This may be fewer than the number * requested. If nr_pages is 0 or negative, returns 0. If no pages * were pinned, returns -errno. Each page returned must be released * with a put_page() call when it is finished with. */ int get_kernel_pages(const struct kvec *kiov, int nr_segs, int write, struct page **pages) { int seg; for (seg = 0; seg < nr_segs; seg++) { if (WARN_ON(kiov[seg].iov_len != PAGE_SIZE)) return seg; pages[seg] = kmap_to_page(kiov[seg].iov_base); get_page(pages[seg]); } return seg; } EXPORT_SYMBOL_GPL(get_kernel_pages); /* * get_kernel_page() - pin a kernel page in memory * @start: starting kernel address * @write: pinning for read/write, currently ignored * @pages: array that receives pointer to the page pinned. * Must be at least nr_segs long. * * Returns 1 if page is pinned. If the page was not pinned, returns * -errno. The page returned must be released with a put_page() call * when it is finished with. */ int get_kernel_page(unsigned long start, int write, struct page **pages) { const struct kvec kiov = { .iov_base = (void *)start, .iov_len = PAGE_SIZE }; return get_kernel_pages(&kiov, 1, write, pages); } EXPORT_SYMBOL_GPL(get_kernel_page); static void pagevec_lru_move_fn(struct pagevec *pvec, void (*move_fn)(struct page *page, struct lruvec *lruvec, void *arg), void *arg) { int i; struct pglist_data *pgdat = NULL; struct lruvec *lruvec; unsigned long flags = 0; for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; struct pglist_data *pagepgdat = page_pgdat(page); if (pagepgdat != pgdat) { if (pgdat) spin_unlock_irqrestore(&pgdat->lru_lock, flags); pgdat = pagepgdat; spin_lock_irqsave(&pgdat->lru_lock, flags); } lruvec = mem_cgroup_page_lruvec(page, pgdat); (*move_fn)(page, lruvec, arg); } if (pgdat) spin_unlock_irqrestore(&pgdat->lru_lock, flags); release_pages(pvec->pages, pvec->nr); pagevec_reinit(pvec); } static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec, void *arg) { int *pgmoved = arg; if (PageLRU(page) && !PageUnevictable(page)) { del_page_from_lru_list(page, lruvec, page_lru(page)); ClearPageActive(page); add_page_to_lru_list_tail(page, lruvec, page_lru(page)); (*pgmoved) += thp_nr_pages(page); } } /* * pagevec_move_tail() must be called with IRQ disabled. * Otherwise this may cause nasty races. */ static void pagevec_move_tail(struct pagevec *pvec) { int pgmoved = 0; pagevec_lru_move_fn(pvec, pagevec_move_tail_fn, &pgmoved); __count_vm_events(PGROTATED, pgmoved); } /* * Writeback is about to end against a page which has been marked for immediate * reclaim. If it still appears to be reclaimable, move it to the tail of the * inactive list. */ void rotate_reclaimable_page(struct page *page) { if (!PageLocked(page) && !PageDirty(page) && !PageUnevictable(page) && PageLRU(page)) { struct pagevec *pvec; unsigned long flags; get_page(page); local_lock_irqsave(&lru_rotate.lock, flags); pvec = this_cpu_ptr(&lru_rotate.pvec); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_move_tail(pvec); local_unlock_irqrestore(&lru_rotate.lock, flags); } } void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) { do { unsigned long lrusize; /* Record cost event */ if (file) lruvec->file_cost += nr_pages; else lruvec->anon_cost += nr_pages; /* * Decay previous events * * Because workloads change over time (and to avoid * overflow) we keep these statistics as a floating * average, which ends up weighing recent refaults * more than old ones. */ lrusize = lruvec_page_state(lruvec, NR_INACTIVE_ANON) + lruvec_page_state(lruvec, NR_ACTIVE_ANON) + lruvec_page_state(lruvec, NR_INACTIVE_FILE) + lruvec_page_state(lruvec, NR_ACTIVE_FILE); if (lruvec->file_cost + lruvec->anon_cost > lrusize / 4) { lruvec->file_cost /= 2; lruvec->anon_cost /= 2; } } while ((lruvec = parent_lruvec(lruvec))); } void lru_note_cost_page(struct page *page) { lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)), page_is_file_lru(page), thp_nr_pages(page)); } static void __activate_page(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { int lru = page_lru_base_type(page); int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec, lru); SetPageActive(page); lru += LRU_ACTIVE; add_page_to_lru_list(page, lruvec, lru); trace_mm_lru_activate(page); __count_vm_events(PGACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages); } } #ifdef CONFIG_SMP static void activate_page_drain(int cpu) { struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, __activate_page, NULL); } static bool need_activate_page_drain(int cpu) { return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0; } static void activate_page(struct page *page) { page = compound_head(page); if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.activate_page); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, __activate_page, NULL); local_unlock(&lru_pvecs.lock); } } #else static inline void activate_page_drain(int cpu) { } static void activate_page(struct page *page) { pg_data_t *pgdat = page_pgdat(page); page = compound_head(page); spin_lock_irq(&pgdat->lru_lock); __activate_page(page, mem_cgroup_page_lruvec(page, pgdat), NULL); spin_unlock_irq(&pgdat->lru_lock); } #endif static void __lru_cache_activate_page(struct page *page) { struct pagevec *pvec; int i; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); /* * Search backwards on the optimistic assumption that the page being * activated has just been added to this pagevec. Note that only * the local pagevec is examined as a !PageLRU page could be in the * process of being released, reclaimed, migrated or on a remote * pagevec that is currently being drained. Furthermore, marking * a remote pagevec's page PageActive potentially hits a race where * a page is marked PageActive just after it is added to the inactive * list causing accounting errors and BUG_ON checks to trigger. */ for (i = pagevec_count(pvec) - 1; i >= 0; i--) { struct page *pagevec_page = pvec->pages[i]; if (pagevec_page == page) { SetPageActive(page); break; } } local_unlock(&lru_pvecs.lock); } /* * Mark a page as having seen activity. * * inactive,unreferenced -> inactive,referenced * inactive,referenced -> active,unreferenced * active,unreferenced -> active,referenced * * When a newly allocated page is not yet visible, so safe for non-atomic ops, * __SetPageReferenced(page) may be substituted for mark_page_accessed(page). */ void mark_page_accessed(struct page *page) { page = compound_head(page); if (!PageReferenced(page)) { SetPageReferenced(page); } else if (PageUnevictable(page)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * evictable page accessed has no effect. */ } else if (!PageActive(page)) { /* * If the page is on the LRU, queue it for activation via * lru_pvecs.activate_page. Otherwise, assume the page is on a * pagevec, mark it active and it'll be moved to the active * LRU on the next drain. */ if (PageLRU(page)) activate_page(page); else __lru_cache_activate_page(page); ClearPageReferenced(page); workingset_activation(page); } if (page_is_idle(page)) clear_page_idle(page); } EXPORT_SYMBOL(mark_page_accessed); /** * lru_cache_add - add a page to a page list * @page: the page to be added to the LRU. * * Queue the page for addition to the LRU via pagevec. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the * pagevec is drained. This gives a chance for the caller of lru_cache_add() * have the page added to the active list using mark_page_accessed(). */ void lru_cache_add(struct page *page) { struct pagevec *pvec; VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); VM_BUG_ON_PAGE(PageLRU(page), page); get_page(page); local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); if (!pagevec_add(pvec, page) || PageCompound(page)) __pagevec_lru_add(pvec); local_unlock(&lru_pvecs.lock); } EXPORT_SYMBOL(lru_cache_add); /** * lru_cache_add_inactive_or_unevictable * @page: the page to be added to LRU * @vma: vma in which page is mapped for determining reclaimability * * Place @page on the inactive or unevictable LRU list, depending on its * evictability. */ void lru_cache_add_inactive_or_unevictable(struct page *page, struct vm_area_struct *vma) { bool unevictable; VM_BUG_ON_PAGE(PageLRU(page), page); unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED; if (unlikely(unevictable) && !TestSetPageMlocked(page)) { int nr_pages = thp_nr_pages(page); /* * We use the irq-unsafe __mod_zone_page_stat because this * counter is not modified from interrupt context, and the pte * lock is held(spinlock), which implies preemption disabled. */ __mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages); count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages); } lru_cache_add(page); } /* * If the page can not be invalidated, it is moved to the * inactive list to speed up its reclaim. It is moved to the * head of the list, rather than the tail, to give the flusher * threads some time to write it out, as this is much more * effective than the single-page writeout from reclaim. * * If the page isn't page_mapped and dirty/writeback, the page * could reclaim asap using PG_reclaim. * * 1. active, mapped page -> none * 2. active, dirty/writeback page -> inactive, head, PG_reclaim * 3. inactive, mapped page -> none * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim * 5. inactive, clean -> inactive, tail * 6. Others -> none * * In 4, why it moves inactive's head, the VM expects the page would * be write it out by flusher threads as this is much more effective * than the single-page writeout from reclaim. */ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, void *arg) { int lru; bool active; int nr_pages = thp_nr_pages(page); if (!PageLRU(page)) return; if (PageUnevictable(page)) return; /* Some processes are using the page */ if (page_mapped(page)) return; active = PageActive(page); lru = page_lru_base_type(page); del_page_from_lru_list(page, lruvec, lru + active); ClearPageActive(page); ClearPageReferenced(page); if (PageWriteback(page) || PageDirty(page)) { /* * PG_reclaim could be raced with end_page_writeback * It can make readahead confusing. But race window * is _really_ small and it's non-critical problem. */ add_page_to_lru_list(page, lruvec, lru); SetPageReclaim(page); } else { /* * The page's writeback ends up during pagevec * We moves tha page into tail of inactive. */ add_page_to_lru_list_tail(page, lruvec, lru); __count_vm_events(PGROTATED, nr_pages); } if (active) { __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { int lru = page_lru_base_type(page); int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); ClearPageActive(page); ClearPageReferenced(page); add_page_to_lru_list(page, lruvec, lru); __count_vm_events(PGDEACTIVATE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages); } } static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page) && !PageUnevictable(page)) { bool active = PageActive(page); int nr_pages = thp_nr_pages(page); del_page_from_lru_list(page, lruvec, LRU_INACTIVE_ANON + active); ClearPageActive(page); ClearPageReferenced(page); /* * Lazyfree pages are clean anonymous pages. They have * PG_swapbacked flag cleared, to distinguish them from normal * anonymous pages */ ClearPageSwapBacked(page); add_page_to_lru_list(page, lruvec, LRU_INACTIVE_FILE); __count_vm_events(PGLAZYFREE, nr_pages); __count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages); } } /* * Drain pages out of the cpu's pagevecs. * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ void lru_add_drain_cpu(int cpu) { struct pagevec *pvec = &per_cpu(lru_pvecs.lru_add, cpu); if (pagevec_count(pvec)) __pagevec_lru_add(pvec); pvec = &per_cpu(lru_rotate.pvec, cpu); /* Disabling interrupts below acts as a compiler barrier. */ if (data_race(pagevec_count(pvec))) { unsigned long flags; /* No harm done if a racing interrupt already did this */ local_lock_irqsave(&lru_rotate.lock, flags); pagevec_move_tail(pvec); local_unlock_irqrestore(&lru_rotate.lock, flags); } pvec = &per_cpu(lru_pvecs.lru_deactivate_file, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); pvec = &per_cpu(lru_pvecs.lru_deactivate, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); pvec = &per_cpu(lru_pvecs.lru_lazyfree, cpu); if (pagevec_count(pvec)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); activate_page_drain(cpu); } /** * deactivate_file_page - forcefully deactivate a file page * @page: page to deactivate * * This function hints the VM that @page is a good reclaim candidate, * for example if its invalidation fails due to the page being dirty * or under writeback. */ void deactivate_file_page(struct page *page) { /* * In a workload with many unevictable page such as mprotect, * unevictable page deactivation for accelerating reclaim is pointless. */ if (PageUnevictable(page)) return; if (likely(get_page_unless_zero(page))) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); local_unlock(&lru_pvecs.lock); } } /* * deactivate_page - deactivate a page * @page: page to deactivate * * deactivate_page() moves @page to the inactive list if @page was on the active * list and was not an unevictable page. This is done to accelerate the reclaim * of @page. */ void deactivate_page(struct page *page) { if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL); local_unlock(&lru_pvecs.lock); } } /** * mark_page_lazyfree - make an anon page lazyfree * @page: page to deactivate * * mark_page_lazyfree() moves @page to the inactive file list. * This is done to accelerate the reclaim of @page. */ void mark_page_lazyfree(struct page *page) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && !PageSwapCache(page) && !PageUnevictable(page)) { struct pagevec *pvec; local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree); get_page(page); if (!pagevec_add(pvec, page) || PageCompound(page)) pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); local_unlock(&lru_pvecs.lock); } } void lru_add_drain(void) { local_lock(&lru_pvecs.lock); lru_add_drain_cpu(smp_processor_id()); local_unlock(&lru_pvecs.lock); } void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&lru_pvecs.lock); lru_add_drain_cpu(smp_processor_id()); drain_local_pages(zone); local_unlock(&lru_pvecs.lock); } #ifdef CONFIG_SMP static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_drain(); } /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is * executed on the offlined cpu. * Calling this function with cpu hotplug locks held can actually lead * to obscure indirect dependencies via WQ context. */ void lru_add_drain_all(void) { /* * lru_drain_gen - Global pages generation number * * (A) Definition: global lru_drain_gen = x implies that all generations * 0 < n <= x are already *scheduled* for draining. * * This is an optimization for the highly-contended use case where a * user space workload keeps constantly generating a flow of pages for * each CPU. */ static unsigned int lru_drain_gen; static struct cpumask has_work; static DEFINE_MUTEX(lock); unsigned cpu, this_gen; /* * Make sure nobody triggers this path before mm_percpu_wq is fully * initialized. */ if (WARN_ON(!mm_percpu_wq)) return; /* * Guarantee pagevec counter stores visible by this CPU are visible to * other CPUs before loading the current drain generation. */ smp_mb(); /* * (B) Locally cache global LRU draining generation number * * The read barrier ensures that the counter is loaded before the mutex * is taken. It pairs with smp_mb() inside the mutex critical section * at (D). */ this_gen = smp_load_acquire(&lru_drain_gen); mutex_lock(&lock); /* * (C) Exit the draining operation if a newer generation, from another * lru_add_drain_all(), was already scheduled for draining. Check (A). */ if (unlikely(this_gen != lru_drain_gen)) goto done; /* * (D) Increment global generation number * * Pairs with smp_load_acquire() at (B), outside of the critical * section. Use a full memory barrier to guarantee that the new global * drain generation number is stored before loading pagevec counters. * * This pairing must be done here, before the for_each_online_cpu loop * below which drains the page vectors. * * Let x, y, and z represent some system CPU numbers, where x < y < z. * Assume CPU #z is is in the middle of the for_each_online_cpu loop * below and has already reached CPU #y's per-cpu data. CPU #x comes * along, adds some pages to its per-cpu vectors, then calls * lru_add_drain_all(). * * If the paired barrier is done at any later step, e.g. after the * loop, CPU #x will just exit at (C) and miss flushing out all of its * added pages. */ WRITE_ONCE(lru_drain_gen, lru_drain_gen + 1); smp_mb(); cpumask_clear(&has_work); for_each_online_cpu(cpu) { struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); if (pagevec_count(&per_cpu(lru_pvecs.lru_add, cpu)) || data_race(pagevec_count(&per_cpu(lru_rotate.pvec, cpu))) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_deactivate, cpu)) || pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree, cpu)) || need_activate_page_drain(cpu)) { INIT_WORK(work, lru_add_drain_per_cpu); queue_work_on(cpu, mm_percpu_wq, work); __cpumask_set_cpu(cpu, &has_work); } } for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); done: mutex_unlock(&lock); } #else void lru_add_drain_all(void) { lru_add_drain(); } #endif /* CONFIG_SMP */ /** * release_pages - batched put_page() * @pages: array of pages to release * @nr: number of pages * * Decrement the reference count on all the pages in @pages. If it * fell to zero, remove the page from the LRU and free it. */ void release_pages(struct page **pages, int nr) { int i; LIST_HEAD(pages_to_free); struct pglist_data *locked_pgdat = NULL; struct lruvec *lruvec; unsigned long flags; unsigned int lock_batch; for (i = 0; i < nr; i++) { struct page *page = pages[i]; /* * Make sure the IRQ-safe lock-holding time does not get * excessive with a continuous string of pages from the * same pgdat. The lock is held only if pgdat != NULL. */ if (locked_pgdat && ++lock_batch == SWAP_CLUSTER_MAX) { spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); locked_pgdat = NULL; } page = compound_head(page); if (is_huge_zero_page(page)) continue; if (is_zone_device_page(page)) { if (locked_pgdat) { spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); locked_pgdat = NULL; } /* * ZONE_DEVICE pages that return 'false' from * page_is_devmap_managed() do not require special * processing, and instead, expect a call to * put_page_testzero(). */ if (page_is_devmap_managed(page)) { put_devmap_managed_page(page); continue; } } if (!put_page_testzero(page)) continue; if (PageCompound(page)) { if (locked_pgdat) { spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); locked_pgdat = NULL; } __put_compound_page(page); continue; } if (PageLRU(page)) { struct pglist_data *pgdat = page_pgdat(page); if (pgdat != locked_pgdat) { if (locked_pgdat) spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); lock_batch = 0; locked_pgdat = pgdat; spin_lock_irqsave(&locked_pgdat->lru_lock, flags); } lruvec = mem_cgroup_page_lruvec(page, locked_pgdat); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); } __ClearPageWaiters(page); list_add(&page->lru, &pages_to_free); } if (locked_pgdat) spin_unlock_irqrestore(&locked_pgdat->lru_lock, flags); mem_cgroup_uncharge_list(&pages_to_free); free_unref_page_list(&pages_to_free); } EXPORT_SYMBOL(release_pages); /* * The pages which we're about to release may be in the deferred lru-addition * queues. That would prevent them from really being freed right now. That's * OK from a correctness point of view but is inefficient - those pages may be * cache-warm and we want to give them back to the page allocator ASAP. * * So __pagevec_release() will drain those queues here. __pagevec_lru_add() * and __pagevec_lru_add_active() call release_pages() directly to avoid * mutual recursion. */ void __pagevec_release(struct pagevec *pvec) { if (!pvec->percpu_pvec_drained) { lru_add_drain(); pvec->percpu_pvec_drained = true; } release_pages(pvec->pages, pagevec_count(pvec)); pagevec_reinit(pvec); } EXPORT_SYMBOL(__pagevec_release); #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* used by __split_huge_page_refcount() */ void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *list) { VM_BUG_ON_PAGE(!PageHead(page), page); VM_BUG_ON_PAGE(PageCompound(page_tail), page); VM_BUG_ON_PAGE(PageLRU(page_tail), page); lockdep_assert_held(&lruvec_pgdat(lruvec)->lru_lock); if (!list) SetPageLRU(page_tail); if (likely(PageLRU(page))) list_add_tail(&page_tail->lru, &page->lru); else if (list) { /* page reclaim is reclaiming a huge page */ get_page(page_tail); list_add_tail(&page_tail->lru, list); } else { /* * Head page has not yet been counted, as an hpage, * so we must account for each subpage individually. * * Put page_tail on the list at the correct position * so they all end up in order. */ add_page_to_lru_list_tail(page_tail, lruvec, page_lru(page_tail)); } } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, void *arg) { enum lru_list lru; int was_unevictable = TestClearPageUnevictable(page); int nr_pages = thp_nr_pages(page); VM_BUG_ON_PAGE(PageLRU(page), page); /* * Page becomes evictable in two ways: * 1) Within LRU lock [munlock_vma_page() and __munlock_pagevec()]. * 2) Before acquiring LRU lock to put the page to correct LRU and then * a) do PageLRU check with lock [check_move_unevictable_pages] * b) do PageLRU check before lock [clear_page_mlock] * * (1) & (2a) are ok as LRU lock will serialize them. For (2b), we need * following strict ordering: * * #0: __pagevec_lru_add_fn #1: clear_page_mlock * * SetPageLRU() TestClearPageMlocked() * smp_mb() // explicit ordering // above provides strict * // ordering * PageMlocked() PageLRU() * * * if '#1' does not observe setting of PG_lru by '#0' and fails * isolation, the explicit barrier will make sure that page_evictable * check will put the page in correct LRU. Without smp_mb(), SetPageLRU * can be reordered after PageMlocked check and can make '#1' to fail * the isolation of the page whose Mlocked bit is cleared (#0 is also * looking at the same page) and the evictable page will be stranded * in an unevictable LRU. */ SetPageLRU(page); smp_mb__after_atomic(); if (page_evictable(page)) { lru = page_lru(page); if (was_unevictable) __count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages); } else { lru = LRU_UNEVICTABLE; ClearPageActive(page); SetPageUnevictable(page); if (!was_unevictable) __count_vm_events(UNEVICTABLE_PGCULLED, nr_pages); } add_page_to_lru_list(page, lruvec, lru); trace_mm_lru_insertion(page, lru); } /* * Add the passed pages to the LRU, then drop the caller's refcount * on them. Reinitialises the caller's pagevec. */ void __pagevec_lru_add(struct pagevec *pvec) { pagevec_lru_move_fn(pvec, __pagevec_lru_add_fn, NULL); } /** * pagevec_lookup_entries - gang pagecache lookup * @pvec: Where the resulting entries are placed * @mapping: The address_space to search * @start: The starting entry index * @nr_entries: The maximum number of pages * @indices: The cache indices corresponding to the entries in @pvec * * pagevec_lookup_entries() will search for and return a group of up * to @nr_pages pages and shadow entries in the mapping. All * entries are placed in @pvec. pagevec_lookup_entries() takes a * reference against actual pages in @pvec. * * The search returns a group of mapping-contiguous entries with * ascending indexes. There may be holes in the indices due to * not-present entries. * * Only one subpage of a Transparent Huge Page is returned in one call: * allowing truncate_inode_pages_range() to evict the whole THP without * cycling through a pagevec of extra references. * * pagevec_lookup_entries() returns the number of entries which were * found. */ unsigned pagevec_lookup_entries(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_entries, pgoff_t *indices) { pvec->nr = find_get_entries(mapping, start, nr_entries, pvec->pages, indices); return pagevec_count(pvec); } /** * pagevec_remove_exceptionals - pagevec exceptionals pruning * @pvec: The pagevec to prune * * pagevec_lookup_entries() fills both pages and exceptional radix * tree entries into the pagevec. This function prunes all * exceptionals from @pvec without leaving holes, so that it can be * passed on to page-only pagevec operations. */ void pagevec_remove_exceptionals(struct pagevec *pvec) { int i, j; for (i = 0, j = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; if (!xa_is_value(page)) pvec->pages[j++] = page; } pvec->nr = j; } /** * pagevec_lookup_range - gang pagecache lookup * @pvec: Where the resulting pages are placed * @mapping: The address_space to search * @start: The starting page index * @end: The final page index * * pagevec_lookup_range() will search for & return a group of up to PAGEVEC_SIZE * pages in the mapping starting from index @start and upto index @end * (inclusive). The pages are placed in @pvec. pagevec_lookup() takes a * reference against the pages in @pvec. * * The search returns a group of mapping-contiguous pages with ascending * indexes. There may be holes in the indices due to not-present pages. We * also update @start to index the next page for the traversal. * * pagevec_lookup_range() returns the number of pages which were found. If this * number is smaller than PAGEVEC_SIZE, the end of specified range has been * reached. */ unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start, pgoff_t end) { pvec->nr = find_get_pages_range(mapping, start, end, PAGEVEC_SIZE, pvec->pages); return pagevec_count(pvec); } EXPORT_SYMBOL(pagevec_lookup_range); unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag) { pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, PAGEVEC_SIZE, pvec->pages); return pagevec_count(pvec); } EXPORT_SYMBOL(pagevec_lookup_range_tag); unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, xa_mark_t tag, unsigned max_pages) { pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, min_t(unsigned int, max_pages, PAGEVEC_SIZE), pvec->pages); return pagevec_count(pvec); } EXPORT_SYMBOL(pagevec_lookup_range_nr_tag); /* * Perform any setup for the swap system */ void __init swap_setup(void) { unsigned long megs = totalram_pages() >> (20 - PAGE_SHIFT); /* Use a smaller cluster for small-memory machines */ if (megs < 16) page_cluster = 2; else page_cluster = 3; /* * Right now other parts of the system means that we * _really_ don't want to cluster much more */ } #ifdef CONFIG_DEV_PAGEMAP_OPS void put_devmap_managed_page(struct page *page) { int count; if (WARN_ON_ONCE(!page_is_devmap_managed(page))) return; count = page_ref_dec_return(page); /* * devmap page refcounts are 1-based, rather than 0-based: if * refcount is 1, then the page is free and the refcount is * stable because nobody holds a reference on the page. */ if (count == 1) free_devmap_managed_page(page); else if (!count) __put_page(page); } EXPORT_SYMBOL(put_devmap_managed_page); #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Security server interface. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> * */ #ifndef _SELINUX_SECURITY_H_ #define _SELINUX_SECURITY_H_ #include <linux/compiler.h> #include <linux/dcache.h> #include <linux/magic.h> #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/workqueue.h> #include "flask.h" #include "policycap.h" #define SECSID_NULL 0x00000000 /* unspecified SID */ #define SECSID_WILD 0xffffffff /* wildcard SID */ #define SECCLASS_NULL 0x0000 /* no class */ /* Identify specific policy version changes */ #define POLICYDB_VERSION_BASE 15 #define POLICYDB_VERSION_BOOL 16 #define POLICYDB_VERSION_IPV6 17 #define POLICYDB_VERSION_NLCLASS 18 #define POLICYDB_VERSION_VALIDATETRANS 19 #define POLICYDB_VERSION_MLS 19 #define POLICYDB_VERSION_AVTAB 20 #define POLICYDB_VERSION_RANGETRANS 21 #define POLICYDB_VERSION_POLCAP 22 #define POLICYDB_VERSION_PERMISSIVE 23 #define POLICYDB_VERSION_BOUNDARY 24 #define POLICYDB_VERSION_FILENAME_TRANS 25 #define POLICYDB_VERSION_ROLETRANS 26 #define POLICYDB_VERSION_NEW_OBJECT_DEFAULTS 27 #define POLICYDB_VERSION_DEFAULT_TYPE 28 #define POLICYDB_VERSION_CONSTRAINT_NAMES 29 #define POLICYDB_VERSION_XPERMS_IOCTL 30 #define POLICYDB_VERSION_INFINIBAND 31 #define POLICYDB_VERSION_GLBLUB 32 #define POLICYDB_VERSION_COMP_FTRANS 33 /* compressed filename transitions */ /* Range of policy versions we understand*/ #define POLICYDB_VERSION_MIN POLICYDB_VERSION_BASE #define POLICYDB_VERSION_MAX POLICYDB_VERSION_COMP_FTRANS /* Mask for just the mount related flags */ #define SE_MNTMASK 0x0f /* Super block security struct flags for mount options */ /* BE CAREFUL, these need to be the low order bits for selinux_get_mnt_opts */ #define CONTEXT_MNT 0x01 #define FSCONTEXT_MNT 0x02 #define ROOTCONTEXT_MNT 0x04 #define DEFCONTEXT_MNT 0x08 #define SBLABEL_MNT 0x10 /* Non-mount related flags */ #define SE_SBINITIALIZED 0x0100 #define SE_SBPROC 0x0200 #define SE_SBGENFS 0x0400 #define SE_SBGENFS_XATTR 0x0800 #define CONTEXT_STR "context" #define FSCONTEXT_STR "fscontext" #define ROOTCONTEXT_STR "rootcontext" #define DEFCONTEXT_STR "defcontext" #define SECLABEL_STR "seclabel" struct netlbl_lsm_secattr; extern int selinux_enabled_boot; /* * type_datum properties * available at the kernel policy version >= POLICYDB_VERSION_BOUNDARY */ #define TYPEDATUM_PROPERTY_PRIMARY 0x0001 #define TYPEDATUM_PROPERTY_ATTRIBUTE 0x0002 /* limitation of boundary depth */ #define POLICYDB_BOUNDS_MAXDEPTH 4 struct selinux_avc; struct selinux_policy; struct selinux_state { #ifdef CONFIG_SECURITY_SELINUX_DISABLE bool disabled; #endif #ifdef CONFIG_SECURITY_SELINUX_DEVELOP bool enforcing; #endif bool checkreqprot; bool initialized; bool policycap[__POLICYDB_CAPABILITY_MAX]; struct page *status_page; struct mutex status_lock; struct selinux_avc *avc; struct selinux_policy __rcu *policy; struct mutex policy_mutex; } __randomize_layout; void selinux_avc_init(struct selinux_avc **avc); extern struct selinux_state selinux_state; static inline bool selinux_initialized(const struct selinux_state *state) { /* do a synchronized load to avoid race conditions */ return smp_load_acquire(&state->initialized); } static inline void selinux_mark_initialized(struct selinux_state *state) { /* do a synchronized write to avoid race conditions */ smp_store_release(&state->initialized, true); } #ifdef CONFIG_SECURITY_SELINUX_DEVELOP static inline bool enforcing_enabled(struct selinux_state *state) { return READ_ONCE(state->enforcing); } static inline void enforcing_set(struct selinux_state *state, bool value) { WRITE_ONCE(state->enforcing, value); } #else static inline bool enforcing_enabled(struct selinux_state *state) { return true; } static inline void enforcing_set(struct selinux_state *state, bool value) { } #endif static inline bool checkreqprot_get(const struct selinux_state *state) { return READ_ONCE(state->checkreqprot); } static inline void checkreqprot_set(struct selinux_state *state, bool value) { WRITE_ONCE(state->checkreqprot, value); } #ifdef CONFIG_SECURITY_SELINUX_DISABLE static inline bool selinux_disabled(struct selinux_state *state) { return READ_ONCE(state->disabled); } static inline void selinux_mark_disabled(struct selinux_state *state) { WRITE_ONCE(state->disabled, true); } #else static inline bool selinux_disabled(struct selinux_state *state) { return false; } #endif static inline bool selinux_policycap_netpeer(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_NETPEER]); } static inline bool selinux_policycap_openperm(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_OPENPERM]); } static inline bool selinux_policycap_extsockclass(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_EXTSOCKCLASS]); } static inline bool selinux_policycap_alwaysnetwork(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_ALWAYSNETWORK]); } static inline bool selinux_policycap_cgroupseclabel(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_CGROUPSECLABEL]); } static inline bool selinux_policycap_nnp_nosuid_transition(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_NNP_NOSUID_TRANSITION]); } static inline bool selinux_policycap_genfs_seclabel_symlinks(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_GENFS_SECLABEL_SYMLINKS]); } static inline bool selinux_policycap_ioctl_skip_cloexec(void) { struct selinux_state *state = &selinux_state; return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_IOCTL_SKIP_CLOEXEC]); } struct selinux_policy_convert_data; struct selinux_load_state { struct selinux_policy *policy; struct selinux_policy_convert_data *convert_data; }; int security_mls_enabled(struct selinux_state *state); int security_load_policy(struct selinux_state *state, void *data, size_t len, struct selinux_load_state *load_state); void selinux_policy_commit(struct selinux_state *state, struct selinux_load_state *load_state); void selinux_policy_cancel(struct selinux_state *state, struct selinux_load_state *load_state); int security_read_policy(struct selinux_state *state, void **data, size_t *len); int security_policycap_supported(struct selinux_state *state, unsigned int req_cap); #define SEL_VEC_MAX 32 struct av_decision { u32 allowed; u32 auditallow; u32 auditdeny; u32 seqno; u32 flags; }; #define XPERMS_ALLOWED 1 #define XPERMS_AUDITALLOW 2 #define XPERMS_DONTAUDIT 4 #define security_xperm_set(perms, x) (perms[x >> 5] |= 1 << (x & 0x1f)) #define security_xperm_test(perms, x) (1 & (perms[x >> 5] >> (x & 0x1f))) struct extended_perms_data { u32 p[8]; }; struct extended_perms_decision { u8 used; u8 driver; struct extended_perms_data *allowed; struct extended_perms_data *auditallow; struct extended_perms_data *dontaudit; }; struct extended_perms { u16 len; /* length associated decision chain */ struct extended_perms_data drivers; /* flag drivers that are used */ }; /* definitions of av_decision.flags */ #define AVD_FLAGS_PERMISSIVE 0x0001 void security_compute_av(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd, struct extended_perms *xperms); void security_compute_xperms_decision(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u8 driver, struct extended_perms_decision *xpermd); void security_compute_av_user(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd); int security_transition_sid(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, const struct qstr *qstr, u32 *out_sid); int security_transition_sid_user(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, const char *objname, u32 *out_sid); int security_member_sid(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 *out_sid); int security_change_sid(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 *out_sid); int security_sid_to_context(struct selinux_state *state, u32 sid, char **scontext, u32 *scontext_len); int security_sid_to_context_force(struct selinux_state *state, u32 sid, char **scontext, u32 *scontext_len); int security_sid_to_context_inval(struct selinux_state *state, u32 sid, char **scontext, u32 *scontext_len); int security_context_to_sid(struct selinux_state *state, const char *scontext, u32 scontext_len, u32 *out_sid, gfp_t gfp); int security_context_str_to_sid(struct selinux_state *state, const char *scontext, u32 *out_sid, gfp_t gfp); int security_context_to_sid_default(struct selinux_state *state, const char *scontext, u32 scontext_len, u32 *out_sid, u32 def_sid, gfp_t gfp_flags); int security_context_to_sid_force(struct selinux_state *state, const char *scontext, u32 scontext_len, u32 *sid); int security_get_user_sids(struct selinux_state *state, u32 callsid, char *username, u32 **sids, u32 *nel); int security_port_sid(struct selinux_state *state, u8 protocol, u16 port, u32 *out_sid); int security_ib_pkey_sid(struct selinux_state *state, u64 subnet_prefix, u16 pkey_num, u32 *out_sid); int security_ib_endport_sid(struct selinux_state *state, const char *dev_name, u8 port_num, u32 *out_sid); int security_netif_sid(struct selinux_state *state, char *name, u32 *if_sid); int security_node_sid(struct selinux_state *state, u16 domain, void *addr, u32 addrlen, u32 *out_sid); int security_validate_transition(struct selinux_state *state, u32 oldsid, u32 newsid, u32 tasksid, u16 tclass); int security_validate_transition_user(struct selinux_state *state, u32 oldsid, u32 newsid, u32 tasksid, u16 tclass); int security_bounded_transition(struct selinux_state *state, u32 oldsid, u32 newsid); int security_sid_mls_copy(struct selinux_state *state, u32 sid, u32 mls_sid, u32 *new_sid); int security_net_peersid_resolve(struct selinux_state *state, u32 nlbl_sid, u32 nlbl_type, u32 xfrm_sid, u32 *peer_sid); int security_get_classes(struct selinux_policy *policy, char ***classes, int *nclasses); int security_get_permissions(struct selinux_policy *policy, char *class, char ***perms, int *nperms); int security_get_reject_unknown(struct selinux_state *state); int security_get_allow_unknown(struct selinux_state *state); #define SECURITY_FS_USE_XATTR 1 /* use xattr */ #define SECURITY_FS_USE_TRANS 2 /* use transition SIDs, e.g. devpts/tmpfs */ #define SECURITY_FS_USE_TASK 3 /* use task SIDs, e.g. pipefs/sockfs */ #define SECURITY_FS_USE_GENFS 4 /* use the genfs support */ #define SECURITY_FS_USE_NONE 5 /* no labeling support */ #define SECURITY_FS_USE_MNTPOINT 6 /* use mountpoint labeling */ #define SECURITY_FS_USE_NATIVE 7 /* use native label support */ #define SECURITY_FS_USE_MAX 7 /* Highest SECURITY_FS_USE_XXX */ int security_fs_use(struct selinux_state *state, struct super_block *sb); int security_genfs_sid(struct selinux_state *state, const char *fstype, char *name, u16 sclass, u32 *sid); int selinux_policy_genfs_sid(struct selinux_policy *policy, const char *fstype, char *name, u16 sclass, u32 *sid); #ifdef CONFIG_NETLABEL int security_netlbl_secattr_to_sid(struct selinux_state *state, struct netlbl_lsm_secattr *secattr, u32 *sid); int security_netlbl_sid_to_secattr(struct selinux_state *state, u32 sid, struct netlbl_lsm_secattr *secattr); #else static inline int security_netlbl_secattr_to_sid(struct selinux_state *state, struct netlbl_lsm_secattr *secattr, u32 *sid) { return -EIDRM; } static inline int security_netlbl_sid_to_secattr(struct selinux_state *state, u32 sid, struct netlbl_lsm_secattr *secattr) { return -ENOENT; } #endif /* CONFIG_NETLABEL */ const char *security_get_initial_sid_context(u32 sid); /* * status notifier using mmap interface */ extern struct page *selinux_kernel_status_page(struct selinux_state *state); #define SELINUX_KERNEL_STATUS_VERSION 1 struct selinux_kernel_status { u32 version; /* version number of thie structure */ u32 sequence; /* sequence number of seqlock logic */ u32 enforcing; /* current setting of enforcing mode */ u32 policyload; /* times of policy reloaded */ u32 deny_unknown; /* current setting of deny_unknown */ /* * The version > 0 supports above members. */ } __packed; extern void selinux_status_update_setenforce(struct selinux_state *state, int enforcing); extern void selinux_status_update_policyload(struct selinux_state *state, int seqno); extern void selinux_complete_init(void); extern int selinux_disable(struct selinux_state *state); extern void exit_sel_fs(void); extern struct path selinux_null; extern struct vfsmount *selinuxfs_mount; extern void selnl_notify_setenforce(int val); extern void selnl_notify_policyload(u32 seqno); extern int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm); extern void avtab_cache_init(void); extern void ebitmap_cache_init(void); extern void hashtab_cache_init(void); extern int security_sidtab_hash_stats(struct selinux_state *state, char *page); #endif /* _SELINUX_SECURITY_H_ */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some * particular ordering. One way to make the compiler aware of ordering is to * put the two invocations of READ_ONCE or WRITE_ONCE in different C * statements. * * These two macros will also work on aggregate data types like structs or * unions. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, * and (2) Ensuring that the compiler does not fold, spindle, or otherwise * mutilate accesses that either do not require ordering or that interact * with an explicit memory barrier or atomic instruction that provides the * required ordering. */ #ifndef __ASM_GENERIC_RWONCE_H #define __ASM_GENERIC_RWONCE_H #ifndef __ASSEMBLY__ #include <linux/compiler_types.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> /* * Yes, this permits 64-bit accesses on 32-bit architectures. These will * actually be atomic in some cases (namely Armv7 + LPAE), but for others we * rely on the access being split into 2x32-bit accesses for a 32-bit quantity * (e.g. a virtual address) and a strong prevailing wind. */ #define compiletime_assert_rwonce_type(t) \ compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ "Unsupported access size for {READ,WRITE}_ONCE().") /* * Use __READ_ONCE() instead of READ_ONCE() if you do not require any * atomicity. Note that this may result in tears! */ #ifndef __READ_ONCE #define __READ_ONCE(x) (*(const volatile __unqual_scalar_typeof(x) *)&(x)) #endif #define READ_ONCE(x) \ ({ \ compiletime_assert_rwonce_type(x); \ __READ_ONCE(x); \ }) #define __WRITE_ONCE(x, val) \ do { \ *(volatile typeof(x) *)&(x) = (val); \ } while (0) #define WRITE_ONCE(x, val) \ do { \ compiletime_assert_rwonce_type(x); \ __WRITE_ONCE(x, val); \ } while (0) static __no_sanitize_or_inline unsigned long __read_once_word_nocheck(const void *addr) { return __READ_ONCE(*(unsigned long *)addr); } /* * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a * word from memory atomically but without telling KASAN/KCSAN. This is * usually used by unwinding code when walking the stack of a running process. */ #define READ_ONCE_NOCHECK(x) \ ({ \ compiletime_assert(sizeof(x) == sizeof(unsigned long), \ "Unsupported access size for READ_ONCE_NOCHECK()."); \ (typeof(x))__read_once_word_nocheck(&(x)); \ }) static __no_kasan_or_inline unsigned long read_word_at_a_time(const void *addr) { kasan_check_read(addr, 1); return *(unsigned long *)addr; } #endif /* __ASSEMBLY__ */ #endif /* __ASM_GENERIC_RWONCE_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/namei.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * Some corrections by tytso. */ /* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname * lookup logic. */ /* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture. */ #include <linux/init.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/ima.h> #include <linux/syscalls.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/fcntl.h> #include <linux/device_cgroup.h> #include <linux/fs_struct.h> #include <linux/posix_acl.h> #include <linux/hash.h> #include <linux/bitops.h> #include <linux/init_task.h> #include <linux/uaccess.h> #include "internal.h" #include "mount.h" /* [Feb-1997 T. Schoebel-Theuer] * Fundamental changes in the pathname lookup mechanisms (namei) * were necessary because of omirr. The reason is that omirr needs * to know the _real_ pathname, not the user-supplied one, in case * of symlinks (and also when transname replacements occur). * * The new code replaces the old recursive symlink resolution with * an iterative one (in case of non-nested symlink chains). It does * this with calls to <fs>_follow_link(). * As a side effect, dir_namei(), _namei() and follow_link() are now * replaced with a single function lookup_dentry() that can handle all * the special cases of the former code. * * With the new dcache, the pathname is stored at each inode, at least as * long as the refcount of the inode is positive. As a side effect, the * size of the dcache depends on the inode cache and thus is dynamic. * * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink * resolution to correspond with current state of the code. * * Note that the symlink resolution is not *completely* iterative. * There is still a significant amount of tail- and mid- recursion in * the algorithm. Also, note that <fs>_readlink() is not used in * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink() * may return different results than <fs>_follow_link(). Many virtual * filesystems (including /proc) exhibit this behavior. */ /* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation: * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL * and the name already exists in form of a symlink, try to create the new * name indicated by the symlink. The old code always complained that the * name already exists, due to not following the symlink even if its target * is nonexistent. The new semantics affects also mknod() and link() when * the name is a symlink pointing to a non-existent name. * * I don't know which semantics is the right one, since I have no access * to standards. But I found by trial that HP-UX 9.0 has the full "new" * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the * "old" one. Personally, I think the new semantics is much more logical. * Note that "ln old new" where "new" is a symlink pointing to a non-existing * file does succeed in both HP-UX and SunOs, but not in Solaris * and in the old Linux semantics. */ /* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink * semantics. See the comments in "open_namei" and "do_link" below. * * [10-Sep-98 Alan Modra] Another symlink change. */ /* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks: * inside the path - always follow. * in the last component in creation/removal/renaming - never follow. * if LOOKUP_FOLLOW passed - follow. * if the pathname has trailing slashes - follow. * otherwise - don't follow. * (applied in that order). * * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT * restored for 2.4. This is the last surviving part of old 4.2BSD bug. * During the 2.4 we need to fix the userland stuff depending on it - * hopefully we will be able to get rid of that wart in 2.5. So far only * XEmacs seems to be relying on it... */ /* * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland) * implemented. Let's see if raised priority of ->s_vfs_rename_mutex gives * any extra contention... */ /* In order to reduce some races, while at the same time doing additional * checking and hopefully speeding things up, we copy filenames to the * kernel data space before using them.. * * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ #define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname)) struct filename * getname_flags(const char __user *filename, int flags, int *empty) { struct filename *result; char *kname; int len; result = audit_reusename(filename); if (result) return result; result = __getname(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); /* * First, try to embed the struct filename inside the names_cache * allocation */ kname = (char *)result->iname; result->name = kname; len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX); if (unlikely(len < 0)) { __putname(result); return ERR_PTR(len); } /* * Uh-oh. We have a name that's approaching PATH_MAX. Allocate a * separate struct filename so we can dedicate the entire * names_cache allocation for the pathname, and re-do the copy from * userland. */ if (unlikely(len == EMBEDDED_NAME_MAX)) { const size_t size = offsetof(struct filename, iname[1]); kname = (char *)result; /* * size is chosen that way we to guarantee that * result->iname[0] is within the same object and that * kname can't be equal to result->iname, no matter what. */ result = kzalloc(size, GFP_KERNEL); if (unlikely(!result)) { __putname(kname); return ERR_PTR(-ENOMEM); } result->name = kname; len = strncpy_from_user(kname, filename, PATH_MAX); if (unlikely(len < 0)) { __putname(kname); kfree(result); return ERR_PTR(len); } if (unlikely(len == PATH_MAX)) { __putname(kname); kfree(result); return ERR_PTR(-ENAMETOOLONG); } } result->refcnt = 1; /* The empty path is special. */ if (unlikely(!len)) { if (empty) *empty = 1; if (!(flags & LOOKUP_EMPTY)) { putname(result); return ERR_PTR(-ENOENT); } } result->uptr = filename; result->aname = NULL; audit_getname(result); return result; } struct filename * getname(const char __user * filename) { return getname_flags(filename, 0, NULL); } struct filename * getname_kernel(const char * filename) { struct filename *result; int len = strlen(filename) + 1; result = __getname(); if (unlikely(!result)) return ERR_PTR(-ENOMEM); if (len <= EMBEDDED_NAME_MAX) { result->name = (char *)result->iname; } else if (len <= PATH_MAX) { const size_t size = offsetof(struct filename, iname[1]); struct filename *tmp; tmp = kmalloc(size, GFP_KERNEL); if (unlikely(!tmp)) { __putname(result); return ERR_PTR(-ENOMEM); } tmp->name = (char *)result; result = tmp; } else { __putname(result); return ERR_PTR(-ENAMETOOLONG); } memcpy((char *)result->name, filename, len); result->uptr = NULL; result->aname = NULL; result->refcnt = 1; audit_getname(result); return result; } void putname(struct filename *name) { BUG_ON(name->refcnt <= 0); if (--name->refcnt > 0) return; if (name->name != name->iname) { __putname(name->name); kfree(name); } else __putname(name); } static int check_acl(struct inode *inode, int mask) { #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *acl; if (mask & MAY_NOT_BLOCK) { acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS); if (!acl) return -EAGAIN; /* no ->get_acl() calls in RCU mode... */ if (is_uncached_acl(acl)) return -ECHILD; return posix_acl_permission(inode, acl, mask); } acl = get_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR(acl)) return PTR_ERR(acl); if (acl) { int error = posix_acl_permission(inode, acl, mask); posix_acl_release(acl); return error; } #endif return -EAGAIN; } /* * This does the basic UNIX permission checking. * * Note that the POSIX ACL check cares about the MAY_NOT_BLOCK bit, * for RCU walking. */ static int acl_permission_check(struct inode *inode, int mask) { unsigned int mode = inode->i_mode; /* Are we the owner? If so, ACL's don't matter */ if (likely(uid_eq(current_fsuid(), inode->i_uid))) { mask &= 7; mode >>= 6; return (mask & ~mode) ? -EACCES : 0; } /* Do we have ACL's? */ if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { int error = check_acl(inode, mask); if (error != -EAGAIN) return error; } /* Only RWX matters for group/other mode bits */ mask &= 7; /* * Are the group permissions different from * the other permissions in the bits we care * about? Need to check group ownership if so. */ if (mask & (mode ^ (mode >> 3))) { if (in_group_p(inode->i_gid)) mode >>= 3; } /* Bits in 'mode' clear that we require? */ return (mask & ~mode) ? -EACCES : 0; } /** * generic_permission - check for access rights on a Posix-like filesystem * @inode: inode to check access rights for * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, * %MAY_NOT_BLOCK ...) * * Used to check for read/write/execute permissions on a file. * We use "fsuid" for this, letting us set arbitrary permissions * for filesystem access without changing the "normal" uids which * are used for other things. * * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk * request cannot be satisfied (eg. requires blocking or too much complexity). * It would then be called again in ref-walk mode. */ int generic_permission(struct inode *inode, int mask) { int ret; /* * Do the basic permission checks. */ ret = acl_permission_check(inode, mask); if (ret != -EACCES) return ret; if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ if (!(mask & MAY_WRITE)) if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH)) return 0; if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } /* * Searching includes executable on directories, else just read. */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH)) return 0; /* * Read/write DACs are always overridable. * Executable DACs are overridable when there is * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE)) return 0; return -EACCES; } EXPORT_SYMBOL(generic_permission); /* * We _really_ want to just do "generic_permission()" without * even looking at the inode->i_op values. So we keep a cache * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ static inline int do_inode_permission(struct inode *inode, int mask) { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { if (likely(inode->i_op->permission)) return inode->i_op->permission(inode, mask); /* This gets set once for the inode lifetime */ spin_lock(&inode->i_lock); inode->i_opflags |= IOP_FASTPERM; spin_unlock(&inode->i_lock); } return generic_permission(inode, mask); } /** * sb_permission - Check superblock-level permissions * @sb: Superblock of inode to check permission on * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Separate out file-system wide checks from inode-specific permission checks. */ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) { if (unlikely(mask & MAY_WRITE)) { umode_t mode = inode->i_mode; /* Nobody gets write access to a read-only fs. */ if (sb_rdonly(sb) && (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) return -EROFS; } return 0; } /** * inode_permission - Check for access rights to a given inode * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Check for read/write/execute permissions on an inode. We use fs[ug]id for * this, letting us set arbitrary permissions for filesystem access without * changing the "normal" UIDs which are used for other things. * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ int inode_permission(struct inode *inode, int mask) { int retval; retval = sb_permission(inode->i_sb, inode, mask); if (retval) return retval; if (unlikely(mask & MAY_WRITE)) { /* * Nobody gets write access to an immutable file. */ if (IS_IMMUTABLE(inode)) return -EPERM; /* * Updating mtime will likely cause i_uid and i_gid to be * written back improperly if their true value is unknown * to the vfs. */ if (HAS_UNMAPPED_ID(inode)) return -EACCES; } retval = do_inode_permission(inode, mask); if (retval) return retval; retval = devcgroup_inode_permission(inode, mask); if (retval) return retval; return security_inode_permission(inode, mask); } EXPORT_SYMBOL(inode_permission); /** * path_get - get a reference to a path * @path: path to get the reference to * * Given a path increment the reference count to the dentry and the vfsmount. */ void path_get(const struct path *path) { mntget(path->mnt); dget(path->dentry); } EXPORT_SYMBOL(path_get); /** * path_put - put a reference to a path * @path: path to put the reference to * * Given a path decrement the reference count to the dentry and the vfsmount. */ void path_put(const struct path *path) { dput(path->dentry); mntput(path->mnt); } EXPORT_SYMBOL(path_put); #define EMBEDDED_LEVELS 2 struct nameidata { struct path path; struct qstr last; struct path root; struct inode *inode; /* path.dentry.d_inode */ unsigned int flags; unsigned seq, m_seq, r_seq; int last_type; unsigned depth; int total_link_count; struct saved { struct path link; struct delayed_call done; const char *name; unsigned seq; } *stack, internal[EMBEDDED_LEVELS]; struct filename *name; struct nameidata *saved; unsigned root_seq; int dfd; kuid_t dir_uid; umode_t dir_mode; } __randomize_layout; static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) { struct nameidata *old = current->nameidata; p->stack = p->internal; p->dfd = dfd; p->name = name; p->path.mnt = NULL; p->path.dentry = NULL; p->total_link_count = old ? old->total_link_count : 0; p->saved = old; current->nameidata = p; } static void restore_nameidata(void) { struct nameidata *now = current->nameidata, *old = now->saved; current->nameidata = old; if (old) old->total_link_count = now->total_link_count; if (now->stack != now->internal) kfree(now->stack); } static bool nd_alloc_stack(struct nameidata *nd) { struct saved *p; p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved), nd->flags & LOOKUP_RCU ? GFP_ATOMIC : GFP_KERNEL); if (unlikely(!p)) return false; memcpy(p, nd->internal, sizeof(nd->internal)); nd->stack = p; return true; } /** * path_connected - Verify that a dentry is below mnt.mnt_root * * Rename can sometimes move a file or directory outside of a bind * mount, path_connected allows those cases to be detected. */ static bool path_connected(struct vfsmount *mnt, struct dentry *dentry) { struct super_block *sb = mnt->mnt_sb; /* Bind mounts can have disconnected paths */ if (mnt->mnt_root == sb->s_root) return true; return is_subdir(dentry, mnt->mnt_root); } static void drop_links(struct nameidata *nd) { int i = nd->depth; while (i--) { struct saved *last = nd->stack + i; do_delayed_call(&last->done); clear_delayed_call(&last->done); } } static void terminate_walk(struct nameidata *nd) { drop_links(nd); if (!(nd->flags & LOOKUP_RCU)) { int i; path_put(&nd->path); for (i = 0; i < nd->depth; i++) path_put(&nd->stack[i].link); if (nd->flags & LOOKUP_ROOT_GRABBED) { path_put(&nd->root); nd->flags &= ~LOOKUP_ROOT_GRABBED; } } else { nd->flags &= ~LOOKUP_RCU; rcu_read_unlock(); } nd->depth = 0; nd->path.mnt = NULL; nd->path.dentry = NULL; } /* path_put is needed afterwards regardless of success or failure */ static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq) { int res = __legitimize_mnt(path->mnt, mseq); if (unlikely(res)) { if (res > 0) path->mnt = NULL; path->dentry = NULL; return false; } if (unlikely(!lockref_get_not_dead(&path->dentry->d_lockref))) { path->dentry = NULL; return false; } return !read_seqcount_retry(&path->dentry->d_seq, seq); } static inline bool legitimize_path(struct nameidata *nd, struct path *path, unsigned seq) { return __legitimize_path(path, seq, nd->m_seq); } static bool legitimize_links(struct nameidata *nd) { int i; if (unlikely(nd->flags & LOOKUP_CACHED)) { drop_links(nd); nd->depth = 0; return false; } for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { drop_links(nd); nd->depth = i + 1; return false; } } return true; } static bool legitimize_root(struct nameidata *nd) { /* * For scoped-lookups (where nd->root has been zeroed), we need to * restart the whole lookup from scratch -- because set_root() is wrong * for these lookups (nd->dfd is the root, not the filesystem root). */ if (!nd->root.mnt && (nd->flags & LOOKUP_IS_SCOPED)) return false; /* Nothing to do if nd->root is zero or is managed by the VFS user. */ if (!nd->root.mnt || (nd->flags & LOOKUP_ROOT)) return true; nd->flags |= LOOKUP_ROOT_GRABBED; return legitimize_path(nd, &nd->root, nd->root_seq); } /* * Path walking has 2 modes, rcu-walk and ref-walk (see * Documentation/filesystems/path-lookup.txt). In situations when we can't * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab * normal reference counts on dentries and vfsmounts to transition to ref-walk * mode. Refcounts are grabbed at the last known good point before rcu-walk * got stuck, so ref-walk may continue from there. If this is not successful * (eg. a seqcount has changed), then failure is returned and it's up to caller * to restart the path walk from the beginning in ref-walk mode. */ /** * try_to_unlazy - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * Returns: true on success, false on failure * * try_to_unlazy attempts to legitimize the current nd->path and nd->root * for ref-walk mode. * Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy() failure and * terminate_walk(). */ static bool try_to_unlazy(struct nameidata *nd) { struct dentry *parent = nd->path.dentry; BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; if (unlikely(!legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) goto out; if (unlikely(!legitimize_root(nd))) goto out; rcu_read_unlock(); BUG_ON(nd->inode != parent->d_inode); return true; out1: nd->path.mnt = NULL; nd->path.dentry = NULL; out: rcu_read_unlock(); return false; } /** * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * @dentry: next dentry to step into * @seq: seq number to check @dentry against * Returns: true on success, false on failure * * Similar to to try_to_unlazy(), but here we have the next dentry already * picked by rcu-walk and want to legitimize that in addition to the current * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsigned seq) { BUG_ON(!(nd->flags & LOOKUP_RCU)); nd->flags &= ~LOOKUP_RCU; if (unlikely(!legitimize_links(nd))) goto out2; if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq))) goto out2; if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref))) goto out1; /* * We need to move both the parent and the dentry from the RCU domain * to be properly refcounted. And the sequence number in the dentry * validates *both* dentry counters, since we checked the sequence * number of the parent after we got the child sequence number. So we * know the parent must still be valid if the child sequence number is */ if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) goto out; if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) goto out_dput; /* * Sequence counts matched. Now make sure that the root is * still valid and get it if required. */ if (unlikely(!legitimize_root(nd))) goto out_dput; rcu_read_unlock(); return true; out2: nd->path.mnt = NULL; out1: nd->path.dentry = NULL; out: rcu_read_unlock(); return false; out_dput: rcu_read_unlock(); dput(dentry); return false; } static inline int d_revalidate(struct dentry *dentry, unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) return dentry->d_op->d_revalidate(dentry, flags); else return 1; } /** * complete_walk - successful completion of path walk * @nd: pointer nameidata * * If we had been in RCU mode, drop out of it and legitimize nd->path. * Revalidate the final result, unless we'd already done that during * the path walk or the filesystem doesn't ask for it. Return 0 on * success, -error on failure. In case of failure caller does not * need to drop nd->path. */ static int complete_walk(struct nameidata *nd) { struct dentry *dentry = nd->path.dentry; int status; if (nd->flags & LOOKUP_RCU) { /* * We don't want to zero nd->root for scoped-lookups or * externally-managed nd->root. */ if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED))) nd->root.mnt = NULL; nd->flags &= ~LOOKUP_CACHED; if (!try_to_unlazy(nd)) return -ECHILD; } if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * While the guarantee of LOOKUP_IS_SCOPED is (roughly) "don't * ever step outside the root during lookup" and should already * be guaranteed by the rest of namei, we want to avoid a namei * BUG resulting in userspace being given a path that was not * scoped within the root at some point during the lookup. * * So, do a final sanity-check to make sure that in the * worst-case scenario (a complete bypass of LOOKUP_IS_SCOPED) * we won't silently return an fd completely outside of the * requested root to userspace. * * Userspace could move the path outside the root after this * check, but as discussed elsewhere this is not a concern (the * resolved file was inside the root at some point). */ if (!path_is_under(&nd->path, &nd->root)) return -EXDEV; } if (likely(!(nd->flags & LOOKUP_JUMPED))) return 0; if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE))) return 0; status = dentry->d_op->d_weak_revalidate(dentry, nd->flags); if (status > 0) return 0; if (!status) status = -ESTALE; return status; } static int set_root(struct nameidata *nd) { struct fs_struct *fs = current->fs; /* * Jumping to the real root in a scoped-lookup is a BUG in namei, but we * still have to ensure it doesn't happen because it will cause a breakout * from the dirfd. */ if (WARN_ON(nd->flags & LOOKUP_IS_SCOPED)) return -ENOTRECOVERABLE; if (nd->flags & LOOKUP_RCU) { unsigned seq; do { seq = read_seqcount_begin(&fs->seq); nd->root = fs->root; nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_root(fs, &nd->root); nd->flags |= LOOKUP_ROOT_GRABBED; } return 0; } static int nd_jump_root(struct nameidata *nd) { if (unlikely(nd->flags & LOOKUP_BENEATH)) return -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { /* Absolute path arguments to path_init() are allowed. */ if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt) return -EXDEV; } if (!nd->root.mnt) { int error = set_root(nd); if (error) return error; } if (nd->flags & LOOKUP_RCU) { struct dentry *d; nd->path = nd->root; d = nd->path.dentry; nd->inode = d->d_inode; nd->seq = nd->root_seq; if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq))) return -ECHILD; } else { path_put(&nd->path); nd->path = nd->root; path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } nd->flags |= LOOKUP_JUMPED; return 0; } /* * Helper to directly jump to a known parsed path from ->get_link, * caller must have taken a reference to path beforehand. */ int nd_jump_link(struct path *path) { int error = -ELOOP; struct nameidata *nd = current->nameidata; if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS)) goto err; error = -EXDEV; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) { if (nd->path.mnt != path->mnt) goto err; } /* Not currently safe for scoped-lookups. */ if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) goto err; path_put(&nd->path); nd->path = *path; nd->inode = nd->path.dentry->d_inode; nd->flags |= LOOKUP_JUMPED; return 0; err: path_put(path); return error; } static inline void put_link(struct nameidata *nd) { struct saved *last = nd->stack + --nd->depth; do_delayed_call(&last->done); if (!(nd->flags & LOOKUP_RCU)) path_put(&last->link); } int sysctl_protected_symlinks __read_mostly = 0; int sysctl_protected_hardlinks __read_mostly = 0; int sysctl_protected_fifos __read_mostly; int sysctl_protected_regular __read_mostly; /** * may_follow_link - Check symlink following for unsafe situations * @nd: nameidata pathwalk data * * In the case of the sysctl_protected_symlinks sysctl being enabled, * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is * in a sticky world-writable directory. This is to protect privileged * processes from failing races against path names that may change out * from under them by way of other users creating malicious symlinks. * It will permit symlinks to be followed only when outside a sticky * world-writable directory, or when the uid of the symlink and follower * match, or when the directory owner matches the symlink's owner. * * Returns 0 if following the symlink is allowed, -ve on error. */ static inline int may_follow_link(struct nameidata *nd, const struct inode *inode) { if (!sysctl_protected_symlinks) return 0; /* Allowed if owner and follower match. */ if (uid_eq(current_cred()->fsuid, inode->i_uid)) return 0; /* Allowed if parent directory not sticky and world-writable. */ if ((nd->dir_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH)) return 0; /* Allowed if parent directory and link owner match. */ if (uid_valid(nd->dir_uid) && uid_eq(nd->dir_uid, inode->i_uid)) return 0; if (nd->flags & LOOKUP_RCU) return -ECHILD; audit_inode(nd->name, nd->stack[0].link.dentry, 0); audit_log_path_denied(AUDIT_ANOM_LINK, "follow_link"); return -EACCES; } /** * safe_hardlink_source - Check for safe hardlink conditions * @inode: the source inode to hardlink from * * Return false if at least one of the following conditions: * - inode is not a regular file * - inode is setuid * - inode is setgid and group-exec * - access failure for read and write * * Otherwise returns true. */ static bool safe_hardlink_source(struct inode *inode) { umode_t mode = inode->i_mode; /* Special files should not get pinned to the filesystem. */ if (!S_ISREG(mode)) return false; /* Setuid files should not get pinned to the filesystem. */ if (mode & S_ISUID) return false; /* Executable setgid files should not get pinned to the filesystem. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) return false; /* Hardlinking to unreadable or unwritable sources is dangerous. */ if (inode_permission(inode, MAY_READ | MAY_WRITE)) return false; return true; } /** * may_linkat - Check permissions for creating a hardlink * @link: the source to hardlink from * * Block hardlink when all of: * - sysctl_protected_hardlinks enabled * - fsuid does not match inode * - hardlink source is unsafe (see safe_hardlink_source() above) * - not CAP_FOWNER in a namespace with the inode owner uid mapped * * Returns 0 if successful, -ve on error. */ int may_linkat(struct path *link) { struct inode *inode = link->dentry->d_inode; /* Inode writeback is not safe when the uid or gid are invalid. */ if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) return -EOVERFLOW; if (!sysctl_protected_hardlinks) return 0; /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ if (safe_hardlink_source(inode) || inode_owner_or_capable(inode)) return 0; audit_log_path_denied(AUDIT_ANOM_LINK, "linkat"); return -EPERM; } /** * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. * @dir_mode: mode bits of directory * @dir_uid: owner of directory * @inode: the inode of the file to open * * Block an O_CREAT open of a FIFO (or a regular file) when: * - sysctl_protected_fifos (or sysctl_protected_regular) is enabled * - the file already exists * - we are in a sticky directory * - we don't own the file * - the owner of the directory doesn't own the file * - the directory is world writable * If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2 * the directory doesn't have to be world writable: being group writable will * be enough. * * Returns 0 if the open is allowed, -ve on error. */ static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid, struct inode * const inode) { if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) || (!sysctl_protected_regular && S_ISREG(inode->i_mode)) || likely(!(dir_mode & S_ISVTX)) || uid_eq(inode->i_uid, dir_uid) || uid_eq(current_fsuid(), inode->i_uid)) return 0; if (likely(dir_mode & 0002) || (dir_mode & 0020 && ((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) || (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) { const char *operation = S_ISFIFO(inode->i_mode) ? "sticky_create_fifo" : "sticky_create_regular"; audit_log_path_denied(AUDIT_ANOM_CREAT, operation); return -EACCES; } return 0; } /* * follow_up - Find the mountpoint of path's vfsmount * * Given a path, find the mountpoint of its source file system. * Replace @path with the path of the mountpoint in the parent mount. * Up is towards /. * * Return 1 if we went up a level and 0 if we were already at the * root. */ int follow_up(struct path *path) { struct mount *mnt = real_mount(path->mnt); struct mount *parent; struct dentry *mountpoint; read_seqlock_excl(&mount_lock); parent = mnt->mnt_parent; if (parent == mnt) { read_sequnlock_excl(&mount_lock); return 0; } mntget(&parent->mnt); mountpoint = dget(mnt->mnt_mountpoint); read_sequnlock_excl(&mount_lock); dput(path->dentry); path->dentry = mountpoint; mntput(path->mnt); path->mnt = &parent->mnt; return 1; } EXPORT_SYMBOL(follow_up); static bool choose_mountpoint_rcu(struct mount *m, const struct path *root, struct path *path, unsigned *seqp) { while (mnt_has_parent(m)) { struct dentry *mountpoint = m->mnt_mountpoint; m = m->mnt_parent; if (unlikely(root->dentry == mountpoint && root->mnt == &m->mnt)) break; if (mountpoint != m->mnt.mnt_root) { path->mnt = &m->mnt; path->dentry = mountpoint; *seqp = read_seqcount_begin(&mountpoint->d_seq); return true; } } return false; } static bool choose_mountpoint(struct mount *m, const struct path *root, struct path *path) { bool found; rcu_read_lock(); while (1) { unsigned seq, mseq = read_seqbegin(&mount_lock); found = choose_mountpoint_rcu(m, root, path, &seq); if (unlikely(!found)) { if (!read_seqretry(&mount_lock, mseq)) break; } else { if (likely(__legitimize_path(path, seq, mseq))) break; rcu_read_unlock(); path_put(path); rcu_read_lock(); } } rcu_read_unlock(); return found; } /* * Perform an automount * - return -EISDIR to tell follow_managed() to stop and return the path we * were called with. */ static int follow_automount(struct path *path, int *count, unsigned lookup_flags) { struct dentry *dentry = path->dentry; /* We don't want to mount if someone's just doing a stat - * unless they're stat'ing a directory and appended a '/' to * the name. * * We do, however, want to mount if someone wants to open or * create a file of any type under the mountpoint, wants to * traverse through the mountpoint or wants to open the * mounted directory. Also, autofs may mark negative dentries * as being automount points. These will need the attentions * of the daemon to instantiate them before they can be used. */ if (!(lookup_flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) && dentry->d_inode) return -EISDIR; if (count && (*count)++ >= MAXSYMLINKS) return -ELOOP; return finish_automount(dentry->d_op->d_automount(path), path); } /* * mount traversal - out-of-line part. One note on ->d_flags accesses - * dentries are pinned but not locked here, so negative dentry can go * positive right under us. Use of smp_load_acquire() provides a barrier * sufficient for ->d_inode and ->d_flags consistency. */ static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped, int *count, unsigned lookup_flags) { struct vfsmount *mnt = path->mnt; bool need_mntput = false; int ret = 0; while (flags & DCACHE_MANAGED_DENTRY) { /* Allow the filesystem to manage the transit without i_mutex * being held. */ if (flags & DCACHE_MANAGE_TRANSIT) { ret = path->dentry->d_op->d_manage(path, false); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (flags & DCACHE_MOUNTED) { // something's mounted on it.. struct vfsmount *mounted = lookup_mnt(path); if (mounted) { // ... in our namespace dput(path->dentry); if (need_mntput) mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); // here we know it's positive flags = path->dentry->d_flags; need_mntput = true; continue; } } if (!(flags & DCACHE_NEED_AUTOMOUNT)) break; // uncovered automount point ret = follow_automount(path, count, lookup_flags); flags = smp_load_acquire(&path->dentry->d_flags); if (ret < 0) break; } if (ret == -EISDIR) ret = 0; // possible if you race with several mount --move if (need_mntput && path->mnt == mnt) mntput(path->mnt); if (!ret && unlikely(d_flags_negative(flags))) ret = -ENOENT; *jumped = need_mntput; return ret; } static inline int traverse_mounts(struct path *path, bool *jumped, int *count, unsigned lookup_flags) { unsigned flags = smp_load_acquire(&path->dentry->d_flags); /* fastpath */ if (likely(!(flags & DCACHE_MANAGED_DENTRY))) { *jumped = false; if (unlikely(d_flags_negative(flags))) return -ENOENT; return 0; } return __traverse_mounts(path, flags, jumped, count, lookup_flags); } int follow_down_one(struct path *path) { struct vfsmount *mounted; mounted = lookup_mnt(path); if (mounted) { dput(path->dentry); mntput(path->mnt); path->mnt = mounted; path->dentry = dget(mounted->mnt_root); return 1; } return 0; } EXPORT_SYMBOL(follow_down_one); /* * Follow down to the covering mount currently visible to userspace. At each * point, the filesystem owning that dentry may be queried as to whether the * caller is permitted to proceed or not. */ int follow_down(struct path *path) { struct vfsmount *mnt = path->mnt; bool jumped; int ret = traverse_mounts(path, &jumped, NULL, 0); if (path->mnt != mnt) mntput(mnt); return ret; } EXPORT_SYMBOL(follow_down); /* * Try to skip to top of mountpoint pile in rcuwalk mode. Fail if * we meet a managed dentry that would need blocking. */ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path, struct inode **inode, unsigned *seqp) { struct dentry *dentry = path->dentry; unsigned int flags = dentry->d_flags; if (likely(!(flags & DCACHE_MANAGED_DENTRY))) return true; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return false; for (;;) { /* * Don't forget we might have a non-mountpoint managed dentry * that wants to block transit. */ if (unlikely(flags & DCACHE_MANAGE_TRANSIT)) { int res = dentry->d_op->d_manage(path, true); if (res) return res == -EISDIR; flags = dentry->d_flags; } if (flags & DCACHE_MOUNTED) { struct mount *mounted = __lookup_mnt(path->mnt, dentry); if (mounted) { path->mnt = &mounted->mnt; dentry = path->dentry = mounted->mnt.mnt_root; nd->flags |= LOOKUP_JUMPED; *seqp = read_seqcount_begin(&dentry->d_seq); *inode = dentry->d_inode; /* * We don't need to re-check ->d_seq after this * ->d_inode read - there will be an RCU delay * between mount hash removal and ->mnt_root * becoming unpinned. */ flags = dentry->d_flags; if (read_seqretry(&mount_lock, nd->m_seq)) return false; continue; } if (read_seqretry(&mount_lock, nd->m_seq)) return false; } return !(flags & DCACHE_NEED_AUTOMOUNT); } } static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, struct path *path, struct inode **inode, unsigned int *seqp) { bool jumped; int ret; path->mnt = nd->path.mnt; path->dentry = dentry; if (nd->flags & LOOKUP_RCU) { unsigned int seq = *seqp; if (unlikely(!*inode)) return -ENOENT; if (likely(__follow_mount_rcu(nd, path, inode, seqp))) return 0; if (!try_to_unlazy_next(nd, dentry, seq)) return -ECHILD; // *path might've been clobbered by __follow_mount_rcu() path->mnt = nd->path.mnt; path->dentry = dentry; } ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags); if (jumped) { if (unlikely(nd->flags & LOOKUP_NO_XDEV)) ret = -EXDEV; else nd->flags |= LOOKUP_JUMPED; } if (unlikely(ret)) { dput(path->dentry); if (path->mnt != nd->path.mnt) mntput(path->mnt); } else { *inode = d_backing_inode(path->dentry); *seqp = 0; /* out of RCU mode, so the value doesn't matter */ } return ret; } /* * This looks up the name in dcache and possibly revalidates the found dentry. * NULL is returned if the dentry does not exist in the cache. */ static struct dentry *lookup_dcache(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry = d_lookup(dir, name); if (dentry) { int error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { if (!error) d_invalidate(dentry); dput(dentry); return ERR_PTR(error); } } return dentry; } /* * Parent directory has inode locked exclusive. This is one * and only case when ->lookup() gets called on non in-lookup * dentries - as the matter of fact, this only gets called * when directory is guaranteed to have no in-lookup children * at all. */ static struct dentry *__lookup_hash(const struct qstr *name, struct dentry *base, unsigned int flags) { struct dentry *dentry = lookup_dcache(name, base, flags); struct dentry *old; struct inode *dir = base->d_inode; if (dentry) return dentry; /* Don't create child dentry for a dead directory. */ if (unlikely(IS_DEADDIR(dir))) return ERR_PTR(-ENOENT); dentry = d_alloc(base, name); if (unlikely(!dentry)) return ERR_PTR(-ENOMEM); old = dir->i_op->lookup(dir, dentry, flags); if (unlikely(old)) { dput(dentry); dentry = old; } return dentry; } static struct dentry *lookup_fast(struct nameidata *nd, struct inode **inode, unsigned *seqp) { struct dentry *dentry, *parent = nd->path.dentry; int status = 1; /* * Rename seqlock is not required here because in the off chance * of a false negative due to a concurrent rename, the caller is * going to fall back to non-racy lookup. */ if (nd->flags & LOOKUP_RCU) { unsigned seq; dentry = __d_lookup_rcu(parent, &nd->last, &seq); if (unlikely(!dentry)) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); return NULL; } /* * This sequence count validates that the inode matches * the dentry name information from lookup. */ *inode = d_backing_inode(dentry); if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) return ERR_PTR(-ECHILD); /* * This sequence count validates that the parent had no * changes while we did the lookup of the dentry above. * * The memory barrier in read_seqcount_begin of child is * enough, we can use __read_seqcount_retry here. */ if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq))) return ERR_PTR(-ECHILD); *seqp = seq; status = d_revalidate(dentry, nd->flags); if (likely(status > 0)) return dentry; if (!try_to_unlazy_next(nd, dentry, seq)) return ERR_PTR(-ECHILD); if (unlikely(status == -ECHILD)) /* we'd been told to redo it in non-rcu mode */ status = d_revalidate(dentry, nd->flags); } else { dentry = __d_lookup(parent, &nd->last); if (unlikely(!dentry)) return NULL; status = d_revalidate(dentry, nd->flags); } if (unlikely(status <= 0)) { if (!status) d_invalidate(dentry); dput(dentry); return ERR_PTR(status); } return dentry; } /* Fast lookup failed, do it the slow way */ static struct dentry *__lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct dentry *dentry, *old; struct inode *inode = dir->d_inode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); /* Don't go there if it's already dead */ if (unlikely(IS_DEADDIR(inode))) return ERR_PTR(-ENOENT); again: dentry = d_alloc_parallel(dir, name, &wq); if (IS_ERR(dentry)) return dentry; if (unlikely(!d_in_lookup(dentry))) { int error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { if (!error) { d_invalidate(dentry); dput(dentry); goto again; } dput(dentry); dentry = ERR_PTR(error); } } else { old = inode->i_op->lookup(inode, dentry, flags); d_lookup_done(dentry); if (unlikely(old)) { dput(dentry); dentry = old; } } return dentry; } static struct dentry *lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { struct inode *inode = dir->d_inode; struct dentry *res; inode_lock_shared(inode); res = __lookup_slow(name, dir, flags); inode_unlock_shared(inode); return res; } static inline int may_lookup(struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK); if (err != -ECHILD || !try_to_unlazy(nd)) return err; } return inode_permission(nd->inode, MAY_EXEC); } static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq) { if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) return -ELOOP; if (likely(nd->depth != EMBEDDED_LEVELS)) return 0; if (likely(nd->stack != nd->internal)) return 0; if (likely(nd_alloc_stack(nd))) return 0; if (nd->flags & LOOKUP_RCU) { // we need to grab link before we do unlazy. And we can't skip // unlazy even if we fail to grab the link - cleanup needs it bool grabbed_link = legitimize_path(nd, link, seq); if (!try_to_unlazy(nd) != 0 || !grabbed_link) return -ECHILD; if (nd_alloc_stack(nd)) return 0; } return -ENOMEM; } enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4}; static const char *pick_link(struct nameidata *nd, struct path *link, struct inode *inode, unsigned seq, int flags) { struct saved *last; const char *res; int error = reserve_stack(nd, link, seq); if (unlikely(error)) { if (!(nd->flags & LOOKUP_RCU)) path_put(link); return ERR_PTR(error); } last = nd->stack + nd->depth++; last->link = *link; clear_delayed_call(&last->done); last->seq = seq; if (flags & WALK_TRAILING) { error = may_follow_link(nd, inode); if (unlikely(error)) return ERR_PTR(error); } if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) || unlikely(link->mnt->mnt_flags & MNT_NOSYMFOLLOW)) return ERR_PTR(-ELOOP); if (!(nd->flags & LOOKUP_RCU)) { touch_atime(&last->link); cond_resched(); } else if (atime_needs_update(&last->link, inode)) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); touch_atime(&last->link); } error = security_inode_follow_link(link->dentry, inode, nd->flags & LOOKUP_RCU); if (unlikely(error)) return ERR_PTR(error); res = READ_ONCE(inode->i_link); if (!res) { const char * (*get)(struct dentry *, struct inode *, struct delayed_call *); get = inode->i_op->get_link; if (nd->flags & LOOKUP_RCU) { res = get(NULL, inode, &last->done); if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd)) res = get(link->dentry, inode, &last->done); } else { res = get(link->dentry, inode, &last->done); } if (!res) goto all_done; if (IS_ERR(res)) return res; } if (*res == '/') { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); while (unlikely(*++res == '/')) ; } if (*res) return res; all_done: // pure jump put_link(nd); return NULL; } /* * Do we need to follow links? We _really_ want to be able * to do this check without having to look at inode->i_op, * so we keep a cache of "no, this doesn't need follow_link" * for the common case. */ static const char *step_into(struct nameidata *nd, int flags, struct dentry *dentry, struct inode *inode, unsigned seq) { struct path path; int err = handle_mounts(nd, dentry, &path, &inode, &seq); if (err < 0) return ERR_PTR(err); if (likely(!d_is_symlink(path.dentry)) || ((flags & WALK_TRAILING) && !(nd->flags & LOOKUP_FOLLOW)) || (flags & WALK_NOFOLLOW)) { /* not a symlink or should not follow */ if (!(nd->flags & LOOKUP_RCU)) { dput(nd->path.dentry); if (nd->path.mnt != path.mnt) mntput(nd->path.mnt); } nd->path = path; nd->inode = inode; nd->seq = seq; return NULL; } if (nd->flags & LOOKUP_RCU) { /* make sure that d_is_symlink above matches inode */ if (read_seqcount_retry(&path.dentry->d_seq, seq)) return ERR_PTR(-ECHILD); } else { if (path.mnt == nd->path.mnt) mntget(path.mnt); } return pick_link(nd, &path, inode, seq, flags); } static struct dentry *follow_dotdot_rcu(struct nameidata *nd, struct inode **inodep, unsigned *seqp) { struct dentry *parent, *old; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; unsigned seq; if (!choose_mountpoint_rcu(real_mount(nd->path.mnt), &nd->root, &path, &seq)) goto in_root; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-ECHILD); nd->path = path; nd->inode = path.dentry->d_inode; nd->seq = seq; if (unlikely(read_seqretry(&mount_lock, nd->m_seq))) return ERR_PTR(-ECHILD); /* we know that mountpoint was pinned */ } old = nd->path.dentry; parent = old->d_parent; *inodep = parent->d_inode; *seqp = read_seqcount_begin(&parent->d_seq); if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq))) return ERR_PTR(-ECHILD); if (unlikely(!path_connected(nd->path.mnt, parent))) return ERR_PTR(-ECHILD); return parent; in_root: if (unlikely(read_seqretry(&mount_lock, nd->m_seq))) return ERR_PTR(-ECHILD); if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-ECHILD); return NULL; } static struct dentry *follow_dotdot(struct nameidata *nd, struct inode **inodep, unsigned *seqp) { struct dentry *parent; if (path_equal(&nd->path, &nd->root)) goto in_root; if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) { struct path path; if (!choose_mountpoint(real_mount(nd->path.mnt), &nd->root, &path)) goto in_root; path_put(&nd->path); nd->path = path; nd->inode = path.dentry->d_inode; if (unlikely(nd->flags & LOOKUP_NO_XDEV)) return ERR_PTR(-EXDEV); } /* rare case of legitimate dget_parent()... */ parent = dget_parent(nd->path.dentry); if (unlikely(!path_connected(nd->path.mnt, parent))) { dput(parent); return ERR_PTR(-ENOENT); } *seqp = 0; *inodep = parent->d_inode; return parent; in_root: if (unlikely(nd->flags & LOOKUP_BENEATH)) return ERR_PTR(-EXDEV); dget(nd->path.dentry); return NULL; } static const char *handle_dots(struct nameidata *nd, int type) { if (type == LAST_DOTDOT) { const char *error = NULL; struct dentry *parent; struct inode *inode; unsigned seq; if (!nd->root.mnt) { error = ERR_PTR(set_root(nd)); if (error) return error; } if (nd->flags & LOOKUP_RCU) parent = follow_dotdot_rcu(nd, &inode, &seq); else parent = follow_dotdot(nd, &inode, &seq); if (IS_ERR(parent)) return ERR_CAST(parent); if (unlikely(!parent)) error = step_into(nd, WALK_NOFOLLOW, nd->path.dentry, nd->inode, nd->seq); else error = step_into(nd, WALK_NOFOLLOW, parent, inode, seq); if (unlikely(error)) return error; if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) { /* * If there was a racing rename or mount along our * path, then we can't be sure that ".." hasn't jumped * above nd->root (and so userspace should retry or use * some fallback). */ smp_rmb(); if (unlikely(__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq))) return ERR_PTR(-EAGAIN); if (unlikely(__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq))) return ERR_PTR(-EAGAIN); } } return NULL; } static const char *walk_component(struct nameidata *nd, int flags) { struct dentry *dentry; struct inode *inode; unsigned seq; /* * "." and ".." are special - ".." especially so because it has * to be able to know about the current root directory and * parent relationships. */ if (unlikely(nd->last_type != LAST_NORM)) { if (!(flags & WALK_MORE) && nd->depth) put_link(nd); return handle_dots(nd, nd->last_type); } dentry = lookup_fast(nd, &inode, &seq); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (unlikely(!dentry)) { dentry = lookup_slow(&nd->last, nd->path.dentry, nd->flags); if (IS_ERR(dentry)) return ERR_CAST(dentry); } if (!(flags & WALK_MORE) && nd->depth) put_link(nd); return step_into(nd, flags, dentry, inode, seq); } /* * We can do the critical dentry name comparison and hashing * operations one word at a time, but we are limited to: * * - Architectures with fast unaligned word accesses. We could * do a "get_unaligned()" if this helps and is sufficiently * fast. * * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we * do not trap on the (extremely unlikely) case of a page * crossing operation. * * - Furthermore, we need an efficient 64-bit compile for the * 64-bit case in order to generate the "number of bytes in * the final mask". Again, that could be replaced with a * efficient population count instruction or similar. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> #ifdef HASH_MIX /* Architecture provides HASH_MIX and fold_hash() in <asm/hash.h> */ #elif defined(CONFIG_64BIT) /* * Register pressure in the mixing function is an issue, particularly * on 32-bit x86, but almost any function requires one state value and * one temporary. Instead, use a function designed for two state values * and no temporaries. * * This function cannot create a collision in only two iterations, so * we have two iterations to achieve avalanche. In those two iterations, * we have six layers of mixing, which is enough to spread one bit's * influence out to 2^6 = 64 state bits. * * Rotate constants are scored by considering either 64 one-bit input * deltas or 64*63/2 = 2016 two-bit input deltas, and finding the * probability of that delta causing a change to each of the 128 output * bits, using a sample of random initial states. * * The Shannon entropy of the computed probabilities is then summed * to produce a score. Ideally, any input change has a 50% chance of * toggling any given output bit. * * Mixing scores (in bits) for (12,45): * Input delta: 1-bit 2-bit * 1 round: 713.3 42542.6 * 2 rounds: 2753.7 140389.8 * 3 rounds: 5954.1 233458.2 * 4 rounds: 7862.6 256672.2 * Perfect: 8192 258048 * (64*128) (64*63/2 * 128) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol64(x,12),\ x += y, y = rol64(y,45),\ y *= 9 ) /* * Fold two longs into one 32-bit hash value. This must be fast, but * latency isn't quite as critical, as there is a fair bit of additional * work done before the hash value is used. */ static inline unsigned int fold_hash(unsigned long x, unsigned long y) { y ^= x * GOLDEN_RATIO_64; y *= GOLDEN_RATIO_64; return y >> 32; } #else /* 32-bit case */ /* * Mixing scores (in bits) for (7,20): * Input delta: 1-bit 2-bit * 1 round: 330.3 9201.6 * 2 rounds: 1246.4 25475.4 * 3 rounds: 1907.1 31295.1 * 4 rounds: 2042.3 31718.6 * Perfect: 2048 31744 * (32*64) (32*31/2 * 64) */ #define HASH_MIX(x, y, a) \ ( x ^= (a), \ y ^= x, x = rol32(x, 7),\ x += y, y = rol32(y,20),\ y *= 9 ) static inline unsigned int fold_hash(unsigned long x, unsigned long y) { /* Use arch-optimized multiply if one exists */ return __hash_32(y ^ __hash_32(x)); } #endif /* * Return the hash of a string of known length. This is carfully * designed to match hash_name(), which is the more critical function. * In particular, we must end by hashing a final word containing 0..7 * payload bytes, to match the way that hash_name() iterates until it * finds the delimiter after the name. */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long a, x = 0, y = (unsigned long)salt; for (;;) { if (!len) goto done; a = load_unaligned_zeropad(name); if (len < sizeof(unsigned long)) break; HASH_MIX(x, y, a); name += sizeof(unsigned long); len -= sizeof(unsigned long); } x ^= a & bytemask_from_count(len); done: return fold_hash(x, y); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long a = 0, x = 0, y = (unsigned long)salt; unsigned long adata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; len = 0; goto inside; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); inside: a = load_unaligned_zeropad(name+len); } while (!has_zero(a, &adata, &constants)); adata = prep_zero_mask(a, adata, &constants); mask = create_zero_mask(adata); x ^= a & zero_bytemask(mask); return hashlen_create(fold_hash(x, y), len + find_zero(mask)); } EXPORT_SYMBOL(hashlen_string); /* * Calculate the length and hash of the path component, and * return the "hash_len" as the result. */ static inline u64 hash_name(const void *salt, const char *name) { unsigned long a = 0, b, x = 0, y = (unsigned long)salt; unsigned long adata, bdata, mask, len; const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; len = 0; goto inside; do { HASH_MIX(x, y, a); len += sizeof(unsigned long); inside: a = load_unaligned_zeropad(name+len); b = a ^ REPEAT_BYTE('/'); } while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants))); adata = prep_zero_mask(a, adata, &constants); bdata = prep_zero_mask(b, bdata, &constants); mask = create_zero_mask(adata | bdata); x ^= a & zero_bytemask(mask); return hashlen_create(fold_hash(x, y), len + find_zero(mask)); } #else /* !CONFIG_DCACHE_WORD_ACCESS: Slow, byte-at-a-time version */ /* Return the hash of a string of known length */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long hash = init_name_hash(salt); while (len--) hash = partial_name_hash((unsigned char)*name++, hash); return end_name_hash(hash); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long hash = init_name_hash(salt); unsigned long len = 0, c; c = (unsigned char)*name; while (c) { len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } return hashlen_create(end_name_hash(hash), len); } EXPORT_SYMBOL(hashlen_string); /* * We know there's a real path component here of at least * one character. */ static inline u64 hash_name(const void *salt, const char *name) { unsigned long hash = init_name_hash(salt); unsigned long len = 0, c; c = (unsigned char)*name; do { len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } while (c && c != '/'); return hashlen_create(end_name_hash(hash), len); } #endif /* * Name resolution. * This is the basic name resolution function, turning a pathname into * the final dentry. We expect 'base' to be positive and a directory. * * Returns 0 and nd will have valid dentry and mnt on success. * Returns error and drops reference to input namei data on failure. */ static int link_path_walk(const char *name, struct nameidata *nd) { int depth = 0; // depth <= nd->depth int err; nd->last_type = LAST_ROOT; nd->flags |= LOOKUP_PARENT; if (IS_ERR(name)) return PTR_ERR(name); while (*name=='/') name++; if (!*name) return 0; /* At this point we know we have a real path component. */ for(;;) { const char *link; u64 hash_len; int type; err = may_lookup(nd); if (err) return err; hash_len = hash_name(nd->path.dentry, name); type = LAST_NORM; if (name[0] == '.') switch (hashlen_len(hash_len)) { case 2: if (name[1] == '.') { type = LAST_DOTDOT; nd->flags |= LOOKUP_JUMPED; } break; case 1: type = LAST_DOT; } if (likely(type == LAST_NORM)) { struct dentry *parent = nd->path.dentry; nd->flags &= ~LOOKUP_JUMPED; if (unlikely(parent->d_flags & DCACHE_OP_HASH)) { struct qstr this = { { .hash_len = hash_len }, .name = name }; err = parent->d_op->d_hash(parent, &this); if (err < 0) return err; hash_len = this.hash_len; name = this.name; } } nd->last.hash_len = hash_len; nd->last.name = name; nd->last_type = type; name += hashlen_len(hash_len); if (!*name) goto OK; /* * If it wasn't NUL, we know it was '/'. Skip that * slash, and continue until no more slashes. */ do { name++; } while (unlikely(*name == '/')); if (unlikely(!*name)) { OK: /* pathname or trailing symlink, done */ if (!depth) { nd->dir_uid = nd->inode->i_uid; nd->dir_mode = nd->inode->i_mode; nd->flags &= ~LOOKUP_PARENT; return 0; } /* last component of nested symlink */ name = nd->stack[--depth].name; link = walk_component(nd, 0); } else { /* not the last component */ link = walk_component(nd, WALK_MORE); } if (unlikely(link)) { if (IS_ERR(link)) return PTR_ERR(link); /* a symlink to follow */ nd->stack[depth++].name = name; name = link; continue; } if (unlikely(!d_can_lookup(nd->path.dentry))) { if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return -ECHILD; } return -ENOTDIR; } } } /* must be paired with terminate_walk() */ static const char *path_init(struct nameidata *nd, unsigned flags) { int error; const char *s = nd->name->name; /* LOOKUP_CACHED requires RCU, ask caller to retry */ if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED) return ERR_PTR(-EAGAIN); if (!*s) flags &= ~LOOKUP_RCU; if (flags & LOOKUP_RCU) rcu_read_lock(); nd->flags = flags | LOOKUP_JUMPED; nd->depth = 0; nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount); nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount); smp_rmb(); if (flags & LOOKUP_ROOT) { struct dentry *root = nd->root.dentry; struct inode *inode = root->d_inode; if (*s && unlikely(!d_can_lookup(root))) return ERR_PTR(-ENOTDIR); nd->path = nd->root; nd->inode = inode; if (flags & LOOKUP_RCU) { nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); nd->root_seq = nd->seq; } else { path_get(&nd->path); } return s; } nd->root.mnt = NULL; /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */ if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) { error = nd_jump_root(nd); if (unlikely(error)) return ERR_PTR(error); return s; } /* Relative pathname -- get the starting-point it is relative to. */ if (nd->dfd == AT_FDCWD) { if (flags & LOOKUP_RCU) { struct fs_struct *fs = current->fs; unsigned seq; do { seq = read_seqcount_begin(&fs->seq); nd->path = fs->pwd; nd->inode = nd->path.dentry->d_inode; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } while (read_seqcount_retry(&fs->seq, seq)); } else { get_fs_pwd(current->fs, &nd->path); nd->inode = nd->path.dentry->d_inode; } } else { /* Caller must check execute permissions on the starting path component */ struct fd f = fdget_raw(nd->dfd); struct dentry *dentry; if (!f.file) return ERR_PTR(-EBADF); dentry = f.file->f_path.dentry; if (*s && unlikely(!d_can_lookup(dentry))) { fdput(f); return ERR_PTR(-ENOTDIR); } nd->path = f.file->f_path; if (flags & LOOKUP_RCU) { nd->inode = nd->path.dentry->d_inode; nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq); } else { path_get(&nd->path); nd->inode = nd->path.dentry->d_inode; } fdput(f); } /* For scoped-lookups we need to set the root to the dirfd as well. */ if (flags & LOOKUP_IS_SCOPED) { nd->root = nd->path; if (flags & LOOKUP_RCU) { nd->root_seq = nd->seq; } else { path_get(&nd->root); nd->flags |= LOOKUP_ROOT_GRABBED; } } return s; } static inline const char *lookup_last(struct nameidata *nd) { if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; return walk_component(nd, WALK_TRAILING); } static int handle_lookup_down(struct nameidata *nd) { if (!(nd->flags & LOOKUP_RCU)) dget(nd->path.dentry); return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry, nd->inode, nd->seq)); } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path) { const char *s = path_init(nd, flags); int err; if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) { err = handle_lookup_down(nd); if (unlikely(err < 0)) s = ERR_PTR(err); } while (!(err = link_path_walk(s, nd)) && (s = lookup_last(nd)) != NULL) ; if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) { err = handle_lookup_down(nd); nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please... } if (!err) err = complete_walk(nd); if (!err && nd->flags & LOOKUP_DIRECTORY) if (!d_can_lookup(nd->path.dentry)) err = -ENOTDIR; if (!err) { *path = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, struct path *root) { int retval; struct nameidata nd; if (IS_ERR(name)) return PTR_ERR(name); if (unlikely(root)) { nd.root = *root; flags |= LOOKUP_ROOT; } set_nameidata(&nd, dfd, name); retval = path_lookupat(&nd, flags | LOOKUP_RCU, path); if (unlikely(retval == -ECHILD)) retval = path_lookupat(&nd, flags, path); if (unlikely(retval == -ESTALE)) retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path); if (likely(!retval)) audit_inode(name, path->dentry, flags & LOOKUP_MOUNTPOINT ? AUDIT_INODE_NOEVAL : 0); restore_nameidata(); putname(name); return retval; } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ static int path_parentat(struct nameidata *nd, unsigned flags, struct path *parent) { const char *s = path_init(nd, flags); int err = link_path_walk(s, nd); if (!err) err = complete_walk(nd); if (!err) { *parent = nd->path; nd->path.mnt = NULL; nd->path.dentry = NULL; } terminate_walk(nd); return err; } static struct filename *filename_parentat(int dfd, struct filename *name, unsigned int flags, struct path *parent, struct qstr *last, int *type) { int retval; struct nameidata nd; if (IS_ERR(name)) return name; set_nameidata(&nd, dfd, name); retval = path_parentat(&nd, flags | LOOKUP_RCU, parent); if (unlikely(retval == -ECHILD)) retval = path_parentat(&nd, flags, parent); if (unlikely(retval == -ESTALE)) retval = path_parentat(&nd, flags | LOOKUP_REVAL, parent); if (likely(!retval)) { *last = nd.last; *type = nd.last_type; audit_inode(name, parent->dentry, AUDIT_INODE_PARENT); } else { putname(name); name = ERR_PTR(retval); } restore_nameidata(); return name; } /* does lookup, returns the object with parent locked */ struct dentry *kern_path_locked(const char *name, struct path *path) { struct filename *filename; struct dentry *d; struct qstr last; int type; filename = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path, &last, &type); if (IS_ERR(filename)) return ERR_CAST(filename); if (unlikely(type != LAST_NORM)) { path_put(path); putname(filename); return ERR_PTR(-EINVAL); } inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); d = __lookup_hash(&last, path->dentry, 0); if (IS_ERR(d)) { inode_unlock(path->dentry->d_inode); path_put(path); } putname(filename); return d; } int kern_path(const char *name, unsigned int flags, struct path *path) { return filename_lookup(AT_FDCWD, getname_kernel(name), flags, path, NULL); } EXPORT_SYMBOL(kern_path); /** * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair * @dentry: pointer to dentry of the base directory * @mnt: pointer to vfs mount of the base directory * @name: pointer to file name * @flags: lookup flags * @path: pointer to struct path to fill */ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct path *path) { struct path root = {.mnt = mnt, .dentry = dentry}; /* the first argument of filename_lookup() is ignored with root */ return filename_lookup(AT_FDCWD, getname_kernel(name), flags , path, &root); } EXPORT_SYMBOL(vfs_path_lookup); static int lookup_one_len_common(const char *name, struct dentry *base, int len, struct qstr *this) { this->name = name; this->len = len; this->hash = full_name_hash(base, name, len); if (!len) return -EACCES; if (unlikely(name[0] == '.')) { if (len < 2 || (len == 2 && name[1] == '.')) return -EACCES; } while (len--) { unsigned int c = *(const unsigned char *)name++; if (c == '/' || c == '\0') return -EACCES; } /* * See if the low-level filesystem might want * to use its own hash.. */ if (base->d_flags & DCACHE_OP_HASH) { int err = base->d_op->d_hash(base, this); if (err < 0) return err; } return inode_permission(base->d_inode, MAY_EXEC); } /** * try_lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Look up a dentry by name in the dcache, returning NULL if it does not * currently exist. The function does not try to create a dentry. * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len) { struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_len_common(name, base, len, &this); if (err) return ERR_PTR(err); return lookup_dcache(&this, base, 0); } EXPORT_SYMBOL(try_lookup_one_len); /** * lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) { struct dentry *dentry; struct qstr this; int err; WARN_ON_ONCE(!inode_is_locked(base->d_inode)); err = lookup_one_len_common(name, base, len, &this); if (err) return ERR_PTR(err); dentry = lookup_dcache(&this, base, 0); return dentry ? dentry : __lookup_slow(&this, base, 0); } EXPORT_SYMBOL(lookup_one_len); /** * lookup_one_len_unlocked - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * Unlike lookup_one_len, it should be called without the parent * i_mutex held, and will take the i_mutex itself if necessary. */ struct dentry *lookup_one_len_unlocked(const char *name, struct dentry *base, int len) { struct qstr this; int err; struct dentry *ret; err = lookup_one_len_common(name, base, len, &this); if (err) return ERR_PTR(err); ret = lookup_dcache(&this, base, 0); if (!ret) ret = lookup_slow(&this, base, 0); return ret; } EXPORT_SYMBOL(lookup_one_len_unlocked); /* * Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT) * on negatives. Returns known positive or ERR_PTR(); that's what * most of the users want. Note that pinned negative with unlocked parent * _can_ become positive at any time, so callers of lookup_one_len_unlocked() * need to be very careful; pinned positives have ->d_inode stable, so * this one avoids such problems. */ struct dentry *lookup_positive_unlocked(const char *name, struct dentry *base, int len) { struct dentry *ret = lookup_one_len_unlocked(name, base, len); if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) { dput(ret); ret = ERR_PTR(-ENOENT); } return ret; } EXPORT_SYMBOL(lookup_positive_unlocked); #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { /* Find something mounted on "pts" in the same directory as * the input path. */ struct dentry *parent = dget_parent(path->dentry); struct dentry *child; struct qstr this = QSTR_INIT("pts", 3); if (unlikely(!path_connected(path->mnt, parent))) { dput(parent); return -ENOENT; } dput(path->dentry); path->dentry = parent; child = d_hash_and_lookup(parent, &this); if (IS_ERR_OR_NULL(child)) return -ENOENT; path->dentry = child; dput(parent); follow_down(path); return 0; } #endif int user_path_at_empty(int dfd, const char __user *name, unsigned flags, struct path *path, int *empty) { return filename_lookup(dfd, getname_flags(name, flags, empty), flags, path, NULL); } EXPORT_SYMBOL(user_path_at_empty); int __check_sticky(struct inode *dir, struct inode *inode) { kuid_t fsuid = current_fsuid(); if (uid_eq(inode->i_uid, fsuid)) return 0; if (uid_eq(dir->i_uid, fsuid)) return 0; return !capable_wrt_inode_uidgid(inode, CAP_FOWNER); } EXPORT_SYMBOL(__check_sticky); /* * Check whether we can remove a link victim from directory dir, check * whether the type of victim is right. * 1. We can't do it if dir is read-only (done in permission()) * 2. We should have write and exec permissions on dir * 3. We can't remove anything from append-only dir * 4. We can't do anything with immutable dir (done in permission()) * 5. If the sticky bit on dir is set we should either * a. be owner of dir, or * b. be owner of victim, or * c. have CAP_FOWNER capability * 6. If the victim is append-only or immutable we can't do antyhing with * links pointing to it. * 7. If the victim has an unknown uid or gid we can't change the inode. * 8. If we were asked to remove a directory and victim isn't one - ENOTDIR. * 9. If we were asked to remove a non-directory and victim isn't one - EISDIR. * 10. We can't remove a root or mountpoint. * 11. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) { struct inode *inode = d_backing_inode(victim); int error; if (d_is_negative(victim)) return -ENOENT; BUG_ON(!inode); BUG_ON(victim->d_parent->d_inode != dir); /* Inode writeback is not safe when the uid or gid are invalid. */ if (!uid_valid(inode->i_uid) || !gid_valid(inode->i_gid)) return -EOVERFLOW; audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); error = inode_permission(dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) return -EPERM; if (check_sticky(dir, inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || HAS_UNMAPPED_ID(inode)) return -EPERM; if (isdir) { if (!d_is_dir(victim)) return -ENOTDIR; if (IS_ROOT(victim)) return -EBUSY; } else if (d_is_dir(victim)) return -EISDIR; if (IS_DEADDIR(dir)) return -ENOENT; if (victim->d_flags & DCACHE_NFSFS_RENAMED) return -EBUSY; return 0; } /* Check whether we can create an object with dentry child in directory * dir. * 1. We can't do it if child already exists (open has special treatment for * this case, but since we are inlined it's OK) * 2. We can't do it if dir is read-only (done in permission()) * 3. We can't do it if the fs can't represent the fsuid or fsgid. * 4. We should have write and exec permissions on dir * 5. We can't do it if dir is immutable (done in permission()) */ static inline int may_create(struct inode *dir, struct dentry *child) { struct user_namespace *s_user_ns; audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); if (child->d_inode) return -EEXIST; if (IS_DEADDIR(dir)) return -ENOENT; s_user_ns = dir->i_sb->s_user_ns; if (!kuid_has_mapping(s_user_ns, current_fsuid()) || !kgid_has_mapping(s_user_ns, current_fsgid())) return -EOVERFLOW; return inode_permission(dir, MAY_WRITE | MAY_EXEC); } /* * p1 and p2 should be directories on the same fs. */ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) { struct dentry *p; if (p1 == p2) { inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); return NULL; } mutex_lock(&p1->d_sb->s_vfs_rename_mutex); p = d_ancestor(p2, p1); if (p) { inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2); return p; } p = d_ancestor(p1, p2); inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); return p; } EXPORT_SYMBOL(lock_rename); void unlock_rename(struct dentry *p1, struct dentry *p2) { inode_unlock(p1->d_inode); if (p1 != p2) { inode_unlock(p2->d_inode); mutex_unlock(&p1->d_sb->s_vfs_rename_mutex); } } EXPORT_SYMBOL(unlock_rename); /** * mode_strip_umask - handle vfs umask stripping * @dir: parent directory of the new inode * @mode: mode of the new inode to be created in @dir * * Umask stripping depends on whether or not the filesystem supports POSIX * ACLs. If the filesystem doesn't support it umask stripping is done directly * in here. If the filesystem does support POSIX ACLs umask stripping is * deferred until the filesystem calls posix_acl_create(). * * Returns: mode */ static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir)) mode &= ~current_umask(); return mode; } /** * vfs_prepare_mode - prepare the mode to be used for a new inode * @dir: parent directory of the new inode * @mode: mode of the new inode * @mask_perms: allowed permission by the vfs * @type: type of file to be created * * This helper consolidates and enforces vfs restrictions on the @mode of a new * object to be created. * * Umask stripping depends on whether the filesystem supports POSIX ACLs (see * the kernel documentation for mode_strip_umask()). Moving umask stripping * after setgid stripping allows the same ordering for both non-POSIX ACL and * POSIX ACL supporting filesystems. * * Note that it's currently valid for @type to be 0 if a directory is created. * Filesystems raise that flag individually and we need to check whether each * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a * non-zero type. * * Returns: mode to be passed to the filesystem */ static inline umode_t vfs_prepare_mode(const struct inode *dir, umode_t mode, umode_t mask_perms, umode_t type) { mode = mode_strip_sgid(dir, mode); mode = mode_strip_umask(dir, mode); /* * Apply the vfs mandated allowed permission mask and set the type of * file to be created before we call into the filesystem. */ mode &= (mask_perms & ~S_IFMT); mode |= (type & S_IFMT); return mode; } int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool want_excl) { int error = may_create(dir, dentry); if (error) return error; if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ mode = vfs_prepare_mode(dir, mode, S_IALLUGO, S_IFREG); error = security_inode_create(dir, dentry, mode); if (error) return error; error = dir->i_op->create(dir, dentry, mode, want_excl); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_create); int vfs_mkobj(struct dentry *dentry, umode_t mode, int (*f)(struct dentry *, umode_t, void *), void *arg) { struct inode *dir = dentry->d_parent->d_inode; int error = may_create(dir, dentry); if (error) return error; mode &= S_IALLUGO; mode |= S_IFREG; error = security_inode_create(dir, dentry, mode); if (error) return error; error = f(dentry, mode, arg); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkobj); bool may_open_dev(const struct path *path) { return !(path->mnt->mnt_flags & MNT_NODEV) && !(path->mnt->mnt_sb->s_iflags & SB_I_NODEV); } static int may_open(const struct path *path, int acc_mode, int flag) { struct dentry *dentry = path->dentry; struct inode *inode = dentry->d_inode; int error; if (!inode) return -ENOENT; switch (inode->i_mode & S_IFMT) { case S_IFLNK: return -ELOOP; case S_IFDIR: if (acc_mode & MAY_WRITE) return -EISDIR; if (acc_mode & MAY_EXEC) return -EACCES; break; case S_IFBLK: case S_IFCHR: if (!may_open_dev(path)) return -EACCES; fallthrough; case S_IFIFO: case S_IFSOCK: if (acc_mode & MAY_EXEC) return -EACCES; flag &= ~O_TRUNC; break; case S_IFREG: if ((acc_mode & MAY_EXEC) && path_noexec(path)) return -EACCES; break; } error = inode_permission(inode, MAY_OPEN | acc_mode); if (error) return error; /* * An append-only file must be opened in append mode for writing. */ if (IS_APPEND(inode)) { if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND)) return -EPERM; if (flag & O_TRUNC) return -EPERM; } /* O_NOATIME can only be set by the owner or superuser */ if (flag & O_NOATIME && !inode_owner_or_capable(inode)) return -EPERM; return 0; } static int handle_truncate(struct file *filp) { const struct path *path = &filp->f_path; struct inode *inode = path->dentry->d_inode; int error = get_write_access(inode); if (error) return error; /* * Refuse to truncate files with mandatory locks held on them. */ error = locks_verify_locked(filp); if (!error) error = security_path_truncate(path); if (!error) { error = do_truncate(path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } put_write_access(inode); return error; } static inline int open_to_namei_flags(int flag) { if ((flag & O_ACCMODE) == 3) flag--; return flag; } static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode) { struct user_namespace *s_user_ns; int error = security_path_mknod(dir, dentry, mode, 0); if (error) return error; s_user_ns = dir->dentry->d_sb->s_user_ns; if (!kuid_has_mapping(s_user_ns, current_fsuid()) || !kgid_has_mapping(s_user_ns, current_fsgid())) return -EOVERFLOW; error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; return security_inode_create(dir->dentry->d_inode, dentry, mode); } /* * Attempt to atomically look up, create and open a file from a negative * dentry. * * Returns 0 if successful. The file will have been created and attached to * @file by the filesystem calling finish_open(). * * If the file was looked up only or didn't need creating, FMODE_OPENED won't * be set. The caller will need to perform the open themselves. @path will * have been updated to point to the new dentry. This may be negative. * * Returns an error code otherwise. */ static struct dentry *atomic_open(struct nameidata *nd, struct dentry *dentry, struct file *file, int open_flag, umode_t mode) { struct dentry *const DENTRY_NOT_SET = (void *) -1UL; struct inode *dir = nd->path.dentry->d_inode; int error; if (nd->flags & LOOKUP_DIRECTORY) open_flag |= O_DIRECTORY; file->f_path.dentry = DENTRY_NOT_SET; file->f_path.mnt = nd->path.mnt; error = dir->i_op->atomic_open(dir, dentry, file, open_to_namei_flags(open_flag), mode); d_lookup_done(dentry); if (!error) { if (file->f_mode & FMODE_OPENED) { if (unlikely(dentry != file->f_path.dentry)) { dput(dentry); dentry = dget(file->f_path.dentry); } } else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) { error = -EIO; } else { if (file->f_path.dentry) { dput(dentry); dentry = file->f_path.dentry; } if (unlikely(d_is_negative(dentry))) error = -ENOENT; } } if (error) { dput(dentry); dentry = ERR_PTR(error); } return dentry; } /* * Look up and maybe create and open the last component. * * Must be called with parent locked (exclusive in O_CREAT case). * * Returns 0 on success, that is, if * the file was successfully atomically created (if necessary) and opened, or * the file was not completely opened at this time, though lookups and * creations were performed. * These case are distinguished by presence of FMODE_OPENED on file->f_mode. * In the latter case dentry returned in @path might be negative if O_CREAT * hadn't been specified. * * An error code is returned on failure. */ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, const struct open_flags *op, bool got_write) { struct dentry *dir = nd->path.dentry; struct inode *dir_inode = dir->d_inode; int open_flag = op->open_flag; struct dentry *dentry; int error, create_error = 0; umode_t mode = op->mode; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); if (unlikely(IS_DEADDIR(dir_inode))) return ERR_PTR(-ENOENT); file->f_mode &= ~FMODE_CREATED; dentry = d_lookup(dir, &nd->last); for (;;) { if (!dentry) { dentry = d_alloc_parallel(dir, &nd->last, &wq); if (IS_ERR(dentry)) return dentry; } if (d_in_lookup(dentry)) break; error = d_revalidate(dentry, nd->flags); if (likely(error > 0)) break; if (error) goto out_dput; d_invalidate(dentry); dput(dentry); dentry = NULL; } if (dentry->d_inode) { /* Cached positive dentry: will open in f_op->open */ return dentry; } /* * Checking write permission is tricky, bacuse we don't know if we are * going to actually need it: O_CREAT opens should work as long as the * file exists. But checking existence breaks atomicity. The trick is * to check access and if not granted clear O_CREAT from the flags. * * Another problem is returing the "right" error value (e.g. for an * O_EXCL open we want to return EEXIST not EROFS). */ if (unlikely(!got_write)) open_flag &= ~O_TRUNC; if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; mode = vfs_prepare_mode(dir->d_inode, mode, mode, mode); if (likely(got_write)) create_error = may_o_create(&nd->path, dentry, mode); else create_error = -EROFS; } if (create_error) open_flag &= ~O_CREAT; if (dir_inode->i_op->atomic_open) { dentry = atomic_open(nd, dentry, file, open_flag, mode); if (unlikely(create_error) && dentry == ERR_PTR(-ENOENT)) dentry = ERR_PTR(create_error); return dentry; } if (d_in_lookup(dentry)) { struct dentry *res = dir_inode->i_op->lookup(dir_inode, dentry, nd->flags); d_lookup_done(dentry); if (unlikely(res)) { if (IS_ERR(res)) { error = PTR_ERR(res); goto out_dput; } dput(dentry); dentry = res; } } /* Negative dentry, just create the file */ if (!dentry->d_inode && (open_flag & O_CREAT)) { file->f_mode |= FMODE_CREATED; audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE); if (!dir_inode->i_op->create) { error = -EACCES; goto out_dput; } error = dir_inode->i_op->create(dir_inode, dentry, mode, open_flag & O_EXCL); if (error) goto out_dput; } if (unlikely(create_error) && !dentry->d_inode) { error = create_error; goto out_dput; } return dentry; out_dput: dput(dentry); return ERR_PTR(error); } static const char *open_last_lookups(struct nameidata *nd, struct file *file, const struct open_flags *op) { struct dentry *dir = nd->path.dentry; int open_flag = op->open_flag; bool got_write = false; unsigned seq; struct inode *inode; struct dentry *dentry; const char *res; nd->flags |= op->intent; if (nd->last_type != LAST_NORM) { if (nd->depth) put_link(nd); return handle_dots(nd, nd->last_type); } if (!(open_flag & O_CREAT)) { if (nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; /* we _can_ be in RCU mode here */ dentry = lookup_fast(nd, &inode, &seq); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (likely(dentry)) goto finish_lookup; BUG_ON(nd->flags & LOOKUP_RCU); } else { /* create side of things */ if (nd->flags & LOOKUP_RCU) { if (!try_to_unlazy(nd)) return ERR_PTR(-ECHILD); } audit_inode(nd->name, dir, AUDIT_INODE_PARENT); /* trailing slashes? */ if (unlikely(nd->last.name[nd->last.len])) return ERR_PTR(-EISDIR); } if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) { got_write = !mnt_want_write(nd->path.mnt); /* * do _not_ fail yet - we might not need that or fail with * a different error; let lookup_open() decide; we'll be * dropping this one anyway. */ } if (open_flag & O_CREAT) inode_lock(dir->d_inode); else inode_lock_shared(dir->d_inode); dentry = lookup_open(nd, file, op, got_write); if (!IS_ERR(dentry) && (file->f_mode & FMODE_CREATED)) fsnotify_create(dir->d_inode, dentry); if (open_flag & O_CREAT) inode_unlock(dir->d_inode); else inode_unlock_shared(dir->d_inode); if (got_write) mnt_drop_write(nd->path.mnt); if (IS_ERR(dentry)) return ERR_CAST(dentry); if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) { dput(nd->path.dentry); nd->path.dentry = dentry; return NULL; } finish_lookup: if (nd->depth) put_link(nd); res = step_into(nd, WALK_TRAILING, dentry, inode, seq); if (unlikely(res)) nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL); return res; } /* * Handle the last step of open() */ static int do_open(struct nameidata *nd, struct file *file, const struct open_flags *op) { int open_flag = op->open_flag; bool do_truncate; int acc_mode; int error; if (!(file->f_mode & (FMODE_OPENED | FMODE_CREATED))) { error = complete_walk(nd); if (error) return error; } if (!(file->f_mode & FMODE_CREATED)) audit_inode(nd->name, nd->path.dentry, 0); if (open_flag & O_CREAT) { if ((open_flag & O_EXCL) && !(file->f_mode & FMODE_CREATED)) return -EEXIST; if (d_is_dir(nd->path.dentry)) return -EISDIR; error = may_create_in_sticky(nd->dir_mode, nd->dir_uid, d_backing_inode(nd->path.dentry)); if (unlikely(error)) return error; } if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) return -ENOTDIR; do_truncate = false; acc_mode = op->acc_mode; if (file->f_mode & FMODE_CREATED) { /* Don't check for write permission, don't truncate */ open_flag &= ~O_TRUNC; acc_mode = 0; } else if (d_is_reg(nd->path.dentry) && open_flag & O_TRUNC) { error = mnt_want_write(nd->path.mnt); if (error) return error; do_truncate = true; } error = may_open(&nd->path, acc_mode, open_flag); if (!error && !(file->f_mode & FMODE_OPENED)) error = vfs_open(&nd->path, file); if (!error) error = ima_file_check(file, op->acc_mode); if (!error && do_truncate) error = handle_truncate(file); if (unlikely(error > 0)) { WARN_ON(1); error = -EINVAL; } if (do_truncate) mnt_drop_write(nd->path.mnt); return error; } struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) { struct dentry *child = NULL; struct inode *dir = dentry->d_inode; struct inode *inode; int error; /* we want directory to be writable */ error = inode_permission(dir, MAY_WRITE | MAY_EXEC); if (error) goto out_err; error = -EOPNOTSUPP; if (!dir->i_op->tmpfile) goto out_err; error = -ENOMEM; child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; mode = vfs_prepare_mode(dir, mode, mode, mode); error = dir->i_op->tmpfile(dir, child, mode); if (error) goto out_err; error = -ENOENT; inode = child->d_inode; if (unlikely(!inode)) goto out_err; if (!(open_flag & O_EXCL)) { spin_lock(&inode->i_lock); inode->i_state |= I_LINKABLE; spin_unlock(&inode->i_lock); } ima_post_create_tmpfile(inode); return child; out_err: dput(child); return ERR_PTR(error); } EXPORT_SYMBOL(vfs_tmpfile); static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, struct file *file) { struct dentry *child; struct path path; int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path); if (unlikely(error)) return error; error = mnt_want_write(path.mnt); if (unlikely(error)) goto out; child = vfs_tmpfile(path.dentry, op->mode, op->open_flag); error = PTR_ERR(child); if (IS_ERR(child)) goto out2; dput(path.dentry); path.dentry = child; audit_inode(nd->name, child, 0); /* Don't check for other permissions, the inode was just created */ error = may_open(&path, 0, op->open_flag); if (error) goto out2; file->f_path.mnt = path.mnt; error = finish_open(file, child, NULL); out2: mnt_drop_write(path.mnt); out: path_put(&path); return error; } static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file) { struct path path; int error = path_lookupat(nd, flags, &path); if (!error) { audit_inode(nd->name, path.dentry, 0); error = vfs_open(&path, file); path_put(&path); } return error; } static struct file *path_openat(struct nameidata *nd, const struct open_flags *op, unsigned flags) { struct file *file; int error; file = alloc_empty_file(op->open_flag, current_cred()); if (IS_ERR(file)) return file; if (unlikely(file->f_flags & __O_TMPFILE)) { error = do_tmpfile(nd, flags, op, file); } else if (unlikely(file->f_flags & O_PATH)) { error = do_o_path(nd, flags, file); } else { const char *s = path_init(nd, flags); while (!(error = link_path_walk(s, nd)) && (s = open_last_lookups(nd, file, op)) != NULL) ; if (!error) error = do_open(nd, file, op); terminate_walk(nd); } if (likely(!error)) { if (likely(file->f_mode & FMODE_OPENED)) return file; WARN_ON(1); error = -EINVAL; } fput(file); if (error == -EOPENSTALE) { if (flags & LOOKUP_RCU) error = -ECHILD; else error = -ESTALE; } return ERR_PTR(error); } struct file *do_filp_open(int dfd, struct filename *pathname, const struct open_flags *op) { struct nameidata nd; int flags = op->lookup_flags; struct file *filp; set_nameidata(&nd, dfd, pathname); filp = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(filp == ERR_PTR(-ECHILD))) filp = path_openat(&nd, op, flags); if (unlikely(filp == ERR_PTR(-ESTALE))) filp = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); return filp; } struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt, const char *name, const struct open_flags *op) { struct nameidata nd; struct file *file; struct filename *filename; int flags = op->lookup_flags | LOOKUP_ROOT; nd.root.mnt = mnt; nd.root.dentry = dentry; if (d_is_symlink(dentry) && op->intent & LOOKUP_OPEN) return ERR_PTR(-ELOOP); filename = getname_kernel(name); if (IS_ERR(filename)) return ERR_CAST(filename); set_nameidata(&nd, -1, filename); file = path_openat(&nd, op, flags | LOOKUP_RCU); if (unlikely(file == ERR_PTR(-ECHILD))) file = path_openat(&nd, op, flags); if (unlikely(file == ERR_PTR(-ESTALE))) file = path_openat(&nd, op, flags | LOOKUP_REVAL); restore_nameidata(); putname(filename); return file; } static struct dentry *filename_create(int dfd, struct filename *name, struct path *path, unsigned int lookup_flags) { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; int type; int err2; int error; bool is_dir = (lookup_flags & LOOKUP_DIRECTORY); /* * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any * other flags passed in are ignored! */ lookup_flags &= LOOKUP_REVAL; name = filename_parentat(dfd, name, lookup_flags, path, &last, &type); if (IS_ERR(name)) return ERR_CAST(name); /* * Yucky last component or no last component at all? * (foo/., foo/.., /////) */ if (unlikely(type != LAST_NORM)) goto out; /* don't fail immediately if it's r/o, at least try to report other errors */ err2 = mnt_want_write(path->mnt); /* * Do the final lookup. */ lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path->dentry, lookup_flags); if (IS_ERR(dentry)) goto unlock; error = -EEXIST; if (d_is_positive(dentry)) goto fail; /* * Special case - lookup gave negative, but... we had foo/bar/ * From the vfs_mknod() POV we just have a negative dentry - * all is fine. Let's be bastards - you had / on the end, you've * been asking for (non-existent) directory. -ENOENT for you. */ if (unlikely(!is_dir && last.name[last.len])) { error = -ENOENT; goto fail; } if (unlikely(err2)) { error = err2; goto fail; } putname(name); return dentry; fail: dput(dentry); dentry = ERR_PTR(error); unlock: inode_unlock(path->dentry->d_inode); if (!err2) mnt_drop_write(path->mnt); out: path_put(path); putname(name); return dentry; } struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path, unsigned int lookup_flags) { return filename_create(dfd, getname_kernel(pathname), path, lookup_flags); } EXPORT_SYMBOL(kern_path_create); void done_path_create(struct path *path, struct dentry *dentry) { dput(dentry); inode_unlock(path->dentry->d_inode); mnt_drop_write(path->mnt); path_put(path); } EXPORT_SYMBOL(done_path_create); inline struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, unsigned int lookup_flags) { return filename_create(dfd, getname(pathname), path, lookup_flags); } EXPORT_SYMBOL(user_path_create); int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV; int error = may_create(dir, dentry); if (error) return error; if ((S_ISCHR(mode) || S_ISBLK(mode)) && !is_whiteout && !capable(CAP_MKNOD)) return -EPERM; if (!dir->i_op->mknod) return -EPERM; mode = vfs_prepare_mode(dir, mode, mode, mode); error = devcgroup_inode_mknod(mode, dev); if (error) return error; error = security_inode_mknod(dir, dentry, mode, dev); if (error) return error; error = dir->i_op->mknod(dir, dentry, mode, dev); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mknod); static int may_mknod(umode_t mode) { switch (mode & S_IFMT) { case S_IFREG: case S_IFCHR: case S_IFBLK: case S_IFIFO: case S_IFSOCK: case 0: /* zero mode translates to S_IFREG */ return 0; case S_IFDIR: return -EPERM; default: return -EINVAL; } } static long do_mknodat(int dfd, const char __user *filename, umode_t mode, unsigned int dev) { struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = 0; error = may_mknod(mode); if (error) return error; retry: dentry = user_path_create(dfd, filename, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_path_mknod(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode), dev); if (error) goto out; switch (mode & S_IFMT) { case 0: case S_IFREG: error = vfs_create(path.dentry->d_inode,dentry,mode,true); if (!error) ima_post_path_mknod(dentry); break; case S_IFCHR: case S_IFBLK: error = vfs_mknod(path.dentry->d_inode,dentry,mode, new_decode_dev(dev)); break; case S_IFIFO: case S_IFSOCK: error = vfs_mknod(path.dentry->d_inode,dentry,mode,0); break; } out: done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned int, dev) { return do_mknodat(dfd, filename, mode, dev); } SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev) { return do_mknodat(AT_FDCWD, filename, mode, dev); } int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { int error = may_create(dir, dentry); unsigned max_links = dir->i_sb->s_max_links; if (error) return error; if (!dir->i_op->mkdir) return -EPERM; mode = vfs_prepare_mode(dir, mode, S_IRWXUGO | S_ISVTX, 0); error = security_inode_mkdir(dir, dentry, mode); if (error) return error; if (max_links && dir->i_nlink >= max_links) return -EMLINK; error = dir->i_op->mkdir(dir, dentry, mode); if (!error) fsnotify_mkdir(dir, dentry); return error; } EXPORT_SYMBOL(vfs_mkdir); static long do_mkdirat(int dfd, const char __user *pathname, umode_t mode) { struct dentry *dentry; struct path path; int error; unsigned int lookup_flags = LOOKUP_DIRECTORY; retry: dentry = user_path_create(dfd, pathname, &path, lookup_flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_path_mkdir(&path, dentry, mode_strip_umask(path.dentry->d_inode, mode)); if (!error) error = vfs_mkdir(path.dentry->d_inode, dentry, mode); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) { return do_mkdirat(dfd, pathname, mode); } SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) { return do_mkdirat(AT_FDCWD, pathname, mode); } int vfs_rmdir(struct inode *dir, struct dentry *dentry) { int error = may_delete(dir, dentry, 1); if (error) return error; if (!dir->i_op->rmdir) return -EPERM; dget(dentry); inode_lock(dentry->d_inode); error = -EBUSY; if (is_local_mountpoint(dentry)) goto out; error = security_inode_rmdir(dir, dentry); if (error) goto out; error = dir->i_op->rmdir(dir, dentry); if (error) goto out; shrink_dcache_parent(dentry); dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); detach_mounts(dentry); out: inode_unlock(dentry->d_inode); dput(dentry); if (!error) d_delete_notify(dir, dentry); return error; } EXPORT_SYMBOL(vfs_rmdir); long do_rmdir(int dfd, struct filename *name) { int error = 0; struct dentry *dentry; struct path path; struct qstr last; int type; unsigned int lookup_flags = 0; retry: name = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (IS_ERR(name)) return PTR_ERR(name); switch (type) { case LAST_DOTDOT: error = -ENOTEMPTY; goto exit1; case LAST_DOT: error = -EINVAL; goto exit1; case LAST_ROOT: error = -EBUSY; goto exit1; } error = mnt_want_write(path.mnt); if (error) goto exit1; inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto exit2; if (!dentry->d_inode) { error = -ENOENT; goto exit3; } error = security_path_rmdir(&path, dentry); if (error) goto exit3; error = vfs_rmdir(path.dentry->d_inode, dentry); exit3: dput(dentry); exit2: inode_unlock(path.dentry->d_inode); mnt_drop_write(path.mnt); exit1: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } putname(name); return error; } SYSCALL_DEFINE1(rmdir, const char __user *, pathname) { return do_rmdir(AT_FDCWD, getname(pathname)); } /** * vfs_unlink - unlink a filesystem object * @dir: parent directory * @dentry: victim * @delegated_inode: returns victim inode, if the inode is delegated. * * The caller must hold dir->i_mutex. * * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and * return a reference to the inode in delegated_inode. The caller * should then break the delegation on that inode and retry. Because * breaking a delegation may take a long time, the caller should drop * dir->i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. */ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) { struct inode *target = dentry->d_inode; int error = may_delete(dir, dentry, 0); if (error) return error; if (!dir->i_op->unlink) return -EPERM; inode_lock(target); if (is_local_mountpoint(dentry)) error = -EBUSY; else { error = security_inode_unlink(dir, dentry); if (!error) { error = try_break_deleg(target, delegated_inode); if (error) goto out; error = dir->i_op->unlink(dir, dentry); if (!error) { dont_mount(dentry); detach_mounts(dentry); } } } out: inode_unlock(target); /* We don't d_delete() NFS sillyrenamed files--they still exist. */ if (!error && dentry->d_flags & DCACHE_NFSFS_RENAMED) { fsnotify_unlink(dir, dentry); } else if (!error) { fsnotify_link_count(target); d_delete_notify(dir, dentry); } return error; } EXPORT_SYMBOL(vfs_unlink); /* * Make sure that the actual truncation of the file will occur outside its * directory's i_mutex. Truncate can take a long time if there is a lot of * writeout happening, and we don't want to prevent access to the directory * while waiting on the I/O. */ long do_unlinkat(int dfd, struct filename *name) { int error; struct dentry *dentry; struct path path; struct qstr last; int type; struct inode *inode = NULL; struct inode *delegated_inode = NULL; unsigned int lookup_flags = 0; retry: name = filename_parentat(dfd, name, lookup_flags, &path, &last, &type); if (IS_ERR(name)) return PTR_ERR(name); error = -EISDIR; if (type != LAST_NORM) goto exit1; error = mnt_want_write(path.mnt); if (error) goto exit1; retry_deleg: inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT); dentry = __lookup_hash(&last, path.dentry, lookup_flags); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { /* Why not before? Because we want correct error value */ if (last.name[last.len]) goto slashes; inode = dentry->d_inode; if (d_is_negative(dentry)) goto slashes; ihold(inode); error = security_path_unlink(&path, dentry); if (error) goto exit2; error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode); exit2: dput(dentry); } inode_unlock(path.dentry->d_inode); if (inode) iput(inode); /* truncate the inode here */ inode = NULL; if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(path.mnt); exit1: path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; inode = NULL; goto retry; } putname(name); return error; slashes: if (d_is_negative(dentry)) error = -ENOENT; else if (d_is_dir(dentry)) error = -EISDIR; else error = -ENOTDIR; goto exit2; } SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag) { if ((flag & ~AT_REMOVEDIR) != 0) return -EINVAL; if (flag & AT_REMOVEDIR) return do_rmdir(dfd, getname(pathname)); return do_unlinkat(dfd, getname(pathname)); } SYSCALL_DEFINE1(unlink, const char __user *, pathname) { return do_unlinkat(AT_FDCWD, getname(pathname)); } int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) { int error = may_create(dir, dentry); if (error) return error; if (!dir->i_op->symlink) return -EPERM; error = security_inode_symlink(dir, dentry, oldname); if (error) return error; error = dir->i_op->symlink(dir, dentry, oldname); if (!error) fsnotify_create(dir, dentry); return error; } EXPORT_SYMBOL(vfs_symlink); static long do_symlinkat(const char __user *oldname, int newdfd, const char __user *newname) { int error; struct filename *from; struct dentry *dentry; struct path path; unsigned int lookup_flags = 0; from = getname(oldname); if (IS_ERR(from)) return PTR_ERR(from); retry: dentry = user_path_create(newdfd, newname, &path, lookup_flags); error = PTR_ERR(dentry); if (IS_ERR(dentry)) goto out_putname; error = security_path_symlink(&path, dentry, from->name); if (!error) error = vfs_symlink(path.dentry->d_inode, dentry, from->name); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } out_putname: putname(from); return error; } SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname) { return do_symlinkat(oldname, newdfd, newname); } SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname) { return do_symlinkat(oldname, AT_FDCWD, newname); } /** * vfs_link - create a new link * @old_dentry: object to be linked * @dir: new parent * @new_dentry: where to create the new link * @delegated_inode: returns inode needing a delegation break * * The caller must hold dir->i_mutex * * If vfs_link discovers a delegation on the to-be-linked file in need * of breaking, it will return -EWOULDBLOCK and return a reference to the * inode in delegated_inode. The caller should then break the delegation * and retry. Because breaking a delegation may take a long time, the * caller should drop the i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. */ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) { struct inode *inode = old_dentry->d_inode; unsigned max_links = dir->i_sb->s_max_links; int error; if (!inode) return -ENOENT; error = may_create(dir, new_dentry); if (error) return error; if (dir->i_sb != inode->i_sb) return -EXDEV; /* * A link to an append-only or immutable file cannot be created. */ if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return -EPERM; /* * Updating the link count will likely cause i_uid and i_gid to * be writen back improperly if their true value is unknown to * the vfs. */ if (HAS_UNMAPPED_ID(inode)) return -EPERM; if (!dir->i_op->link) return -EPERM; if (S_ISDIR(inode->i_mode)) return -EPERM; error = security_inode_link(old_dentry, dir, new_dentry); if (error) return error; inode_lock(inode); /* Make sure we don't allow creating hardlink to an unlinked file */ if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE)) error = -ENOENT; else if (max_links && inode->i_nlink >= max_links) error = -EMLINK; else { error = try_break_deleg(inode, delegated_inode); if (!error) error = dir->i_op->link(old_dentry, dir, new_dentry); } if (!error && (inode->i_state & I_LINKABLE)) { spin_lock(&inode->i_lock); inode->i_state &= ~I_LINKABLE; spin_unlock(&inode->i_lock); } inode_unlock(inode); if (!error) fsnotify_link(dir, inode, new_dentry); return error; } EXPORT_SYMBOL(vfs_link); /* * Hardlinks are often used in delicate situations. We avoid * security-related surprises by not following symlinks on the * newname. --KAB * * We don't follow them on the oldname either to be compatible * with linux 2.0, and to avoid hard-linking to directories * and other special files. --ADM */ static int do_linkat(int olddfd, const char __user *oldname, int newdfd, const char __user *newname, int flags) { struct dentry *new_dentry; struct path old_path, new_path; struct inode *delegated_inode = NULL; int how = 0; int error; if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; /* * To use null names we require CAP_DAC_READ_SEARCH * This ensures that not everyone will be able to create * handlink using the passed filedescriptor. */ if (flags & AT_EMPTY_PATH) { if (!capable(CAP_DAC_READ_SEARCH)) return -ENOENT; how = LOOKUP_EMPTY; } if (flags & AT_SYMLINK_FOLLOW) how |= LOOKUP_FOLLOW; retry: error = user_path_at(olddfd, oldname, how, &old_path); if (error) return error; new_dentry = user_path_create(newdfd, newname, &new_path, (how & LOOKUP_REVAL)); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto out; error = -EXDEV; if (old_path.mnt != new_path.mnt) goto out_dput; error = may_linkat(&old_path); if (unlikely(error)) goto out_dput; error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode); out_dput: done_path_create(&new_path, new_dentry); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) { path_put(&old_path); goto retry; } } if (retry_estale(error, how)) { path_put(&old_path); how |= LOOKUP_REVAL; goto retry; } out: path_put(&old_path); return error; } SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags) { return do_linkat(olddfd, oldname, newdfd, newname, flags); } SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname) { return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } /** * vfs_rename - rename a filesystem object * @old_dir: parent of source * @old_dentry: source * @new_dir: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags * * The caller must hold multiple mutexes--see lock_rename()). * * If vfs_rename discovers a delegation in need of breaking at either * the source or destination, it will return -EWOULDBLOCK and return a * reference to the inode in delegated_inode. The caller should then * break the delegation and retry. Because breaking a delegation may * take a long time, the caller should drop all locks before doing * so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * The worst of all namespace operations - renaming directory. "Perverted" * doesn't even start to describe it. Somebody in UCB had a heck of a trip... * Problems: * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. * That's where 4.4BSD screws up. Current fix: serialization on * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. * c) we may have to lock up to _four_ objects - parents and victim (if it exists), * and source (if it's a non-directory or a subdirectory that moves to * different parent). * And that - after we got ->i_mutex on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change * only under ->s_vfs_rename_mutex _and_ that parent of the object we * move will be locked. Thus we can rank directories by the tree * (ancestors first) and rank all non-directories after them. * That works since everybody except rename does "lock parent, lookup, * lock child" and rename is under ->s_vfs_rename_mutex. * HOWEVER, it relies on the assumption that any object with ->lookup() * has no more than 1 dentry. If "hybrid" objects will ever appear, * we'd better make sure that there's no link(2) for them. * d) conversion from fhandle to dentry may come in the wrong moment - when * we are removing the target. Solution: we will have to grab ->i_mutex * in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ int vfs_rename(struct renamedata *rd) { int error; struct inode *old_dir = rd->old_dir, *new_dir = rd->new_dir; struct dentry *old_dentry = rd->old_dentry; struct dentry *new_dentry = rd->new_dentry; struct inode **delegated_inode = rd->delegated_inode; unsigned int flags = rd->flags; bool is_dir = d_is_dir(old_dentry); struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; struct name_snapshot old_name; bool lock_old_subdir, lock_new_subdir; if (source == target) return 0; error = may_delete(old_dir, old_dentry, is_dir); if (error) return error; if (!target) { error = may_create(new_dir, new_dentry); } else { new_is_dir = d_is_dir(new_dentry); if (!(flags & RENAME_EXCHANGE)) error = may_delete(new_dir, new_dentry, is_dir); else error = may_delete(new_dir, new_dentry, new_is_dir); } if (error) return error; if (!old_dir->i_op->rename) return -EPERM; /* * If we are going to change the parent - check write permissions, * we'll need to flip '..'. */ if (new_dir != old_dir) { if (is_dir) { error = inode_permission(source, MAY_WRITE); if (error) return error; } if ((flags & RENAME_EXCHANGE) && new_is_dir) { error = inode_permission(target, MAY_WRITE); if (error) return error; } } error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry, flags); if (error) return error; take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); /* * Lock children. * The source subdirectory needs to be locked on cross-directory * rename or cross-directory exchange since its parent changes. * The target subdirectory needs to be locked on cross-directory * exchange due to parent change and on any rename due to becoming * a victim. * Non-directories need locking in all cases (for NFS reasons); * they get locked after any subdirectories (in inode address order). * * NOTE: WE ONLY LOCK UNRELATED DIRECTORIES IN CROSS-DIRECTORY CASE. * NEVER, EVER DO THAT WITHOUT ->s_vfs_rename_mutex. */ lock_old_subdir = new_dir != old_dir; lock_new_subdir = new_dir != old_dir || !(flags & RENAME_EXCHANGE); if (is_dir) { if (lock_old_subdir) inode_lock_nested(source, I_MUTEX_CHILD); if (target && (!new_is_dir || lock_new_subdir)) inode_lock(target); } else if (new_is_dir) { if (lock_new_subdir) inode_lock_nested(target, I_MUTEX_CHILD); inode_lock(source); } else { lock_two_nondirectories(source, target); } error = -EBUSY; if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry)) goto out; if (max_links && new_dir != old_dir) { error = -EMLINK; if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links) goto out; if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir && old_dir->i_nlink >= max_links) goto out; } if (!is_dir) { error = try_break_deleg(source, delegated_inode); if (error) goto out; } if (target && !new_is_dir) { error = try_break_deleg(target, delegated_inode); if (error) goto out; } error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry, flags); if (error) goto out; if (!(flags & RENAME_EXCHANGE) && target) { if (is_dir) { shrink_dcache_parent(new_dentry); target->i_flags |= S_DEAD; } dont_mount(new_dentry); detach_mounts(new_dentry); } if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) { if (!(flags & RENAME_EXCHANGE)) d_move(old_dentry, new_dentry); else d_exchange(old_dentry, new_dentry); } out: if (!is_dir || lock_old_subdir) inode_unlock(source); if (target && (!new_is_dir || lock_new_subdir)) inode_unlock(target); dput(new_dentry); if (!error) { fsnotify_move(old_dir, new_dir, &old_name.name, is_dir, !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry); if (flags & RENAME_EXCHANGE) { fsnotify_move(new_dir, old_dir, &old_dentry->d_name, new_is_dir, NULL, new_dentry); } } release_dentry_name_snapshot(&old_name); return error; } EXPORT_SYMBOL(vfs_rename); int do_renameat2(int olddfd, struct filename *from, int newdfd, struct filename *to, unsigned int flags) { struct renamedata rd; struct dentry *old_dentry, *new_dentry; struct dentry *trap; struct path old_path, new_path; struct qstr old_last, new_last; int old_type, new_type; struct inode *delegated_inode = NULL; unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET; bool should_retry = false; int error = -EINVAL; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) goto put_both; if ((flags & (RENAME_NOREPLACE | RENAME_WHITEOUT)) && (flags & RENAME_EXCHANGE)) goto put_both; if (flags & RENAME_EXCHANGE) target_flags = 0; retry: from = filename_parentat(olddfd, from, lookup_flags, &old_path, &old_last, &old_type); if (IS_ERR(from)) { error = PTR_ERR(from); goto put_new; } to = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last, &new_type); if (IS_ERR(to)) { error = PTR_ERR(to); goto exit1; } error = -EXDEV; if (old_path.mnt != new_path.mnt) goto exit2; error = -EBUSY; if (old_type != LAST_NORM) goto exit2; if (flags & RENAME_NOREPLACE) error = -EEXIST; if (new_type != LAST_NORM) goto exit2; error = mnt_want_write(old_path.mnt); if (error) goto exit2; retry_deleg: trap = lock_rename(new_path.dentry, old_path.dentry); old_dentry = __lookup_hash(&old_last, old_path.dentry, lookup_flags); error = PTR_ERR(old_dentry); if (IS_ERR(old_dentry)) goto exit3; /* source must exist */ error = -ENOENT; if (d_is_negative(old_dentry)) goto exit4; new_dentry = __lookup_hash(&new_last, new_path.dentry, lookup_flags | target_flags); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto exit4; error = -EEXIST; if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) goto exit5; if (flags & RENAME_EXCHANGE) { error = -ENOENT; if (d_is_negative(new_dentry)) goto exit5; if (!d_is_dir(new_dentry)) { error = -ENOTDIR; if (new_last.name[new_last.len]) goto exit5; } } /* unless the source is a directory trailing slashes give -ENOTDIR */ if (!d_is_dir(old_dentry)) { error = -ENOTDIR; if (old_last.name[old_last.len]) goto exit5; if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len]) goto exit5; } /* source should not be ancestor of target */ error = -EINVAL; if (old_dentry == trap) goto exit5; /* target should not be an ancestor of source */ if (!(flags & RENAME_EXCHANGE)) error = -ENOTEMPTY; if (new_dentry == trap) goto exit5; error = security_path_rename(&old_path, old_dentry, &new_path, new_dentry, flags); if (error) goto exit5; rd.old_dir = old_path.dentry->d_inode; rd.old_dentry = old_dentry; rd.new_dir = new_path.dentry->d_inode; rd.new_dentry = new_dentry; rd.delegated_inode = &delegated_inode; rd.flags = flags; error = vfs_rename(&rd); exit5: dput(new_dentry); exit4: dput(old_dentry); exit3: unlock_rename(new_path.dentry, old_path.dentry); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(old_path.mnt); exit2: if (retry_estale(error, lookup_flags)) should_retry = true; path_put(&new_path); exit1: path_put(&old_path); if (should_retry) { should_retry = false; lookup_flags |= LOOKUP_REVAL; goto retry; } put_both: if (!IS_ERR(from)) putname(from); put_new: if (!IS_ERR(to)) putname(to); return error; } SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags) { return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), flags); } SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname) { return do_renameat2(olddfd, getname(oldname), newdfd, getname(newname), 0); } SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { return do_renameat2(AT_FDCWD, getname(oldname), AT_FDCWD, getname(newname), 0); } int readlink_copy(char __user *buffer, int buflen, const char *link) { int len = PTR_ERR(link); if (IS_ERR(link)) goto out; len = strlen(link); if (len > (unsigned) buflen) len = buflen; if (copy_to_user(buffer, link, len)) len = -EFAULT; out: return len; } /** * vfs_readlink - copy symlink body into userspace buffer * @dentry: dentry on which to get symbolic link * @buffer: user memory pointer * @buflen: size of buffer * * Does not touch atime. That's up to the caller if necessary * * Does not call security hook. */ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen) { struct inode *inode = d_inode(dentry); DEFINE_DELAYED_CALL(done); const char *link; int res; if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) { if (unlikely(inode->i_op->readlink)) return inode->i_op->readlink(dentry, buffer, buflen); if (!d_is_symlink(dentry)) return -EINVAL; spin_lock(&inode->i_lock); inode->i_opflags |= IOP_DEFAULT_READLINK; spin_unlock(&inode->i_lock); } link = READ_ONCE(inode->i_link); if (!link) { link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) return PTR_ERR(link); } res = readlink_copy(buffer, buflen, link); do_delayed_call(&done); return res; } EXPORT_SYMBOL(vfs_readlink); /** * vfs_get_link - get symlink body * @dentry: dentry on which to get symbolic link * @done: caller needs to free returned data with this * * Calls security hook and i_op->get_link() on the supplied inode. * * It does not touch atime. That's up to the caller if necessary. * * Does not work on "special" symlinks like /proc/$$/fd/N */ const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done) { const char *res = ERR_PTR(-EINVAL); struct inode *inode = d_inode(dentry); if (d_is_symlink(dentry)) { res = ERR_PTR(security_inode_readlink(dentry)); if (!res) res = inode->i_op->get_link(dentry, inode, done); } return res; } EXPORT_SYMBOL(vfs_get_link); /* get the link contents into pagecache */ static char *__page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { struct page *page; struct address_space *mapping = inode->i_mapping; if (!dentry) { page = find_get_page(mapping, 0); if (!page) return ERR_PTR(-ECHILD); if (!PageUptodate(page)) { put_page(page); return ERR_PTR(-ECHILD); } } else { page = read_mapping_page(mapping, 0, NULL); if (IS_ERR(page)) return (char*)page; } set_delayed_call(callback, page_put_link, page); BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM); return page_address(page); } const char *page_get_link_raw(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { return __page_get_link(dentry, inode, callback); } EXPORT_SYMBOL_GPL(page_get_link_raw); const char *page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { char *kaddr = __page_get_link(dentry, inode, callback); if (!IS_ERR(kaddr)) nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1); return kaddr; } EXPORT_SYMBOL(page_get_link); void page_put_link(void *arg) { put_page(arg); } EXPORT_SYMBOL(page_put_link); int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { DEFINE_DELAYED_CALL(done); int res = readlink_copy(buffer, buflen, page_get_link(dentry, d_inode(dentry), &done)); do_delayed_call(&done); return res; } EXPORT_SYMBOL(page_readlink); /* * The nofs argument instructs pagecache_write_begin to pass AOP_FLAG_NOFS */ int __page_symlink(struct inode *inode, const char *symname, int len, int nofs) { struct address_space *mapping = inode->i_mapping; struct page *page; void *fsdata = NULL; int err; unsigned int flags = 0; if (nofs) flags |= AOP_FLAG_NOFS; retry: err = pagecache_write_begin(NULL, mapping, 0, len-1, flags, &page, &fsdata); if (err) goto fail; memcpy(page_address(page), symname, len-1); err = pagecache_write_end(NULL, mapping, 0, len-1, len-1, page, fsdata); if (err < 0) goto fail; if (err < len-1) goto retry; mark_inode_dirty(inode); return 0; fail: return err; } EXPORT_SYMBOL(__page_symlink); int page_symlink(struct inode *inode, const char *symname, int len) { return __page_symlink(inode, symname, len, !mapping_gfp_constraint(inode->i_mapping, __GFP_FS)); } EXPORT_SYMBOL(page_symlink); const struct inode_operations page_symlink_inode_operations = { .get_link = page_get_link, }; EXPORT_SYMBOL(page_symlink_inode_operations); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the SID table type. * * Original author: Stephen Smalley, <sds@tycho.nsa.gov> * Author: Ondrej Mosnacek, <omosnacek@gmail.com> * * Copyright (C) 2018 Red Hat, Inc. */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <asm/barrier.h> #include "flask.h" #include "security.h" #include "sidtab.h" struct sidtab_str_cache { struct rcu_head rcu_member; struct list_head lru_member; struct sidtab_entry *parent; u32 len; char str[]; }; #define index_to_sid(index) (index + SECINITSID_NUM + 1) #define sid_to_index(sid) (sid - (SECINITSID_NUM + 1)) int sidtab_init(struct sidtab *s) { u32 i; memset(s->roots, 0, sizeof(s->roots)); for (i = 0; i < SECINITSID_NUM; i++) s->isids[i].set = 0; s->frozen = false; s->count = 0; s->convert = NULL; hash_init(s->context_to_sid); spin_lock_init(&s->lock); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 s->cache_free_slots = CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE; INIT_LIST_HEAD(&s->cache_lru_list); spin_lock_init(&s->cache_lock); #endif return 0; } static u32 context_to_sid(struct sidtab *s, struct context *context, u32 hash) { struct sidtab_entry *entry; u32 sid = 0; rcu_read_lock(); hash_for_each_possible_rcu(s->context_to_sid, entry, list, hash) { if (entry->hash != hash) continue; if (context_cmp(&entry->context, context)) { sid = entry->sid; break; } } rcu_read_unlock(); return sid; } int sidtab_set_initial(struct sidtab *s, u32 sid, struct context *context) { struct sidtab_isid_entry *isid; u32 hash; int rc; if (sid == 0 || sid > SECINITSID_NUM) return -EINVAL; isid = &s->isids[sid - 1]; rc = context_cpy(&isid->entry.context, context); if (rc) return rc; #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 isid->entry.cache = NULL; #endif isid->set = 1; hash = context_compute_hash(context); /* * Multiple initial sids may map to the same context. Check that this * context is not already represented in the context_to_sid hashtable * to avoid duplicate entries and long linked lists upon hash * collision. */ if (!context_to_sid(s, context, hash)) { isid->entry.sid = sid; isid->entry.hash = hash; hash_add(s->context_to_sid, &isid->entry.list, hash); } return 0; } int sidtab_hash_stats(struct sidtab *sidtab, char *page) { int i; int chain_len = 0; int slots_used = 0; int entries = 0; int max_chain_len = 0; int cur_bucket = 0; struct sidtab_entry *entry; rcu_read_lock(); hash_for_each_rcu(sidtab->context_to_sid, i, entry, list) { entries++; if (i == cur_bucket) { chain_len++; if (chain_len == 1) slots_used++; } else { cur_bucket = i; if (chain_len > max_chain_len) max_chain_len = chain_len; chain_len = 0; } } rcu_read_unlock(); if (chain_len > max_chain_len) max_chain_len = chain_len; return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n" "longest chain: %d\n", entries, slots_used, SIDTAB_HASH_BUCKETS, max_chain_len); } static u32 sidtab_level_from_count(u32 count) { u32 capacity = SIDTAB_LEAF_ENTRIES; u32 level = 0; while (count > capacity) { capacity <<= SIDTAB_INNER_SHIFT; ++level; } return level; } static int sidtab_alloc_roots(struct sidtab *s, u32 level) { u32 l; if (!s->roots[0].ptr_leaf) { s->roots[0].ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[0].ptr_leaf) return -ENOMEM; } for (l = 1; l <= level; ++l) if (!s->roots[l].ptr_inner) { s->roots[l].ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[l].ptr_inner) return -ENOMEM; s->roots[l].ptr_inner->entries[0] = s->roots[l - 1]; } return 0; } static struct sidtab_entry *sidtab_do_lookup(struct sidtab *s, u32 index, int alloc) { union sidtab_entry_inner *entry; u32 level, capacity_shift, leaf_index = index / SIDTAB_LEAF_ENTRIES; /* find the level of the subtree we need */ level = sidtab_level_from_count(index + 1); capacity_shift = level * SIDTAB_INNER_SHIFT; /* allocate roots if needed */ if (alloc && sidtab_alloc_roots(s, level) != 0) return NULL; /* lookup inside the subtree */ entry = &s->roots[level]; while (level != 0) { capacity_shift -= SIDTAB_INNER_SHIFT; --level; entry = &entry->ptr_inner->entries[leaf_index >> capacity_shift]; leaf_index &= ((u32)1 << capacity_shift) - 1; if (!entry->ptr_inner) { if (alloc) entry->ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_inner) return NULL; } } if (!entry->ptr_leaf) { if (alloc) entry->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_leaf) return NULL; } return &entry->ptr_leaf->entries[index % SIDTAB_LEAF_ENTRIES]; } static struct sidtab_entry *sidtab_lookup(struct sidtab *s, u32 index) { /* read entries only after reading count */ u32 count = smp_load_acquire(&s->count); if (index >= count) return NULL; return sidtab_do_lookup(s, index, 0); } static struct sidtab_entry *sidtab_lookup_initial(struct sidtab *s, u32 sid) { return s->isids[sid - 1].set ? &s->isids[sid - 1].entry : NULL; } static struct sidtab_entry *sidtab_search_core(struct sidtab *s, u32 sid, int force) { if (sid != 0) { struct sidtab_entry *entry; if (sid > SECINITSID_NUM) entry = sidtab_lookup(s, sid_to_index(sid)); else entry = sidtab_lookup_initial(s, sid); if (entry && (!entry->context.len || force)) return entry; } return sidtab_lookup_initial(s, SECINITSID_UNLABELED); } struct sidtab_entry *sidtab_search_entry(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 0); } struct sidtab_entry *sidtab_search_entry_force(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 1); } int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid) { unsigned long flags; u32 count, hash = context_compute_hash(context); struct sidtab_convert_params *convert; struct sidtab_entry *dst, *dst_convert; int rc; *sid = context_to_sid(s, context, hash); if (*sid) return 0; /* lock-free search failed: lock, re-search, and insert if not found */ spin_lock_irqsave(&s->lock, flags); rc = 0; *sid = context_to_sid(s, context, hash); if (*sid) goto out_unlock; if (unlikely(s->frozen)) { /* * This sidtab is now frozen - tell the caller to abort and * get the new one. */ rc = -ESTALE; goto out_unlock; } count = s->count; convert = s->convert; /* bail out if we already reached max entries */ rc = -EOVERFLOW; if (count >= SIDTAB_MAX) goto out_unlock; /* insert context into new entry */ rc = -ENOMEM; dst = sidtab_do_lookup(s, count, 1); if (!dst) goto out_unlock; dst->sid = index_to_sid(count); dst->hash = hash; rc = context_cpy(&dst->context, context); if (rc) goto out_unlock; /* * if we are building a new sidtab, we need to convert the context * and insert it there as well */ if (convert) { rc = -ENOMEM; dst_convert = sidtab_do_lookup(convert->target, count, 1); if (!dst_convert) { context_destroy(&dst->context); goto out_unlock; } rc = convert->func(context, &dst_convert->context, convert->args, GFP_ATOMIC); if (rc) { context_destroy(&dst->context); goto out_unlock; } dst_convert->sid = index_to_sid(count); dst_convert->hash = context_compute_hash(&dst_convert->context); convert->target->count = count + 1; hash_add_rcu(convert->target->context_to_sid, &dst_convert->list, dst_convert->hash); } if (context->len) pr_info("SELinux: Context %s is not valid (left unmapped).\n", context->str); *sid = index_to_sid(count); /* write entries before updating count */ smp_store_release(&s->count, count + 1); hash_add_rcu(s->context_to_sid, &dst->list, dst->hash); rc = 0; out_unlock: spin_unlock_irqrestore(&s->lock, flags); return rc; } static void sidtab_convert_hashtable(struct sidtab *s, u32 count) { struct sidtab_entry *entry; u32 i; for (i = 0; i < count; i++) { entry = sidtab_do_lookup(s, i, 0); entry->sid = index_to_sid(i); entry->hash = context_compute_hash(&entry->context); hash_add_rcu(s->context_to_sid, &entry->list, entry->hash); } } static int sidtab_convert_tree(union sidtab_entry_inner *edst, union sidtab_entry_inner *esrc, u32 *pos, u32 count, u32 level, struct sidtab_convert_params *convert) { int rc; u32 i; if (level != 0) { if (!edst->ptr_inner) { edst->ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_inner) return -ENOMEM; } i = 0; while (i < SIDTAB_INNER_ENTRIES && *pos < count) { rc = sidtab_convert_tree(&edst->ptr_inner->entries[i], &esrc->ptr_inner->entries[i], pos, count, level - 1, convert); if (rc) return rc; i++; } } else { if (!edst->ptr_leaf) { edst->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_leaf) return -ENOMEM; } i = 0; while (i < SIDTAB_LEAF_ENTRIES && *pos < count) { rc = convert->func(&esrc->ptr_leaf->entries[i].context, &edst->ptr_leaf->entries[i].context, convert->args, GFP_KERNEL); if (rc) return rc; (*pos)++; i++; } cond_resched(); } return 0; } int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params) { unsigned long flags; u32 count, level, pos; int rc; spin_lock_irqsave(&s->lock, flags); /* concurrent policy loads are not allowed */ if (s->convert) { spin_unlock_irqrestore(&s->lock, flags); return -EBUSY; } count = s->count; level = sidtab_level_from_count(count); /* allocate last leaf in the new sidtab (to avoid race with * live convert) */ rc = sidtab_do_lookup(params->target, count - 1, 1) ? 0 : -ENOMEM; if (rc) { spin_unlock_irqrestore(&s->lock, flags); return rc; } /* set count in case no new entries are added during conversion */ params->target->count = count; /* enable live convert of new entries */ s->convert = params; /* we can safely convert the tree outside the lock */ spin_unlock_irqrestore(&s->lock, flags); pr_info("SELinux: Converting %u SID table entries...\n", count); /* convert all entries not covered by live convert */ pos = 0; rc = sidtab_convert_tree(¶ms->target->roots[level], &s->roots[level], &pos, count, level, params); if (rc) { /* we need to keep the old table - disable live convert */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); return rc; } /* * The hashtable can also be modified in sidtab_context_to_sid() * so we must re-acquire the lock here. */ spin_lock_irqsave(&s->lock, flags); sidtab_convert_hashtable(params->target, count); spin_unlock_irqrestore(&s->lock, flags); return 0; } void sidtab_cancel_convert(struct sidtab *s) { unsigned long flags; /* cancelling policy load - disable live convert of sidtab */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); } void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock) { spin_lock_irqsave(&s->lock, *flags); s->frozen = true; s->convert = NULL; } void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock) { spin_unlock_irqrestore(&s->lock, *flags); } static void sidtab_destroy_entry(struct sidtab_entry *entry) { context_destroy(&entry->context); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 kfree(rcu_dereference_raw(entry->cache)); #endif } static void sidtab_destroy_tree(union sidtab_entry_inner entry, u32 level) { u32 i; if (level != 0) { struct sidtab_node_inner *node = entry.ptr_inner; if (!node) return; for (i = 0; i < SIDTAB_INNER_ENTRIES; i++) sidtab_destroy_tree(node->entries[i], level - 1); kfree(node); } else { struct sidtab_node_leaf *node = entry.ptr_leaf; if (!node) return; for (i = 0; i < SIDTAB_LEAF_ENTRIES; i++) sidtab_destroy_entry(&node->entries[i]); kfree(node); } } void sidtab_destroy(struct sidtab *s) { u32 i, level; for (i = 0; i < SECINITSID_NUM; i++) if (s->isids[i].set) sidtab_destroy_entry(&s->isids[i].entry); level = SIDTAB_MAX_LEVEL; while (level && !s->roots[level].ptr_inner) --level; sidtab_destroy_tree(s->roots[level], level); /* * The context_to_sid hashtable's objects are all shared * with the isids array and context tree, and so don't need * to be cleaned up here. */ } #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 void sidtab_sid2str_put(struct sidtab *s, struct sidtab_entry *entry, const char *str, u32 str_len) { struct sidtab_str_cache *cache, *victim = NULL; unsigned long flags; /* do not cache invalid contexts */ if (entry->context.len) return; spin_lock_irqsave(&s->cache_lock, flags); cache = rcu_dereference_protected(entry->cache, lockdep_is_held(&s->cache_lock)); if (cache) { /* entry in cache - just bump to the head of LRU list */ list_move(&cache->lru_member, &s->cache_lru_list); goto out_unlock; } cache = kmalloc(sizeof(struct sidtab_str_cache) + str_len, GFP_ATOMIC); if (!cache) goto out_unlock; if (s->cache_free_slots == 0) { /* pop a cache entry from the tail and free it */ victim = container_of(s->cache_lru_list.prev, struct sidtab_str_cache, lru_member); list_del(&victim->lru_member); rcu_assign_pointer(victim->parent->cache, NULL); } else { s->cache_free_slots--; } cache->parent = entry; cache->len = str_len; memcpy(cache->str, str, str_len); list_add(&cache->lru_member, &s->cache_lru_list); rcu_assign_pointer(entry->cache, cache); out_unlock: spin_unlock_irqrestore(&s->cache_lock, flags); kfree_rcu(victim, rcu_member); } int sidtab_sid2str_get(struct sidtab *s, struct sidtab_entry *entry, char **out, u32 *out_len) { struct sidtab_str_cache *cache; int rc = 0; if (entry->context.len) return -ENOENT; /* do not cache invalid contexts */ rcu_read_lock(); cache = rcu_dereference(entry->cache); if (!cache) { rc = -ENOENT; } else { *out_len = cache->len; if (out) { *out = kmemdup(cache->str, cache->len, GFP_ATOMIC); if (!*out) rc = -ENOMEM; } } rcu_read_unlock(); if (!rc && out) sidtab_sid2str_put(s, entry, *out, *out_len); return rc; } #endif /* CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 */ |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __SHMEM_FS_H #define __SHMEM_FS_H #include <linux/file.h> #include <linux/swap.h> #include <linux/mempolicy.h> #include <linux/pagemap.h> #include <linux/percpu_counter.h> #include <linux/xattr.h> #include <linux/fs_parser.h> /* inode in-kernel data */ struct shmem_inode_info { spinlock_t lock; unsigned int seals; /* shmem seals */ unsigned long flags; unsigned long alloced; /* data pages alloced to file */ unsigned long swapped; /* subtotal assigned to swap */ struct list_head shrinklist; /* shrinkable hpage inodes */ struct list_head swaplist; /* chain of maybes on swap */ struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ atomic_t stop_eviction; /* hold when working on inode */ struct inode vfs_inode; }; struct shmem_sb_info { unsigned long max_blocks; /* How many blocks are allowed */ struct percpu_counter used_blocks; /* How many are allocated */ unsigned long max_inodes; /* How many inodes are allowed */ unsigned long free_inodes; /* How many are left for allocation */ spinlock_t stat_lock; /* Serialize shmem_sb_info changes */ umode_t mode; /* Mount mode for root directory */ unsigned char huge; /* Whether to try for hugepages */ kuid_t uid; /* Mount uid for root directory */ kgid_t gid; /* Mount gid for root directory */ bool full_inums; /* If i_ino should be uint or ino_t */ ino_t next_ino; /* The next per-sb inode number to use */ ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */ struct mempolicy *mpol; /* default memory policy for mappings */ spinlock_t shrinklist_lock; /* Protects shrinklist */ struct list_head shrinklist; /* List of shinkable inodes */ unsigned long shrinklist_len; /* Length of shrinklist */ }; static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) { return container_of(inode, struct shmem_inode_info, vfs_inode); } /* * Functions in mm/shmem.c called directly from elsewhere: */ extern const struct fs_parameter_spec shmem_fs_parameters[]; extern int shmem_init(void); extern int shmem_init_fs_context(struct fs_context *fc); extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags); extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt, const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); #ifdef CONFIG_SHMEM extern bool shmem_mapping(struct address_space *mapping); #else static inline bool shmem_mapping(struct address_space *mapping) { return false; } #endif /* CONFIG_SHMEM */ extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); extern int shmem_unuse(unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse); extern bool shmem_huge_enabled(struct vm_area_struct *vma); extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); /* Flag allocation requirements to shmem_getpage */ enum sgp_type { SGP_READ, /* don't exceed i_size, don't allocate page */ SGP_CACHE, /* don't exceed i_size, may allocate page */ SGP_NOHUGE, /* like SGP_CACHE, but no huge pages */ SGP_HUGE, /* like SGP_CACHE, huge pages preferred */ SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */ SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */ }; extern int shmem_getpage(struct inode *inode, pgoff_t index, struct page **pagep, enum sgp_type sgp); static inline struct page *shmem_read_mapping_page( struct address_space *mapping, pgoff_t index) { return shmem_read_mapping_page_gfp(mapping, index, mapping_gfp_mask(mapping)); } static inline bool shmem_file(struct file *file) { if (!IS_ENABLED(CONFIG_SHMEM)) return false; if (!file || !file->f_mapping) return false; return shmem_mapping(file->f_mapping); } extern bool shmem_charge(struct inode *inode, long pages); extern void shmem_uncharge(struct inode *inode, long pages); #ifdef CONFIG_SHMEM extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, struct page **pagep); extern int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr); #else #define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ src_addr, pagep) ({ BUG(); 0; }) #define shmem_mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, \ dst_addr) ({ BUG(); 0; }) #endif #endif |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/percpu_counter.h> #include <linux/atomic.h> #include <uapi/linux/mman.h> /* * Arrange for legacy / undefined architecture specific flags to be * ignored by mmap handling code. */ #ifndef MAP_32BIT #define MAP_32BIT 0 #endif #ifndef MAP_HUGE_2MB #define MAP_HUGE_2MB 0 #endif #ifndef MAP_HUGE_1GB #define MAP_HUGE_1GB 0 #endif #ifndef MAP_UNINITIALIZED #define MAP_UNINITIALIZED 0 #endif #ifndef MAP_SYNC #define MAP_SYNC 0 #endif /* * The historical set of flags that all mmap implementations implicitly * support when a ->mmap_validate() op is not provided in file_operations. */ #define LEGACY_MAP_MASK (MAP_SHARED \ | MAP_PRIVATE \ | MAP_FIXED \ | MAP_ANONYMOUS \ | MAP_DENYWRITE \ | MAP_EXECUTABLE \ | MAP_UNINITIALIZED \ | MAP_GROWSDOWN \ | MAP_LOCKED \ | MAP_NORESERVE \ | MAP_POPULATE \ | MAP_NONBLOCK \ | MAP_STACK \ | MAP_HUGETLB \ | MAP_32BIT \ | MAP_HUGE_2MB \ | MAP_HUGE_1GB) extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; extern struct percpu_counter vm_committed_as; #ifdef CONFIG_SMP extern s32 vm_committed_as_batch; extern void mm_compute_batch(int overcommit_policy); #else #define vm_committed_as_batch 0 static inline void mm_compute_batch(int overcommit_policy) { } #endif unsigned long vm_memory_committed(void); static inline void vm_acct_memory(long pages) { percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch); } static inline void vm_unacct_memory(long pages) { vm_acct_memory(-pages); } /* * Allow architectures to handle additional protection and flag bits. The * overriding macros must be defined in the arch-specific asm/mman.h file. */ #ifndef arch_calc_vm_prot_bits #define arch_calc_vm_prot_bits(prot, pkey) 0 #endif #ifndef arch_calc_vm_flag_bits #define arch_calc_vm_flag_bits(file, flags) 0 #endif #ifndef arch_vm_get_page_prot #define arch_vm_get_page_prot(vm_flags) __pgprot(0) #endif #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have * already been masked out. * * Returns true if the prot flags are valid */ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) { return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0; } #define arch_validate_prot arch_validate_prot #endif #ifndef arch_validate_flags /* * This is called from mmap() and mprotect() with the updated vma->vm_flags. * * Returns true if the VM_* flags are valid. */ static inline bool arch_validate_flags(unsigned long flags) { return true; } #define arch_validate_flags arch_validate_flags #endif /* * Optimisation macro. It is equivalent to: * (x & bit1) ? bit2 : 0 * but this version is faster. * ("bit1" and "bit2" must be single bits) */ #define _calc_vm_trans(x, bit1, bit2) \ ((!(bit1) || !(bit2)) ? 0 : \ ((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \ : ((x) & (bit1)) / ((bit1) / (bit2)))) /* * Combine the mmap "prot" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { return _calc_vm_trans(prot, PROT_READ, VM_READ ) | _calc_vm_trans(prot, PROT_WRITE, VM_WRITE) | _calc_vm_trans(prot, PROT_EXEC, VM_EXEC) | arch_calc_vm_prot_bits(prot, pkey); } /* * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_flag_bits(struct file *file, unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_DENYWRITE, VM_DENYWRITE ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | arch_calc_vm_flag_bits(file, flags); } unsigned long vm_commit_limit(void); #endif /* _LINUX_MMAN_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PAGE_64_H #define _ASM_X86_PAGE_64_H #include <asm/page_64_types.h> #ifndef __ASSEMBLY__ #include <asm/alternative.h> /* duplicated to the one in bootmem.h */ extern unsigned long max_pfn; extern unsigned long phys_base; extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; static inline unsigned long __phys_addr_nodebug(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ x = y + ((x > y) ? phys_base : (__START_KERNEL_map - PAGE_OFFSET)); return x; } #ifdef CONFIG_DEBUG_VIRTUAL extern unsigned long __phys_addr(unsigned long); extern unsigned long __phys_addr_symbol(unsigned long); #else #define __phys_addr(x) __phys_addr_nodebug(x) #define __phys_addr_symbol(x) \ ((unsigned long)(x) - __START_KERNEL_map + phys_base) #endif #define __phys_reloc_hide(x) (x) #ifdef CONFIG_FLATMEM #define pfn_valid(pfn) ((pfn) < max_pfn) #endif void clear_page_orig(void *page); void clear_page_rep(void *page); void clear_page_erms(void *page); static inline void clear_page(void *page) { alternative_call_2(clear_page_orig, clear_page_rep, X86_FEATURE_REP_GOOD, clear_page_erms, X86_FEATURE_ERMS, "=D" (page), "0" (page) : "cc", "memory", "rax", "rcx"); } void copy_page(void *to, void *from); #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION # define __HAVE_ARCH_GATE_AREA 1 #endif #endif /* _ASM_X86_PAGE_64_H */ |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/lockref.h> #if USE_CMPXCHG_LOCKREF /* * Note that the "cmpxchg()" reloads the "old" value for the * failure case. */ #define CMPXCHG_LOOP(CODE, SUCCESS) do { \ int retry = 100; \ struct lockref old; \ BUILD_BUG_ON(sizeof(old) != 8); \ old.lock_count = READ_ONCE(lockref->lock_count); \ while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ struct lockref new = old, prev = old; \ CODE \ old.lock_count = cmpxchg64_relaxed(&lockref->lock_count, \ old.lock_count, \ new.lock_count); \ if (likely(old.lock_count == prev.lock_count)) { \ SUCCESS; \ } \ if (!--retry) \ break; \ } \ } while (0) #else #define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0) #endif /** * lockref_get - Increments reference count unconditionally * @lockref: pointer to lockref structure * * This operation is only valid if you already hold a reference * to the object, so you know the count cannot be zero. */ void lockref_get(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; , return; ); spin_lock(&lockref->lock); lockref->count++; spin_unlock(&lockref->lock); } EXPORT_SYMBOL(lockref_get); /** * lockref_get_not_zero - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero */ int lockref_get_not_zero(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count++; if (old.count <= 0) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count > 0) { lockref->count++; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_zero); /** * lockref_put_not_zero - Decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count would become zero */ int lockref_put_not_zero(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count--; if (old.count <= 1) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count > 1) { lockref->count--; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_put_not_zero); /** * lockref_get_or_lock - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero * and we got the lock instead. */ int lockref_get_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; if (old.count <= 0) break; , return 1; ); spin_lock(&lockref->lock); if (lockref->count <= 0) return 0; lockref->count++; spin_unlock(&lockref->lock); return 1; } EXPORT_SYMBOL(lockref_get_or_lock); /** * lockref_put_return - Decrement reference count if possible * @lockref: pointer to lockref structure * * Decrement the reference count and return the new value. * If the lockref was dead or locked, return an error. */ int lockref_put_return(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 0) return -1; , return new.count; ); return -1; } EXPORT_SYMBOL(lockref_put_return); /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken */ int lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , return 1; ); spin_lock(&lockref->lock); if (lockref->count <= 1) return 0; lockref->count--; spin_unlock(&lockref->lock); return 1; } EXPORT_SYMBOL(lockref_put_or_lock); /** * lockref_mark_dead - mark lockref dead * @lockref: pointer to lockref structure */ void lockref_mark_dead(struct lockref *lockref) { assert_spin_locked(&lockref->lock); lockref->count = -128; } EXPORT_SYMBOL(lockref_mark_dead); /** * lockref_get_not_dead - Increments count unless the ref is dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if lockref was dead */ int lockref_get_not_dead(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count++; if (old.count < 0) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count >= 0) { lockref->count++; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_dead); |
| 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2014 Davidlohr Bueso. */ #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/mm.h> #include <linux/vmacache.h> /* * Hash based on the pmd of addr if configured with MMU, which provides a good * hit rate for workloads with spatial locality. Otherwise, use pages. */ #ifdef CONFIG_MMU #define VMACACHE_SHIFT PMD_SHIFT #else #define VMACACHE_SHIFT PAGE_SHIFT #endif #define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK) /* * This task may be accessing a foreign mm via (for example) * get_user_pages()->find_vma(). The vmacache is task-local and this * task's vmacache pertains to a different mm (ie, its own). There is * nothing we can do here. * * Also handle the case where a kernel thread has adopted this mm via * kthread_use_mm(). That kernel thread's vmacache is not applicable to this mm. */ static inline bool vmacache_valid_mm(struct mm_struct *mm) { return current->mm == mm && !(current->flags & PF_KTHREAD); } void vmacache_update(unsigned long addr, struct vm_area_struct *newvma) { if (vmacache_valid_mm(newvma->vm_mm)) current->vmacache.vmas[VMACACHE_HASH(addr)] = newvma; } static bool vmacache_valid(struct mm_struct *mm) { struct task_struct *curr; if (!vmacache_valid_mm(mm)) return false; curr = current; if (mm->vmacache_seqnum != curr->vmacache.seqnum) { /* * First attempt will always be invalid, initialize * the new cache for this task here. */ curr->vmacache.seqnum = mm->vmacache_seqnum; vmacache_flush(curr); return false; } return true; } struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr) { int idx = VMACACHE_HASH(addr); int i; count_vm_vmacache_event(VMACACHE_FIND_CALLS); if (!vmacache_valid(mm)) return NULL; for (i = 0; i < VMACACHE_SIZE; i++) { struct vm_area_struct *vma = current->vmacache.vmas[idx]; if (vma) { #ifdef CONFIG_DEBUG_VM_VMACACHE if (WARN_ON_ONCE(vma->vm_mm != mm)) break; #endif if (vma->vm_start <= addr && vma->vm_end > addr) { count_vm_vmacache_event(VMACACHE_FIND_HITS); return vma; } } if (++idx == VMACACHE_SIZE) idx = 0; } return NULL; } #ifndef CONFIG_MMU struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, unsigned long start, unsigned long end) { int idx = VMACACHE_HASH(start); int i; count_vm_vmacache_event(VMACACHE_FIND_CALLS); if (!vmacache_valid(mm)) return NULL; for (i = 0; i < VMACACHE_SIZE; i++) { struct vm_area_struct *vma = current->vmacache.vmas[idx]; if (vma && vma->vm_start == start && vma->vm_end == end) { count_vm_vmacache_event(VMACACHE_FIND_HITS); return vma; } if (++idx == VMACACHE_SIZE) idx = 0; } return NULL; } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * https://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * * These are functions for producing 32-bit hashes for hash table lookup. * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() * are externally useful functions. Routines to test the hash are included * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. * Jozsef */ #include <linux/bitops.h> #include <linux/unaligned/packed_struct.h> /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) /* __jhash_mix -- mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ b -= a; b ^= rol32(a, 6); a += c; \ c -= b; c ^= rol32(b, 8); b += a; \ a -= c; a ^= rol32(c, 16); c += b; \ b -= a; b ^= rol32(a, 19); a += c; \ c -= b; c ^= rol32(b, 4); b += a; \ } /* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ #define __jhash_final(a, b, c) \ { \ c ^= b; c -= rol32(b, 14); \ a ^= c; a -= rol32(c, 11); \ b ^= a; b -= rol32(a, 25); \ c ^= b; c -= rol32(b, 16); \ a ^= c; a -= rol32(c, 4); \ b ^= a; b -= rol32(a, 14); \ c ^= b; c -= rol32(b, 24); \ } /* An arbitrary initial parameter */ #define JHASH_INITVAL 0xdeadbeef /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key * @initval: the previous hash, or an arbitray value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. * * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { u32 a, b, c; const u8 *k = key; /* Set up the internal state */ a = b = c = JHASH_INITVAL + length + initval; /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { a += __get_unaligned_cpu32(k); b += __get_unaligned_cpu32(k + 4); c += __get_unaligned_cpu32(k + 8); __jhash_mix(a, b, c); length -= 12; k += 12; } /* Last block: affect all 32 bits of (c) */ switch (length) { case 12: c += (u32)k[11]<<24; fallthrough; case 11: c += (u32)k[10]<<16; fallthrough; case 10: c += (u32)k[9]<<8; fallthrough; case 9: c += k[8]; fallthrough; case 8: b += (u32)k[7]<<24; fallthrough; case 7: b += (u32)k[6]<<16; fallthrough; case 6: b += (u32)k[5]<<8; fallthrough; case 5: b += k[4]; fallthrough; case 4: a += (u32)k[3]<<24; fallthrough; case 3: a += (u32)k[2]<<16; fallthrough; case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key * @initval: the previous hash, or an arbitray value * * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { u32 a, b, c; /* Set up the internal state */ a = b = c = JHASH_INITVAL + (length<<2) + initval; /* Handle most of the key */ while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); length -= 3; k += 3; } /* Handle the last 3 u32's */ switch (length) { case 3: c += k[2]; fallthrough; case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; case 0: /* Nothing left to add */ break; } return c; } /* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; b += initval; c += initval; __jhash_final(a, b, c); return c; } static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); } static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_MMU_CONTEXT_H #define _ASM_X86_MMU_CONTEXT_H #include <asm/desc.h> #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/pkeys.h> #include <trace/events/tlb.h> #include <asm/tlbflush.h> #include <asm/paravirt.h> #include <asm/debugreg.h> extern atomic64_t last_mm_ctx_id; #ifndef CONFIG_PARAVIRT_XXL static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { } #endif /* !CONFIG_PARAVIRT_XXL */ #ifdef CONFIG_PERF_EVENTS DECLARE_STATIC_KEY_FALSE(rdpmc_never_available_key); DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key); void cr4_update_pce(void *ignored); #endif #ifdef CONFIG_MODIFY_LDT_SYSCALL /* * ldt_structs can be allocated, used, and freed, but they are never * modified while live. */ struct ldt_struct { /* * Xen requires page-aligned LDTs with special permissions. This is * needed to prevent us from installing evil descriptors such as * call gates. On native, we could merge the ldt_struct and LDT * allocations, but it's not worth trying to optimize. */ struct desc_struct *entries; unsigned int nr_entries; /* * If PTI is in use, then the entries array is not mapped while we're * in user mode. The whole array will be aliased at the addressed * given by ldt_slot_va(slot). We use two slots so that we can allocate * and map, and enable a new LDT without invalidating the mapping * of an older, still-in-use LDT. * * slot will be -1 if this LDT doesn't have an alias mapping. */ int slot; }; /* * Used for LDT copy/destruction. */ static inline void init_new_context_ldt(struct mm_struct *mm) { mm->context.ldt = NULL; init_rwsem(&mm->context.ldt_usr_sem); } int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm); void destroy_context_ldt(struct mm_struct *mm); void ldt_arch_exit_mmap(struct mm_struct *mm); #else /* CONFIG_MODIFY_LDT_SYSCALL */ static inline void init_new_context_ldt(struct mm_struct *mm) { } static inline int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm) { return 0; } static inline void destroy_context_ldt(struct mm_struct *mm) { } static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { } #endif #ifdef CONFIG_MODIFY_LDT_SYSCALL extern void load_mm_ldt(struct mm_struct *mm); extern void switch_ldt(struct mm_struct *prev, struct mm_struct *next); #else static inline void load_mm_ldt(struct mm_struct *mm) { clear_LDT(); } static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) { DEBUG_LOCKS_WARN_ON(preemptible()); } #endif extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); /* * Init a new mm. Used on mm copies, like at fork() * and on mm's that are brand-new, like at execve(). */ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { mutex_init(&mm->context.lock); mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { /* pkey 0 is the default and allocated implicitly */ mm->context.pkey_allocation_map = 0x1; /* -1 means unallocated or invalid */ mm->context.execute_only_pkey = -1; } #endif init_new_context_ldt(mm); return 0; } static inline void destroy_context(struct mm_struct *mm) { destroy_context_ldt(mm); } extern void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk); #define switch_mm_irqs_off switch_mm_irqs_off #define activate_mm(prev, next) \ do { \ paravirt_activate_mm((prev), (next)); \ switch_mm((prev), (next), NULL); \ } while (0); #ifdef CONFIG_X86_32 #define deactivate_mm(tsk, mm) \ do { \ lazy_load_gs(0); \ } while (0) #else #define deactivate_mm(tsk, mm) \ do { \ load_gs_index(0); \ loadsegment(fs, 0); \ } while (0) #endif static inline void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm) { #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return; /* Duplicate the oldmm pkey state in mm: */ mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; mm->context.execute_only_pkey = oldmm->context.execute_only_pkey; #endif } static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { arch_dup_pkeys(oldmm, mm); paravirt_arch_dup_mmap(oldmm, mm); return ldt_dup_context(oldmm, mm); } static inline void arch_exit_mmap(struct mm_struct *mm) { paravirt_arch_exit_mmap(mm); ldt_arch_exit_mmap(mm); } #ifdef CONFIG_X86_64 static inline bool is_64bit_mm(struct mm_struct *mm) { return !IS_ENABLED(CONFIG_IA32_EMULATION) || !(mm->context.ia32_compat == TIF_IA32); } #else static inline bool is_64bit_mm(struct mm_struct *mm) { return false; } #endif static inline void arch_unmap(struct mm_struct *mm, unsigned long start, unsigned long end) { } /* * We only want to enforce protection keys on the current process * because we effectively have no access to PKRU for other * processes or any way to tell *which * PKRU in a threaded * process we could use. * * So do not enforce things if the VMA is not from the current * mm, or if we are in a kernel thread. */ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { /* pkeys never affect instruction fetches */ if (execute) return true; /* allow access if the VMA is not one from this process */ if (foreign || vma_is_foreign(vma)) return true; return __pkru_allows_pkey(vma_pkey(vma), write); } unsigned long __get_current_cr3_fast(void); #endif /* _ASM_X86_MMU_CONTEXT_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H #define HAVE_JUMP_LABEL_BATCH #define JUMP_LABEL_NOP_SIZE 5 #ifdef CONFIG_X86_64 # define STATIC_KEY_INIT_NOP P6_NOP5_ATOMIC #else # define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC #endif #include <asm/asm.h> #include <asm/nops.h> #ifndef __ASSEMBLY__ #include <linux/stringify.h> #include <linux/types.h> static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:" ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" ".long 1b - ., %l[l_yes] - . \n\t" _ASM_PTR "%c0 + %c1 - .\n\t" ".popsection \n\t" : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { asm_volatile_goto("1:" ".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t" "2:\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" ".long 1b - ., %l[l_yes] - . \n\t" _ASM_PTR "%c0 + %c1 - .\n\t" ".popsection \n\t" : : "i" (key), "i" (branch) : : l_yes); return false; l_yes: return true; } #else /* __ASSEMBLY__ */ .macro STATIC_JUMP_IF_TRUE target, key, def .Lstatic_jump_\@: .if \def /* Equivalent to "jmp.d32 \target" */ .byte 0xe9 .long \target - .Lstatic_jump_after_\@ .Lstatic_jump_after_\@: .else .byte STATIC_KEY_INIT_NOP .endif .pushsection __jump_table, "aw" _ASM_ALIGN .long .Lstatic_jump_\@ - ., \target - . _ASM_PTR \key - . .popsection .endm .macro STATIC_JUMP_IF_FALSE target, key, def .Lstatic_jump_\@: .if \def .byte STATIC_KEY_INIT_NOP .else /* Equivalent to "jmp.d32 \target" */ .byte 0xe9 .long \target - .Lstatic_jump_after_\@ .Lstatic_jump_after_\@: .endif .pushsection __jump_table, "aw" _ASM_ALIGN .long .Lstatic_jump_\@ - ., \target - . _ASM_PTR \key + 1 - . .popsection .endm #endif /* __ASSEMBLY__ */ #endif |
| 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Wrapper functions for accessing the file_struct fd array. */ #ifndef __LINUX_FILE_H #define __LINUX_FILE_H #include <linux/compiler.h> #include <linux/types.h> #include <linux/posix_types.h> #include <linux/errno.h> struct file; extern void fput(struct file *); extern void fput_many(struct file *, unsigned int); struct file_operations; struct task_struct; struct vfsmount; struct dentry; struct inode; struct path; extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *, const char *, int flags, const struct file_operations *); extern struct file *alloc_file_clone(struct file *, int flags, const struct file_operations *); static inline void fput_light(struct file *file, int fput_needed) { if (fput_needed) fput(file); } struct fd { struct file *file; unsigned int flags; }; #define FDPUT_FPUT 1 #define FDPUT_POS_UNLOCK 2 static inline void fdput(struct fd fd) { if (fd.flags & FDPUT_FPUT) fput(fd.file); } extern struct file *fget(unsigned int fd); extern struct file *fget_many(unsigned int fd, unsigned int refs); extern struct file *fget_raw(unsigned int fd); extern struct file *fget_task(struct task_struct *task, unsigned int fd); extern unsigned long __fdget(unsigned int fd); extern unsigned long __fdget_raw(unsigned int fd); extern unsigned long __fdget_pos(unsigned int fd); extern void __f_unlock_pos(struct file *); static inline struct fd __to_fd(unsigned long v) { return (struct fd){(struct file *)(v & ~3),v & 3}; } static inline struct fd fdget(unsigned int fd) { return __to_fd(__fdget(fd)); } static inline struct fd fdget_raw(unsigned int fd) { return __to_fd(__fdget_raw(fd)); } static inline struct fd fdget_pos(int fd) { return __to_fd(__fdget_pos(fd)); } static inline void fdput_pos(struct fd f) { if (f.flags & FDPUT_POS_UNLOCK) __f_unlock_pos(f.file); fdput(f); } extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); extern void set_close_on_exec(unsigned int fd, int flag); extern bool get_close_on_exec(unsigned int fd); extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile); extern int get_unused_fd_flags(unsigned flags); extern void put_unused_fd(unsigned int fd); extern void fd_install(unsigned int fd, struct file *file); extern int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags); static inline int receive_fd_user(struct file *file, int __user *ufd, unsigned int o_flags) { if (ufd == NULL) return -EFAULT; return __receive_fd(-1, file, ufd, o_flags); } static inline int receive_fd(struct file *file, unsigned int o_flags) { return __receive_fd(-1, file, NULL, o_flags); } static inline int receive_fd_replace(int fd, struct file *file, unsigned int o_flags) { return __receive_fd(fd, file, NULL, o_flags); } extern void flush_delayed_fput(void); extern void __fput_sync(struct file *); extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; #endif /* __LINUX_FILE_H */ |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/fs-writeback.c * * Copyright (C) 2002, Linus Torvalds. * * Contains all the functions related to writing back and waiting * upon dirty inodes against superblocks, and writing back dirty * pages against inodes. ie: data writeback. Writeout of the * inode itself is not handled here. * * 10Apr2002 Andrew Morton * Split out of fs/inode.c * Additions for address_space-based writeback */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/tracepoint.h> #include <linux/device.h> #include <linux/memcontrol.h> #include "internal.h" /* * 4MB minimal write chunk size */ #define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) /* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { long nr_pages; struct super_block *sb; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ unsigned int auto_free:1; /* free on completion */ enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ struct wb_completion *done; /* set if the caller waits */ }; /* * If an inode is constantly having its pages dirtied, but then the * updates stop dirtytime_expire_interval seconds in the past, it's * possible for the worst case time between when an inode has its * timestamps updated and when they finally get written out to be two * dirtytime_expire_intervals. We set the default to 12 hours (in * seconds), which means most of the time inodes will have their * timestamps written to disk after 12 hours, but in the worst case a * few inodes might not their timestamps updated for 24 hours. */ unsigned int dirtytime_expire_interval = 12 * 60 * 60; static inline struct inode *wb_inode(struct list_head *head) { return list_entry(head, struct inode, i_io_list); } /* * Include the creation of the trace points after defining the * wb_writeback_work structure and inline functions so that the definition * remains local to this file. */ #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); static bool wb_io_lists_populated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb)) { return false; } else { set_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(!wb->avg_write_bandwidth); atomic_long_add(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth); return true; } } static void wb_io_lists_depopulated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) && list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) { clear_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth) < 0); } } /** * inode_io_list_move_locked - move an inode onto a bdi_writeback IO list * @inode: inode to be moved * @wb: target bdi_writeback * @head: one of @wb->b_{dirty|io|more_io|dirty_time} * * Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io. * Returns %true if @inode is the first occupant of the !dirty_time IO * lists; otherwise, %false. */ static bool inode_io_list_move_locked(struct inode *inode, struct bdi_writeback *wb, struct list_head *head) { assert_spin_locked(&wb->list_lock); list_move(&inode->i_io_list, head); /* dirty_time doesn't count as dirty_io until expiration */ if (head != &wb->b_dirty_time) return wb_io_lists_populated(wb); wb_io_lists_depopulated(wb); return false; } /** * inode_io_list_del_locked - remove an inode from its bdi_writeback IO list * @inode: inode to be removed * @wb: bdi_writeback @inode is being removed from * * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and * clear %WB_has_dirty_io if all are empty afterwards. */ static void inode_io_list_del_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } static void wb_wakeup(struct bdi_writeback *wb) { spin_lock_bh(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) mod_delayed_work(bdi_wq, &wb->dwork, 0); spin_unlock_bh(&wb->work_lock); } static void finish_writeback_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { struct wb_completion *done = work->done; if (work->auto_free) kfree(work); if (done) { wait_queue_head_t *waitq = done->waitq; /* @done can't be accessed after the following dec */ if (atomic_dec_and_test(&done->cnt)) wake_up_all(waitq); } } static void wb_queue_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { trace_writeback_queue(wb, work); if (work->done) atomic_inc(&work->done->cnt); spin_lock_bh(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) { list_add_tail(&work->list, &wb->work_list); mod_delayed_work(bdi_wq, &wb->dwork, 0); } else finish_writeback_work(wb, work); spin_unlock_bh(&wb->work_lock); } /** * wb_wait_for_completion - wait for completion of bdi_writeback_works * @done: target wb_completion * * Wait for one or more work items issued to @bdi with their ->done field * set to @done, which should have been initialized with * DEFINE_WB_COMPLETION(). This function returns after all such work items * are completed. Work items which are waited upon aren't freed * automatically on completion. */ void wb_wait_for_completion(struct wb_completion *done) { atomic_dec(&done->cnt); /* put down the initial count */ wait_event(*done->waitq, !atomic_read(&done->cnt)); } #ifdef CONFIG_CGROUP_WRITEBACK /* * Parameters for foreign inode detection, see wbc_detach_inode() to see * how they're used. * * These paramters are inherently heuristical as the detection target * itself is fuzzy. All we want to do is detaching an inode from the * current owner if it's being written to by some other cgroups too much. * * The current cgroup writeback is built on the assumption that multiple * cgroups writing to the same inode concurrently is very rare and a mode * of operation which isn't well supported. As such, the goal is not * taking too long when a different cgroup takes over an inode while * avoiding too aggressive flip-flops from occasional foreign writes. * * We record, very roughly, 2s worth of IO time history and if more than * half of that is foreign, trigger the switch. The recording is quantized * to 16 slots. To avoid tiny writes from swinging the decision too much, * writes smaller than 1/8 of avg size are ignored. */ #define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */ #define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */ #define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */ #define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */ #define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */ #define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS) /* each slot's duration is 2s / 16 */ #define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2) /* if foreign slots >= 8, switch */ #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ #define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; void __inode_attach_wb(struct inode *inode, struct page *page) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; if (inode_cgwb_enabled(inode)) { struct cgroup_subsys_state *memcg_css; if (page) { memcg_css = mem_cgroup_css_from_page(page); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); } else { /* must pin memcg_css, see wb_get_create() */ memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); } } if (!wb) wb = &bdi->wb; /* * There may be multiple instances of this function racing to * update the same inode. Use cmpxchg() to tell the winner. */ if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) wb_put(wb); } EXPORT_SYMBOL_GPL(__inode_attach_wb); /** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it * @inode: inode of interest with i_lock held * * Returns @inode's wb with its list_lock held. @inode->i_lock must be * held on entry and is released on return. The returned wb is guaranteed * to stay @inode's associated wb until its list_lock is released. */ static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { while (true) { struct bdi_writeback *wb = inode_to_wb(inode); /* * inode_to_wb() association is protected by both * @inode->i_lock and @wb->list_lock but list_lock nests * outside i_lock. Drop i_lock and verify that the * association hasn't changed after acquiring list_lock. */ wb_get(wb); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); /* i_wb may have changed inbetween, can't use inode_to_wb() */ if (likely(wb == inode->i_wb)) { wb_put(wb); /* @inode already has ref */ return wb; } spin_unlock(&wb->list_lock); wb_put(wb); cpu_relax(); spin_lock(&inode->i_lock); } } /** * inode_to_wb_and_lock_list - determine an inode's wb and lock it * @inode: inode of interest * * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held * on entry. */ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { spin_lock(&inode->i_lock); return locked_inode_to_wb_and_lock_list(inode); } struct inode_switch_wbs_context { struct inode *inode; struct bdi_writeback *new_wb; struct rcu_head rcu_head; struct work_struct work; }; static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { down_write(&bdi->wb_switch_rwsem); } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { up_write(&bdi->wb_switch_rwsem); } static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; struct backing_dev_info *bdi = inode_to_bdi(inode); struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; XA_STATE(xas, &mapping->i_pages, 0); struct page *page; bool switched = false; /* * If @inode switches cgwb membership while sync_inodes_sb() is * being issued, sync_inodes_sb() might miss it. Synchronize. */ down_read(&bdi->wb_switch_rwsem); /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be * synchronizing against the i_pages lock. * * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock * gives us exclusion against all wb related operations on @inode * including IO list manipulations and stat updates. */ if (old_wb < new_wb) { spin_lock(&old_wb->list_lock); spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); } else { spin_lock(&new_wb->list_lock); spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); } spin_lock(&inode->i_lock); xa_lock_irq(&mapping->i_pages); /* * Once I_FREEING is visible under i_lock, the eviction path owns * the inode and we shouldn't modify ->i_io_list. */ if (unlikely(inode->i_state & I_FREEING)) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); /* * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points * to possibly dirty pages while PAGECACHE_TAG_WRITEBACK points to * pages actually under writeback. */ xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_DIRTY) { if (PageDirty(page)) { dec_wb_stat(old_wb, WB_RECLAIMABLE); inc_wb_stat(new_wb, WB_RECLAIMABLE); } } xas_set(&xas, 0); xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { WARN_ON_ONCE(!PageWriteback(page)); dec_wb_stat(old_wb, WB_WRITEBACK); inc_wb_stat(new_wb, WB_WRITEBACK); } wb_get(new_wb); /* * Transfer to @new_wb's IO list if necessary. The specific list * @inode was on is ignored and the inode is put on ->b_dirty which * is always correct including from ->b_dirty_time. The transfer * preserves @inode->dirtied_when ordering. */ if (!list_empty(&inode->i_io_list)) { struct inode *pos; inode_io_list_del_locked(inode, old_wb); inode->i_wb = new_wb; list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) if (time_after_eq(inode->dirtied_when, pos->dirtied_when)) break; inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev); } else { inode->i_wb = new_wb; } /* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */ inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; switched = true; skip_switch: /* * Paired with load_acquire in unlocked_inode_to_wb_begin() and * ensures that the new wb is visible if they see !I_WB_SWITCH. */ smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); up_read(&bdi->wb_switch_rwsem); if (switched) { wb_wakeup(new_wb); wb_put(old_wb); } wb_put(new_wb); iput(inode); kfree(isw); atomic_dec(&isw_nr_in_flight); } static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) { struct inode_switch_wbs_context *isw = container_of(rcu_head, struct inode_switch_wbs_context, rcu_head); /* needs to grab bh-unsafe locks, bounce to work item */ INIT_WORK(&isw->work, inode_switch_wbs_work_fn); queue_work(isw_wq, &isw->work); } /** * inode_switch_wbs - change the wb association of an inode * @inode: target inode * @new_wb_id: ID of the new wb * * Switch @inode's wb association to the wb identified by @new_wb_id. The * switching is performed asynchronously and may fail silently. */ static void inode_switch_wbs(struct inode *inode, int new_wb_id) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; /* noop if seems to be already in progress */ if (inode->i_state & I_WB_SWITCH) return; /* avoid queueing a new switch if too many are already in flight */ if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) return; isw = kzalloc(sizeof(*isw), GFP_ATOMIC); if (!isw) return; atomic_inc(&isw_nr_in_flight); /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) goto out_free; isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); if (!isw->new_wb) goto out_free; /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || inode->i_state & (I_WB_SWITCH | I_FREEING) || inode_to_wb(inode) == isw->new_wb) { spin_unlock(&inode->i_lock); goto out_free; } inode->i_state |= I_WB_SWITCH; __iget(inode); spin_unlock(&inode->i_lock); isw->inode = inode; /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); return; out_free: atomic_dec(&isw_nr_in_flight); if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); } /** * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it * @wbc: writeback_control of interest * @inode: target inode * * @inode is locked and about to be written back under the control of @wbc. * Record @inode's writeback context into @wbc and unlock the i_lock. On * writeback completion, wbc_detach_inode() should be called. This is used * to track the cgroup writeback context. */ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) { if (!inode_cgwb_enabled(inode)) { spin_unlock(&inode->i_lock); return; } wbc->wb = inode_to_wb(inode); wbc->inode = inode; wbc->wb_id = wbc->wb->memcg_css->id; wbc->wb_lcand_id = inode->i_wb_frn_winner; wbc->wb_tcand_id = 0; wbc->wb_bytes = 0; wbc->wb_lcand_bytes = 0; wbc->wb_tcand_bytes = 0; wb_get(wbc->wb); spin_unlock(&inode->i_lock); /* * A dying wb indicates that either the blkcg associated with the * memcg changed or the associated memcg is dying. In the first * case, a replacement wb should already be available and we should * refresh the wb immediately. In the second case, trying to * refresh will keep failing. */ if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode); /** * wbc_detach_inode - disassociate wbc from inode and perform foreign detection * @wbc: writeback_control of the just finished writeback * * To be called after a writeback attempt of an inode finishes and undoes * wbc_attach_and_unlock_inode(). Can be called under any context. * * As concurrent write sharing of an inode is expected to be very rare and * memcg only tracks page ownership on first-use basis severely confining * the usefulness of such sharing, cgroup writeback tracks ownership * per-inode. While the support for concurrent write sharing of an inode * is deemed unnecessary, an inode being written to by different cgroups at * different points in time is a lot more common, and, more importantly, * charging only by first-use can too readily lead to grossly incorrect * behaviors (single foreign page can lead to gigabytes of writeback to be * incorrectly attributed). * * To resolve this issue, cgroup writeback detects the majority dirtier of * an inode and transfers the ownership to it. To avoid unnnecessary * oscillation, the detection mechanism keeps track of history and gives * out the switch verdict only if the foreign usage pattern is stable over * a certain amount of time and/or writeback attempts. * * On each writeback attempt, @wbc tries to detect the majority writer * using Boyer-Moore majority vote algorithm. In addition to the byte * count from the majority voting, it also counts the bytes written for the * current wb and the last round's winner wb (max of last round's current * wb, the winner from two rounds ago, and the last round's majority * candidate). Keeping track of the historical winner helps the algorithm * to semi-reliably detect the most active writer even when it's not the * absolute majority. * * Once the winner of the round is determined, whether the winner is * foreign or not and how much IO time the round consumed is recorded in * inode->i_wb_frn_history. If the amount of recorded foreign IO time is * over a certain threshold, the switch verdict is given. */ void wbc_detach_inode(struct writeback_control *wbc) { struct bdi_writeback *wb = wbc->wb; struct inode *inode = wbc->inode; unsigned long avg_time, max_bytes, max_time; u16 history; int max_id; if (!wb) return; history = inode->i_wb_frn_history; avg_time = inode->i_wb_frn_avg_time; /* pick the winner of this round */ if (wbc->wb_bytes >= wbc->wb_lcand_bytes && wbc->wb_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_id; max_bytes = wbc->wb_bytes; } else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_lcand_id; max_bytes = wbc->wb_lcand_bytes; } else { max_id = wbc->wb_tcand_id; max_bytes = wbc->wb_tcand_bytes; } /* * Calculate the amount of IO time the winner consumed and fold it * into the running average kept per inode. If the consumed IO * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for * deciding whether to switch or not. This is to prevent one-off * small dirtiers from skewing the verdict. */ max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT, wb->avg_write_bandwidth); if (avg_time) avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) - (avg_time >> WB_FRN_TIME_AVG_SHIFT); else avg_time = max_time; /* immediate catch up on first run */ if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) { int slots; /* * The switch verdict is reached if foreign wb's consume * more than a certain proportion of IO time in a * WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot * history mask where each bit represents one sixteenth of * the period. Determine the number of slots to shift into * history from @max_time. */ slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT), (unsigned long)WB_FRN_HIST_MAX_SLOTS); history <<= slots; if (wbc->wb_id != max_id) history |= (1U << slots) - 1; if (history) trace_inode_foreign_history(inode, wbc, history); /* * Switch if the current wb isn't the consistent winner. * If there are multiple closely competing dirtiers, the * inode may switch across them repeatedly over time, which * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } /* * Multiple instances of this function may race to update the * following fields but we don't mind occassional inaccuracies. */ inode->i_wb_frn_winner = max_id; inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX); inode->i_wb_frn_history = history; wb_put(wbc->wb); wbc->wb = NULL; } EXPORT_SYMBOL_GPL(wbc_detach_inode); /** * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership * @wbc: writeback_control of the writeback in progress * @page: page being written out * @bytes: number of bytes being written out * * @bytes from @page are about to written out during the writeback * controlled by @wbc. Keep the book for foreign inode detection. See * wbc_detach_inode(). */ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes) { struct cgroup_subsys_state *css; int id; /* * pageout() path doesn't attach @wbc to the inode being written * out. This is intentional as we don't want the function to block * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ if (!wbc->wb || wbc->no_cgroup_owner) return; css = mem_cgroup_css_from_page(page); /* dead cgroups shouldn't contribute to inode ownership arbitration */ if (!(css->flags & CSS_ONLINE)) return; id = css->id; if (id == wbc->wb_id) { wbc->wb_bytes += bytes; return; } if (id == wbc->wb_lcand_id) wbc->wb_lcand_bytes += bytes; /* Boyer-Moore majority vote algorithm */ if (!wbc->wb_tcand_bytes) wbc->wb_tcand_id = id; if (id == wbc->wb_tcand_id) wbc->wb_tcand_bytes += bytes; else wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner); /** * inode_congested - test whether an inode is congested * @inode: inode to test for congestion (may be NULL) * @cong_bits: mask of WB_[a]sync_congested bits to test * * Tests whether @inode is congested. @cong_bits is the mask of congestion * bits to test and the return value is the mask of set bits. * * If cgroup writeback is enabled for @inode, the congestion state is * determined by whether the cgwb (cgroup bdi_writeback) for the blkcg * associated with @inode is congested; otherwise, the root wb's congestion * state is used. * * @inode is allowed to be NULL as this function is often called on * mapping->host which is NULL for the swapper space. */ int inode_congested(struct inode *inode, int cong_bits) { /* * Once set, ->i_wb never becomes NULL while the inode is alive. * Start transaction iff ->i_wb is visible. */ if (inode && inode_to_wb_is_valid(inode)) { struct bdi_writeback *wb; struct wb_lock_cookie lock_cookie = {}; bool congested; wb = unlocked_inode_to_wb_begin(inode, &lock_cookie); congested = wb_congested(wb, cong_bits); unlocked_inode_to_wb_end(inode, &lock_cookie); return congested; } return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); } EXPORT_SYMBOL_GPL(inode_congested); /** * wb_split_bdi_pages - split nr_pages to write according to bandwidth * @wb: target bdi_writeback to split @nr_pages to * @nr_pages: number of pages to write for the whole bdi * * Split @wb's portion of @nr_pages according to @wb's write bandwidth in * relation to the total write bandwidth of all wb's w/ dirty inodes on * @wb->bdi. */ static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); if (nr_pages == LONG_MAX) return LONG_MAX; /* * This may be called on clean wb's and proportional distribution * may not make sense, just use the original @nr_pages in those * cases. In general, we wanna err on the side of writing more. */ if (!tot_bw || this_bw >= tot_bw) return nr_pages; else return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw); } /** * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi * @bdi: target backing_dev_info * @base_work: wb_writeback_work to issue * @skip_if_busy: skip wb's which already have writeback in progress * * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's * distributed to the busy wbs according to each wb's proportion in the * total active write bandwidth of @bdi. */ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { struct bdi_writeback *last_wb = NULL; struct bdi_writeback *wb = list_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION(fallback_work_done, bdi); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; if (last_wb) { wb_put(last_wb); last_wb = NULL; } /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || list_empty(&wb->b_dirty_time))) continue; if (skip_if_busy && writeback_in_progress(wb)) continue; nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages); work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 1; wb_queue_work(wb, work); continue; } /* * If wb_tryget fails, the wb has been shutdown, skip it. * * Pin @wb so that it stays on @bdi->wb_list. This allows * continuing iteration from @wb after dropping and * regrabbing rcu read lock. */ if (!wb_tryget(wb)) continue; /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 0; work->done = &fallback_work_done; wb_queue_work(wb, work); last_wb = wb; rcu_read_unlock(); wb_wait_for_completion(&fallback_work_done); goto restart; } rcu_read_unlock(); if (last_wb) wb_put(last_wb); } /** * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id * @nr: number of pages to write, 0 for best-effort dirty flushing * @reason: reason why some writeback work initiated * @done: target wb_completion * * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id * with the specified parameters. */ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr, enum wb_reason reason, struct wb_completion *done) { struct backing_dev_info *bdi; struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; struct wb_writeback_work *work; int ret; /* lookup bdi and memcg */ bdi = bdi_get_by_id(bdi_id); if (!bdi) return -ENOENT; rcu_read_lock(); memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) { ret = -ENOENT; goto out_bdi_put; } /* * And find the associated wb. If the wb isn't there already * there's nothing to flush, don't create one. */ wb = wb_get_lookup(bdi, memcg_css); if (!wb) { ret = -ENOENT; goto out_css_put; } /* * If @nr is zero, the caller is attempting to write out most of * the currently dirty pages. Let's take the current dirty page * count and inflate it by 25% which should be large enough to * flush out most dirty pages while avoiding getting livelocked by * concurrent dirtiers. */ if (!nr) { unsigned long filepages, headroom, dirty, writeback; mem_cgroup_wb_stats(wb, &filepages, &headroom, &dirty, &writeback); nr = dirty * 10 / 8; } /* issue the writeback work */ work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); if (work) { work->nr_pages = nr; work->sync_mode = WB_SYNC_NONE; work->range_cyclic = 1; work->reason = reason; work->done = done; work->auto_free = 1; wb_queue_work(wb, work); ret = 0; } else { ret = -ENOMEM; } wb_put(wb); out_css_put: css_put(memcg_css); out_bdi_put: bdi_put(bdi); return ret; } /** * cgroup_writeback_umount - flush inode wb switches for umount * * This function is called when a super_block is about to be destroyed and * flushes in-flight inode wb switches. An inode wb switch goes through * RCU and then workqueue, so the two need to be flushed in order to ensure * that all previously scheduled switches are finished. As wb switches are * rare occurrences and synchronize_rcu() can take a while, perform * flushing iff wb switches are in flight. */ void cgroup_writeback_umount(void) { if (atomic_read(&isw_nr_in_flight)) { /* * Use rcu_barrier() to wait for all pending callbacks to * ensure that all in-flight wb switches are in the workqueue. */ rcu_barrier(); flush_workqueue(isw_wq); } } static int __init cgroup_writeback_init(void) { isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); if (!isw_wq) return -ENOMEM; return 0; } fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); return wb; } static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_lock(&wb->list_lock); return wb; } static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { return nr_pages; } static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { might_sleep(); if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) { base_work->auto_free = 0; wb_queue_work(&bdi->wb, base_work); } } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * Add in the number of potentially dirty inodes, because each inode * write can dirty pagecache in the underlying blockdev. */ static unsigned long get_nr_dirty_pages(void) { return global_node_page_state(NR_FILE_DIRTY) + get_nr_dirty_inodes(); } static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason) { if (!wb_has_dirty_io(wb)) return; /* * All callers of this function want to start writeback of all * dirty pages. Places like vmscan can call this at a very * high frequency, causing pointless allocations of tons of * work items and keeping the flusher threads busy retrieving * that work. Ensure that we only allow one of them pending and * inflight at the time. */ if (test_bit(WB_start_all, &wb->state) || test_and_set_bit(WB_start_all, &wb->state)) return; wb->start_all_reason = reason; wb_wakeup(wb); } /** * wb_start_background_writeback - start background writeback * @wb: bdi_writback to write from * * Description: * This makes sure WB_SYNC_NONE background writeback happens. When * this function returns, it is only guaranteed that for given wb * some IO is happening if we are over background dirty threshold. * Caller need not hold sb s_umount semaphore. */ void wb_start_background_writeback(struct bdi_writeback *wb) { /* * We just wake up the flusher thread. It will perform background * writeback as soon as there is no other work to do. */ trace_writeback_wake_background(wb); wb_wakeup(wb); } /* * Remove the inode from the writeback list it is on. */ void inode_io_list_del(struct inode *inode) { struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); inode_io_list_del_locked(inode, wb); spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } EXPORT_SYMBOL(inode_io_list_del); /* * mark an inode as under writeback on the sb */ void sb_mark_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (list_empty(&inode->i_wb_list)) { list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb); trace_sb_mark_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * clear an inode as under writeback on the sb */ void sb_clear_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (!list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (!list_empty(&inode->i_wb_list)) { list_del_init(&inode->i_wb_list); trace_sb_clear_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * Redirty an inode: set its when-it-was dirtied timestamp and move it to the * furthest end of its superblock's dirty-inode list. * * Before stamping the inode's ->dirtied_when, we check to see whether it is * already the most-recently-dirtied inode on the b_dirty list. If that is * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&inode->i_lock); if (!list_empty(&wb->b_dirty)) { struct inode *tail; tail = wb_inode(wb->b_dirty.next); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); inode->i_state &= ~I_SYNC_QUEUED; } static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { spin_lock(&inode->i_lock); redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); } /* * requeue inode for re-scanning after bdi->b_io list is exhausted. */ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { inode_io_list_move_locked(inode, wb, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) { inode->i_state &= ~I_SYNC; /* If inode is clean an unused, put it into LRU now... */ inode_add_lru(inode); /* Waiters must see I_SYNC cleared before being woken up */ smp_mb(); wake_up_bit(&inode->i_state, __I_SYNC); } static bool inode_dirtied_after(struct inode *inode, unsigned long t) { bool ret = time_after(inode->dirtied_when, t); #ifndef CONFIG_64BIT /* * For inodes being constantly redirtied, dirtied_when can get stuck. * It _appears_ to be in the future, but is actually in distant past. * This test is necessary to prevent such wrapped-around relative times * from permanently stopping the whole bdi writeback. */ ret = ret && time_before_eq(inode->dirtied_when, jiffies); #endif return ret; } #define EXPIRE_DIRTY_ATIME 0x0001 /* * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; struct inode *inode; int do_sb_sort = 0; int moved = 0; while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); if (inode_dirtied_after(inode, dirtied_before)) break; list_move(&inode->i_io_list, &tmp); moved++; spin_lock(&inode->i_lock); inode->i_state |= I_SYNC_QUEUED; spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; } /* just one sb in list, splice to dispatch_queue and we're done */ if (!do_sb_sort) { list_splice(&tmp, dispatch_queue); goto out; } /* Move inodes from one superblock together */ while (!list_empty(&tmp)) { sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { inode = wb_inode(pos); if (inode->i_sb == sb) list_move(&inode->i_io_list, dispatch_queue); } } out: return moved; } /* * Queue all expired dirty inodes for io, eldest first. * Before * newly dirtied b_dirty b_io b_more_io * =============> gf edc BA * After * newly dirtied b_dirty b_io b_more_io * =============> g fBAedc * | * +--> dequeue for IO */ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before) { int moved; unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); if (!work->for_sync) time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, time_expire_jif); if (moved) wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) { trace_writeback_write_inode_start(inode, wbc); ret = inode->i_sb->s_op->write_inode(inode, wbc); trace_writeback_write_inode(inode, wbc); return ret; } return 0; } /* * Wait for writeback on an inode to complete. Called with i_lock held. * Caller must make sure inode cannot go away when we drop i_lock. */ static void __inode_wait_for_writeback(struct inode *inode) __releases(inode->i_lock) __acquires(inode->i_lock) { DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); wait_queue_head_t *wqh; wqh = bit_waitqueue(&inode->i_state, __I_SYNC); while (inode->i_state & I_SYNC) { spin_unlock(&inode->i_lock); __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); spin_lock(&inode->i_lock); } } /* * Wait for writeback on an inode to complete. Caller must have inode pinned. */ void inode_wait_for_writeback(struct inode *inode) { spin_lock(&inode->i_lock); __inode_wait_for_writeback(inode); spin_unlock(&inode->i_lock); } /* * Sleep until I_SYNC is cleared. This function must be called with i_lock * held and drops it. It is aimed for callers not holding any inode reference * so once i_lock is dropped, inode can go away. */ static void inode_sleep_on_writeback(struct inode *inode) __releases(inode->i_lock) { DEFINE_WAIT(wait); wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC); int sleep; prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); sleep = inode->i_state & I_SYNC; spin_unlock(&inode->i_lock); if (sleep) schedule(); finish_wait(wqh, &wait); } /* * Find proper writeback list for the inode depending on its current state and * possibly also change of its state while we were doing writeback. Here we * handle things such as livelock prevention or fairness of writeback among * inodes. This function can be called only by flusher thread - noone else * processes all inodes in writeback lists and requeueing inodes behind flusher * thread's back can have unexpected consequences. */ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, struct writeback_control *wbc) { if (inode->i_state & I_FREEING) return; /* * Sync livelock prevention. Each inode is tagged and synced in one * shot. If still dirty, it will be redirty_tail()'ed below. Update * the dirty time to prevent enqueue and sync it again. */ if ((inode->i_state & I_DIRTY) && (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) inode->dirtied_when = jiffies; if (wbc->pages_skipped) { /* * writeback is not making progress due to locked * buffers. Skip this inode for now. */ redirty_tail_locked(inode, wb); return; } if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { /* * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. */ if (wbc->nr_to_write <= 0) { /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); } else { /* * Writeback blocked by something other than * congestion. Delay the inode for some time to * avoid spinning on the CPU (100% iowait) * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* * Filesystems can dirty the inode during writeback operations, * such as delayed allocation during submission or metadata * updates after data IO completion. */ redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_io_list_del_locked(inode, wb); } } /* * Write out an inode and its dirty pages. Do not update the writeback list * linkage. That is left to the caller. The caller is also responsible for * setting I_SYNC flag and calling inode_sync_complete() to clear it. */ static int __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct address_space *mapping = inode->i_mapping; long nr_to_write = wbc->nr_to_write; unsigned dirty; int ret; WARN_ON(!(inode->i_state & I_SYNC)); trace_writeback_single_inode_start(inode, wbc, nr_to_write); ret = do_writepages(mapping, wbc); /* * Make sure to wait on the data before writing out the metadata. * This is important for filesystems that modify metadata on data * I/O completion. We don't do it for sync(2) writeback because it has a * separate, external IO completion path and ->sync_fs for guaranteeing * inode metadata is written back correctly. */ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) { int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; } /* * If the inode has dirty timestamps and we need to write them, call * mark_inode_dirty_sync() to notify the filesystem about it and to * change I_DIRTY_TIME into I_DIRTY_SYNC. */ if ((inode->i_state & I_DIRTY_TIME) && (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { trace_writeback_lazytime(inode); mark_inode_dirty_sync(inode); } /* * Some filesystems may redirty the inode during the writeback * due to delalloc, clear dirty metadata flags right before * write_inode() */ spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* * Paired with smp_mb() in __mark_inode_dirty(). This allows * __mark_inode_dirty() to test i_state without grabbing i_lock - * either they see the I_DIRTY bits cleared or we see the dirtied * inode. * * I_DIRTY_PAGES is always cleared together above even if @mapping * still has dirty pages. The flag is reinstated after smp_mb() if * necessary. This guarantees that either __mark_inode_dirty() * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. */ smp_mb(); if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; spin_unlock(&inode->i_lock); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); if (ret == 0) ret = err; } trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } /* * Write out an inode's dirty pages. Either the caller has an active reference * on the inode or the inode has I_WILL_FREE set. * * This function is designed to be called for writing back one inode which * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode() * and does more profound writeback list handling in writeback_sb_inodes(). */ static int writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct bdi_writeback *wb; int ret = 0; spin_lock(&inode->i_lock); if (!atomic_read(&inode->i_count)) WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); else WARN_ON(inode->i_state & I_WILL_FREE); if (inode->i_state & I_SYNC) { if (wbc->sync_mode != WB_SYNC_ALL) goto out; /* * It's a data-integrity sync. We must wait. Since callers hold * inode reference or inode has I_WILL_FREE set, it cannot go * away under us. */ __inode_wait_for_writeback(inode); } WARN_ON(inode->i_state & I_SYNC); /* * Skip inode if it is clean and we have no outstanding writeback in * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this * function since flusher thread may be doing for example sync in * parallel and if we move the inode, it could get skipped. So here we * make sure inode is on some writeback list and leave it there unless * we have completely cleaned the inode. */ if (!(inode->i_state & I_DIRTY_ALL) && (wbc->sync_mode != WB_SYNC_ALL || !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); wbc_detach_inode(wbc); wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* * If inode is clean, remove it from writeback lists. Otherwise don't * touch it. See comment above for explanation. */ if (!(inode->i_state & I_DIRTY_ALL)) inode_io_list_del_locked(inode, wb); spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: spin_unlock(&inode->i_lock); return ret; } static long writeback_chunk_size(struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; /* * WB_SYNC_ALL mode does livelock avoidance by syncing dirty * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX * here avoids calling into writeback_inodes_wb() more than once. * * The intended call sequence for WB_SYNC_ALL writeback is: * * wb_writeback() * writeback_sb_inodes() <== called only once * write_cache_pages() <== called once for each inode * (quickly) tag currently dirty pages * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) pages = LONG_MAX; else { pages = min(wb->avg_write_bandwidth / 2, global_wb_domain.dirty_limit / DIRTY_SCOPE); pages = min(pages, work->nr_pages); pages = round_down(pages + MIN_WRITEBACK_PAGES, MIN_WRITEBACK_PAGES); } return pages; } /* * Write a portion of b_io inodes which belong to @sb. * * Return the number of pages and/or inodes written. * * NOTE! This is called with wb->list_lock held, and will * unlock and relock that for each inode it ends up doing * IO for. */ static long writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, struct wb_writeback_work *work) { struct writeback_control wbc = { .sync_mode = work->sync_mode, .tagged_writepages = work->tagged_writepages, .for_kupdate = work->for_kupdate, .for_background = work->for_background, .for_sync = work->for_sync, .range_cyclic = work->range_cyclic, .range_start = 0, .range_end = LLONG_MAX, }; unsigned long start_time = jiffies; long write_chunk; long total_wrote = 0; /* count both pages and inodes */ while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; long wrote; if (inode->i_sb != sb) { if (work->sb) { /* * We only want to write back data for this * superblock, move all inodes not belonging * to it back onto the dirty list. */ redirty_tail(inode, wb); continue; } /* * The inode belongs to a different superblock. * Bounce back to the caller to unpin this and * pin the next superblock. */ break; } /* * Don't bother with new inodes or inodes being freed, first * kind does not need periodic writeout yet, and for the latter * kind writeout is handled by the freer. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { /* * If this inode is locked for writeback and we are not * doing writeback-for-data-integrity, move it to * b_more_io so that writeback can proceed with the * other inodes on s_io. * * We'll have another go at writing back this inode * when we completed a full scan of b_io. */ spin_unlock(&inode->i_lock); requeue_io(inode, wb); trace_writeback_sb_inodes_requeue(inode); continue; } spin_unlock(&wb->list_lock); /* * We already requeued the inode if it had I_SYNC set and we * are doing WB_SYNC_NONE writeback. So this catches only the * WB_SYNC_ALL case. */ if (inode->i_state & I_SYNC) { /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ spin_lock(&wb->list_lock); continue; } inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(&wbc, inode); write_chunk = writeback_chunk_size(wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; /* * We use I_SYNC to pin the inode in memory. While it is set * evict_inode() will wait so the inode cannot be freed. */ __writeback_single_inode(inode, &wbc); wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; wrote = wrote < 0 ? 0 : wrote; total_wrote += wrote; if (need_resched()) { /* * We're trying to balance between building up a nice * long list of IOs to improve our merge rate, and * getting those IOs out quickly for anyone throttling * in balance_dirty_pages(). cond_resched() doesn't * unplug, so get our IOs out the door before we * give up the CPU. */ blk_flush_plug(current); cond_resched(); } /* * Requeue @inode if still dirty. Be careful as @inode may * have been switched to another wb in the meantime. */ tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) total_wrote++; requeue_inode(inode, tmp_wb, &wbc); inode_sync_complete(inode); spin_unlock(&inode->i_lock); if (unlikely(tmp_wb != wb)) { spin_unlock(&tmp_wb->list_lock); spin_lock(&wb->list_lock); } /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ if (total_wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } return total_wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long start_time = jiffies; long wrote = 0; while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; if (!trylock_super(sb)) { /* * trylock_super() may fail consistently due to * s_umount being grabbed by someone else. Don't use * requeue_io() to avoid busy retrying the inode/sb. */ redirty_tail(inode, wb); continue; } wrote += writeback_sb_inodes(sb, wb, work); up_read(&sb->s_umount); /* refer to the same tests at the end of writeback_sb_inodes */ if (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } /* Leave any unwritten inodes on b_io */ return wrote; } static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, }; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work.nr_pages; } /* * Explicit flushing or periodic writeback of "old" data. * * Define "old": the first time one of an inode's pages is dirtied, we mark the * dirtying-time in the inode's address_space. So this periodic writeback code * just walks the superblock inode list, writing back any inodes which are * older than a specific point in time. * * Try to run once per dirty_writeback_interval. But if a writeback event * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); for (;;) { /* * Stop writeback when nr_pages has been consumed */ if (work->nr_pages <= 0) break; /* * Background writeout and kupdate-style writeback may * run forever. Stop them if there is other work to do * so that e.g. sync can proceed. They'll be restarted * after the other works are all done. */ if ((work->for_background || work->for_kupdate) && !list_empty(&wb->work_list)) break; /* * For background writeout, stop when we are below the * background dirty threshold */ if (work->for_background && !wb_over_bg_thresh(wb)) break; /* * Kupdate and background works are special and we want to * include all inodes that need writing. Livelock avoidance is * handled by these works yielding to any other work so we are * safe. */ if (work->for_kupdate) { dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) dirtied_before = jiffies; trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) queue_io(wb, work, dirtied_before); if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else progress = __writeback_inodes_wb(wb, work); trace_writeback_written(wb, work); wb_update_bandwidth(wb, wb_start); /* * Did we write something? Try for more * * Dirty inodes are moved to b_io for writeback in batches. * The completion of the current batch does not necessarily * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ if (progress) continue; /* * No more inodes for IO, bail */ if (list_empty(&wb->b_more_io)) break; /* * Nothing written. Wait for some inode to * become available for writeback. Otherwise * we'll just busyloop. */ trace_writeback_wait(wb, work); inode = wb_inode(wb->b_more_io.prev); spin_lock(&inode->i_lock); spin_unlock(&wb->list_lock); /* This function drops i_lock... */ inode_sleep_on_writeback(inode); spin_lock(&wb->list_lock); } spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work->nr_pages; } /* * Return the next wb_writeback_work struct that hasn't been processed yet. */ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; spin_lock_bh(&wb->work_lock); if (!list_empty(&wb->work_list)) { work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } spin_unlock_bh(&wb->work_lock); return work; } static long wb_check_background_flush(struct bdi_writeback *wb) { if (wb_over_bg_thresh(wb)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, .sync_mode = WB_SYNC_NONE, .for_background = 1, .range_cyclic = 1, .reason = WB_REASON_BACKGROUND, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_old_data_flush(struct bdi_writeback *wb) { unsigned long expired; long nr_pages; /* * When set to zero, disable periodic writeback */ if (!dirty_writeback_interval) return 0; expired = wb->last_old_flush + msecs_to_jiffies(dirty_writeback_interval * 10); if (time_before(jiffies, expired)) return 0; wb->last_old_flush = jiffies; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, .reason = WB_REASON_PERIODIC, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_start_all(struct bdi_writeback *wb) { long nr_pages; if (!test_bit(WB_start_all, &wb->state)) return 0; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = wb_split_bdi_pages(wb, nr_pages), .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = wb->start_all_reason, }; nr_pages = wb_writeback(wb, &work); } clear_bit(WB_start_all, &wb->state); return nr_pages; } /* * Retrieve work items and do the writeback they describe */ static long wb_do_writeback(struct bdi_writeback *wb) { struct wb_writeback_work *work; long wrote = 0; set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(wb)) != NULL) { trace_writeback_exec(wb, work); wrote += wb_writeback(wb, work); finish_writeback_work(wb, work); } /* * Check for a flush-everything request */ wrote += wb_check_start_all(wb); /* * Check for periodic writeback, kupdated() style */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); clear_bit(WB_writeback_running, &wb->state); return wrote; } /* * Handle writeback of dirty data for the device backed by this bdi. Also * reschedules periodically and does kupdated style flushing. */ void wb_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, dwork); long pages_written; set_worker_desc("flush-%s", bdi_dev_name(wb->bdi)); current->flags |= PF_SWAPWRITE; if (likely(!current_is_workqueue_rescuer() || !test_bit(WB_registered, &wb->state))) { /* * The normal path. Keep writing back @wb until its * work_list is empty. Note that this path is also taken * if @wb is shutting down even when we're running off the * rescuer as work_list needs to be drained. */ do { pages_written = wb_do_writeback(wb); trace_writeback_pages_written(pages_written); } while (!list_empty(&wb->work_list)); } else { /* * bdi_wq can't get enough workers and we're running off * the emergency worker. Don't hog it. Hopefully, 1024 is * enough for efficient IO. */ pages_written = writeback_inodes_wb(wb, 1024, WB_REASON_FORKER_THREAD); trace_writeback_pages_written(pages_written); } if (!list_empty(&wb->work_list)) wb_wakeup(wb); else if (wb_has_dirty_io(wb) && dirty_writeback_interval) wb_wakeup_delayed(wb); current->flags &= ~PF_SWAPWRITE; } /* * Start writeback of `nr_pages' pages on this bdi. If `nr_pages' is zero, * write back the whole world. */ static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { struct bdi_writeback *wb; if (!bdi_has_dirty_io(bdi)) return; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, reason); } void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { rcu_read_lock(); __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wakeup the flusher threads to start writeback of all currently dirty pages */ void wakeup_flusher_threads(enum wb_reason reason) { struct backing_dev_info *bdi; /* * If we are expecting writeback progress we must submit plugged IO. */ if (blk_needs_flush_plug(current)) blk_schedule_flush_plug(current); rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wake up bdi's periodically to make sure dirtytime inodes gets * written back periodically. We deliberately do *not* check the * b_dirtytime list in wb_has_dirty_io(), since this would cause the * kernel to be constantly waking up once there are any dirtytime * inodes on the system. So instead we define a separate delayed work * function which gets called much more rarely. (By default, only * once every 12 hours.) * * If there is any other write activity going on in the file system, * this function won't be necessary. But if the only thing that has * happened on the file system is a dirtytime inode caused by an atime * update, we need this infrastructure below to make sure that inode * eventually gets pushed out to disk. */ static void wakeup_dirtytime_writeback(struct work_struct *w); static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); static void wakeup_dirtytime_writeback(struct work_struct *w) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) if (!list_empty(&wb->b_dirty_time)) wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } static int __init start_dirtytime_writeback(void) { schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); return 0; } __initcall(start_dirtytime_writeback); int dirtytime_interval_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) mod_delayed_work(system_wq, &dirtytime_work, 0); return ret; } /** * __mark_inode_dirty - internal function * * @inode: inode to mark * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) * * Mark an inode as dirty. Callers should use mark_inode_dirty or * mark_inode_dirty_sync. * * Put the inode on the super block's dirty list. * * CAREFUL! We mark it dirty unconditionally, but move it onto the * dirty list only if it is hashed or if it refers to a blockdev. * If it was not hashed, it will never be added to the dirty list * even if it is later hashed, as it will have been marked dirty already. * * In short, make sure you hash any inodes _before_ you start marking * them dirty. * * Note that for blockdevs, inode->dirtied_when represents the dirtying time of * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of * the kernel-internal blockdev inode represents the dirtying time of the * blockdev's pages. This is why for I_DIRTY_PAGES we always use * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; int dirtytime; trace_writeback_mark_inode_dirty(inode, flags); /* * Don't do this for I_DIRTY_PAGES - that doesn't actually * dirty the inode itself */ if (flags & (I_DIRTY_INODE | I_DIRTY_TIME)) { trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode) sb->s_op->dirty_inode(inode, flags); trace_writeback_dirty_inode(inode, flags); } if (flags & I_DIRTY_INODE) flags &= ~I_DIRTY_TIME; dirtytime = flags & I_DIRTY_TIME; /* * Paired with smp_mb() in __writeback_single_inode() for the * following lockless i_state test. See there for details. */ smp_mb(); if (((inode->i_state & flags) == flags) || (dirtytime && (inode->i_state & I_DIRTY_INODE))) return; spin_lock(&inode->i_lock); if (dirtytime && (inode->i_state & I_DIRTY_INODE)) goto out_unlock_inode; if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; inode_attach_wb(inode, NULL); if (flags & I_DIRTY_INODE) inode->i_state &= ~I_DIRTY_TIME; inode->i_state |= flags; /* * If the inode is queued for writeback by flush worker, just * update its dirty state. Once the flush worker is done with * the inode it will place it on the appropriate superblock * list, based upon its state. */ if (inode->i_state & I_SYNC_QUEUED) goto out_unlock_inode; /* * Only add valid (hashed) inodes to the superblock's * dirty list. Add blockdev inodes as well. */ if (!S_ISBLK(inode->i_mode)) { if (inode_unhashed(inode)) goto out_unlock_inode; } if (inode->i_state & I_FREEING) goto out_unlock_inode; /* * If the inode was already on b_dirty/b_io/b_more_io, don't * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { struct bdi_writeback *wb; struct list_head *dirty_list; bool wakeup_bdi = false; wb = locked_inode_to_wb_and_lock_list(inode); WARN((wb->bdi->capabilities & BDI_CAP_WRITEBACK) && !test_bit(WB_registered, &wb->state), "bdi-%s not registered\n", bdi_dev_name(wb->bdi)); inode->dirtied_when = jiffies; if (dirtytime) inode->dirtied_time_when = jiffies; if (inode->i_state & I_DIRTY) dirty_list = &wb->b_dirty; else dirty_list = &wb->b_dirty_time; wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); spin_unlock(&wb->list_lock); trace_writeback_dirty_inode_enqueue(inode); /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread * to make sure background write-back happens * later. */ if (wakeup_bdi && (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); return; } } out_unlock_inode: spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(__mark_inode_dirty); /* * The @s_sync_lock is used to serialise concurrent sync operations * to avoid lock contention problems with concurrent wait_sb_inodes() calls. * Concurrent callers will block on the s_sync_lock rather than doing contending * walks. The queueing maintains sync(2) required behaviour as all the IO that * has been issued up to the time this function is enter is guaranteed to be * completed by the time we have gained the lock and waited for all IO that is * in progress regardless of the order callers are granted the lock. */ static void wait_sb_inodes(struct super_block *sb) { LIST_HEAD(sync_list); /* * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); mutex_lock(&sb->s_sync_lock); /* * Splice the writeback list onto a temporary list to avoid waiting on * inodes that have started writeback after this point. * * Use rcu_read_lock() to keep the inodes around until we have a * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as * the local list because inodes can be dropped from either by writeback * completion. */ rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); list_splice_init(&sb->s_inodes_wb, &sync_list); /* * Data integrity sync. Must wait for all pages under writeback, because * there may have been pages dirtied before our sync call, but which had * writeout started before we write it out. In which case, the inode * may not be on the dirty list, but we still have to wait for that * writeout. */ while (!list_empty(&sync_list)) { struct inode *inode = list_first_entry(&sync_list, struct inode, i_wb_list); struct address_space *mapping = inode->i_mapping; /* * Move each inode back to the wb list before we drop the lock * to preserve consistency between i_wb_list and the mapping * writeback tag. Writeback completion is responsible to remove * the inode from either list once the writeback tag is cleared. */ list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb); /* * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. */ if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); spin_lock_irq(&sb->s_inode_wblist_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); /* * We keep the error status of individual mapping so that * applications can catch the writeback error using fsync(2). * See filemap_fdatawait_keep_errors() for details. */ filemap_fdatawait_keep_errors(mapping); cond_resched(); iput(inode); rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); } spin_unlock_irq(&sb->s_inode_wblist_lock); rcu_read_unlock(); mutex_unlock(&sb->s_sync_lock); } static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason, bool skip_if_busy) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, .tagged_writepages = 1, .done = &done, .nr_pages = nr, .reason = reason, }; if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); wb_wait_for_completion(&done); } /** * writeback_inodes_sb_nr - writeback dirty inodes from given super_block * @sb: the superblock * @nr: the number of pages to write * @reason: reason why some writeback work initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason) { __writeback_inodes_sb_nr(sb, nr, reason, false); } EXPORT_SYMBOL(writeback_inodes_sb_nr); /** * writeback_inodes_sb - writeback dirty inodes from given super_block * @sb: the superblock * @reason: reason why some writeback work was initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); /** * try_to_writeback_inodes_sb - try to start writeback if none underway * @sb: the superblock * @reason: reason why some writeback work was initiated * * Invoke __writeback_inodes_sb_nr if no writeback is currently underway. */ void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { if (!down_read_trylock(&sb->s_umount)) return; __writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true); up_read(&sb->s_umount); } EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this * super_block. */ void sync_inodes_sb(struct super_block *sb) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, .for_sync = 1, }; /* * Can't skip on !bdi_has_dirty() because we should wait for !dirty * inodes under writeback and I_DIRTY_TIME inodes ignored by * bdi_has_dirty() need to be written out too. */ if (bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(&done); bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk * @inode: inode to write to disk * @sync: whether the write should be synchronous or not * * This function commits an inode to disk immediately if it is dirty. This is * primarily needed by knfsd. * * The caller must either have a ref on the inode or must have set I_WILL_FREE. */ int write_inode_now(struct inode *inode, int sync) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; if (!mapping_can_writeback(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(write_inode_now); /** * sync_inode - write an inode and its pages to disk. * @inode: the inode to sync * @wbc: controls the writeback mode * * sync_inode() will write an inode and its pages to disk. It will also * correctly update the inode on its superblock's dirty inode lists and will * update inode->i_state. * * The caller must have a ref on the inode. */ int sync_inode(struct inode *inode, struct writeback_control *wbc) { return writeback_single_inode(inode, wbc); } EXPORT_SYMBOL(sync_inode); /** * sync_inode_metadata - write an inode to disk * @inode: the inode to sync * @wait: wait for I/O to complete. * * Write an inode to disk and adjust its dirty state after completion. * * Note: only writes the actual inode, no associated data or other metadata. */ int sync_inode_metadata(struct inode *inode, int wait) { struct writeback_control wbc = { .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, .nr_to_write = 0, /* metadata-only */ }; return sync_inode(inode, &wbc); } EXPORT_SYMBOL(sync_inode_metadata); |
r0 = perf_event_open(&(0x7f0000000040)={0x1, 0x80, 0x0, 0x0, 0x0, 0x0, 0x0, 0x5b, 0x0, 0xf, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x7ff, 0x0, @perf_config_ext={0x5, 0x3ff}, 0x0, 0x0, 0x0, 0x0, 0x7}, 0x0, 0xffffffffffffffff, 0xffffffffffffffff, 0x0)
ioctl$AUTOFS_DEV_IOCTL_OPENMOUNT(0xffffffffffffffff, 0xc0189374, &(0x7f0000000480)=ANY=[@ANYBLOB="010000000100000018000000", @ANYRES32=<r1=>r0, @ANYBLOB="000000800000000039f222206c653100"])
sendmsg$nl_generic(0xffffffffffffffff, 0x0, 0x20008044)
perf_event_open(&(0x7f0000000500)={0x4, 0x80, 0x76, 0x0, 0x0, 0x3f, 0x0, 0xa83, 0x38441, 0x2, 0x1, 0x1, 0x1, 0x0, 0x1, 0x1, 0x0, 0x1, 0x0, 0x0, 0x0, 0x0, 0x1, 0x0, 0x1, 0x3, 0x0, 0x0, 0x0, 0x0, 0x0, 0x1, 0x1, 0x1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x1, 0x1, 0x1, 0x0, 0x1, 0x0, 0x0, 0x0, @perf_bp={&(0x7f00000004c0)}, 0x40200, 0x4, 0x7, 0x0, 0x4, 0x3, 0x7, 0x0, 0xffff, 0x0, 0x10000}, 0xffffffffffffffff, 0x6, r0, 0x8)
syz_read_part_table(0x4, 0x3, &(0x7f0000000300)=[{0x0, 0x0, 0x7fff}, {0x0}, {&(0x7f0000000180)="5bffa097ec44ff12ea1e69793d84533c7cb8a98876a1d69640b9350e43bd6dbde6d292e3ec889a2f997ed8ca47e1ce40613b86425c9456f874799fb3e850dbcfeb73af445005e7561b8047b6d9437d7a6c73b62e7124fb2699949fe472ecbf145e1c365cd2287639641d1a0c04144114d1bc776d64b3bf20c3e73b4249f23d53201bfb8491e7b24e3c110cf6fa7d1d67d5ee06beeb1646190fdbb6bc2b1b44a917d0612a21f3a5a8a4911756e842a9b14ac53892cdeca6ea25b9228b5bc75aed64cee705e38f18640770a2a4d5d901853a031c6cc4cddff8c22897481b3c52649adbfe44f9e62e445b1bbfc9af83", 0xee}])
ioctl$TIOCGSID(0xffffffffffffffff, 0x5429, &(0x7f0000000000))
readv(r0, 0x0, 0x0)
fcntl$setlease(r1, 0x400, 0x2)
ioctl$SNDRV_TIMER_IOCTL_CONTINUE(0xffffffffffffffff, 0x54a2)
openat(0xffffffffffffff9c, &(0x7f00000002c0)='./file1\x00', 0x48000, 0x20)
openat(0xffffffffffffffff, &(0x7f0000000280)='./file0\x00', 0x20000, 0x80)